Merge commit 'v2.6.27-rc8' into genirq

90 files changed, 4255 insertions, 2568 deletions

diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
index 526128a2e622..94fabd534b03 100644
--- a/kernel/Kconfig.hz
+++ b/kernel/Kconfig.hz
@@ -55,4 +55,4 @@ config HZ
         default 1000 if HZ_1000
 
 config SCHED_HRTICK
-        def_bool HIGH_RES_TIMERS && X86
+        def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS)
diff --git a/kernel/Makefile b/kernel/Makefile
index 985ddb7da4d0..4e1d7df7c3e2 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
+obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             cpu.o exit.o itimer.o time.o softirq.o resource.o \
             sysctl.o capability.o ptrace.o timer.o user.o \
             signal.o sys.o kmod.o workqueue.o pid.o \
@@ -11,6 +11,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
             notifier.o ksysfs.o pm_qos_params.o sched_clock.o
 
+CFLAGS_REMOVE_sched.o = -mno-spe
+
 ifdef CONFIG_FTRACE
 # Do not trace debug files and internal ftrace files
 CFLAGS_REMOVE_lockdep.o = -pg
@@ -22,6 +24,7 @@ CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_sched.o = -mno-spe -pg
 endif
 
+obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
@@ -81,6 +84,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FTRACE) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
diff --git a/kernel/acct.c b/kernel/acct.c
index 91e1cfd734d2..dd68b9059418 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -75,37 +75,39 @@ int acct_parm[3] = {4, 2, 30};
 /*
  * External references and all of the globals.
  */
-static void do_acct_process(struct pid_namespace *ns, struct file *);
+static void do_acct_process(struct bsd_acct_struct *acct,
+                struct pid_namespace *ns, struct file *);
 
 /*
  * This structure is used so that all the data protected by lock
  * can be placed in the same cache line as the lock.  This primes
  * the cache line to have the data after getting the lock.
  */
-struct acct_glbs {
-        spinlock_t              lock;
+struct bsd_acct_struct {
         volatile int            active;
         volatile int            needcheck;
         struct file             *file;
         struct pid_namespace    *ns;
         struct timer_list       timer;
+        struct list_head        list;
 };
 
-static struct acct_glbs acct_globals __cacheline_aligned =
-        {__SPIN_LOCK_UNLOCKED(acct_globals.lock)};
+static DEFINE_SPINLOCK(acct_lock);
+static LIST_HEAD(acct_list);
 
 /*
  * Called whenever the timer says to check the free space.
  */
-static void acct_timeout(unsigned long unused)
+static void acct_timeout(unsigned long x)
 {
-        acct_globals.needcheck = 1;
+        struct bsd_acct_struct *acct = (struct bsd_acct_struct *)x;
+        acct->needcheck = 1;
 }
 
 /*
  * Check the amount of free space and suspend/resume accordingly.
  */
-static int check_free_space(struct file *file)
+static int check_free_space(struct bsd_acct_struct *acct, struct file *file)
 {
         struct kstatfs sbuf;
         int res;
@@ -113,11 +115,11 @@ static int check_free_space(struct file *file)
         sector_t resume;
         sector_t suspend;
 
-        spin_lock(&acct_globals.lock);
-        res = acct_globals.active;
-        if (!file || !acct_globals.needcheck)
+        spin_lock(&acct_lock);
+        res = acct->active;
+        if (!file || !acct->needcheck)
                 goto out;
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
 
         /* May block */
         if (vfs_statfs(file->f_path.dentry, &sbuf))
@@ -136,35 +138,35 @@ static int check_free_space(struct file *file)
                 act = 0;
 
         /*
-         * If some joker switched acct_globals.file under us we'ld better be
+         * If some joker switched acct->file under us we'ld better be
          * silent and _not_ touch anything.
          */
-        spin_lock(&acct_globals.lock);
-        if (file != acct_globals.file) {
+        spin_lock(&acct_lock);
+        if (file != acct->file) {
                 if (act)
                         res = act>0;
                 goto out;
         }
 
-        if (acct_globals.active) {
+        if (acct->active) {
                 if (act < 0) {
-                        acct_globals.active = 0;
+                        acct->active = 0;
                         printk(KERN_INFO "Process accounting paused\n");
                 }
         } else {
                 if (act > 0) {
-                        acct_globals.active = 1;
+                        acct->active = 1;
                         printk(KERN_INFO "Process accounting resumed\n");
                 }
         }
 
-        del_timer(&acct_globals.timer);
-        acct_globals.needcheck = 0;
-        acct_globals.timer.expires = jiffies + ACCT_TIMEOUT*HZ;
-        add_timer(&acct_globals.timer);
-        res = acct_globals.active;
+        del_timer(&acct->timer);
+        acct->needcheck = 0;
+        acct->timer.expires = jiffies + ACCT_TIMEOUT*HZ;
+        add_timer(&acct->timer);
+        res = acct->active;
 out:
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
         return res;
 }
 
@@ -172,39 +174,41 @@ out:
  * Close the old accounting file (if currently open) and then replace
  * it with file (if non-NULL).
  *
- * NOTE: acct_globals.lock MUST be held on entry and exit.
+ * NOTE: acct_lock MUST be held on entry and exit.
  */
-static void acct_file_reopen(struct file *file)
+static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
+                struct pid_namespace *ns)
 {
         struct file *old_acct = NULL;
         struct pid_namespace *old_ns = NULL;
 
-        if (acct_globals.file) {
-                old_acct = acct_globals.file;
-                old_ns = acct_globals.ns;
-                del_timer(&acct_globals.timer);
-                acct_globals.active = 0;
-                acct_globals.needcheck = 0;
-                acct_globals.file = NULL;
+        if (acct->file) {
+                old_acct = acct->file;
+                old_ns = acct->ns;
+                del_timer(&acct->timer);
+                acct->active = 0;
+                acct->needcheck = 0;
+                acct->file = NULL;
+                acct->ns = NULL;
+                list_del(&acct->list);
         }
         if (file) {
-                acct_globals.file = file;
-                acct_globals.ns = get_pid_ns(task_active_pid_ns(current));
-                acct_globals.needcheck = 0;
-                acct_globals.active = 1;
+                acct->file = file;
+                acct->ns = ns;
+                acct->needcheck = 0;
+                acct->active = 1;
+                list_add(&acct->list, &acct_list);
                 /* It's been deleted if it was used before so this is safe */
-                init_timer(&acct_globals.timer);
-                acct_globals.timer.function = acct_timeout;
-                acct_globals.timer.expires = jiffies + ACCT_TIMEOUT*HZ;
-                add_timer(&acct_globals.timer);
+                setup_timer(&acct->timer, acct_timeout, (unsigned long)acct);
+                acct->timer.expires = jiffies + ACCT_TIMEOUT*HZ;
+                add_timer(&acct->timer);
         }
         if (old_acct) {
                 mnt_unpin(old_acct->f_path.mnt);
-                spin_unlock(&acct_globals.lock);
-                do_acct_process(old_ns, old_acct);
+                spin_unlock(&acct_lock);
+                do_acct_process(acct, old_ns, old_acct);
                 filp_close(old_acct, NULL);
-                put_pid_ns(old_ns);
-                spin_lock(&acct_globals.lock);
+                spin_lock(&acct_lock);
         }
 }
 
@@ -212,6 +216,8 @@ static int acct_on(char *name)
 {
         struct file *file;
         int error;
+        struct pid_namespace *ns;
+        struct bsd_acct_struct *acct = NULL;
 
         /* Difference from BSD - they don't do O_APPEND */
         file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
@@ -228,18 +234,34 @@ static int acct_on(char *name)
                 return -EIO;
         }
 
+        ns = task_active_pid_ns(current);
+        if (ns->bacct == NULL) {
+                acct = kzalloc(sizeof(struct bsd_acct_struct), GFP_KERNEL);
+                if (acct == NULL) {
+                        filp_close(file, NULL);
+                        return -ENOMEM;
+                }
+        }
+
         error = security_acct(file);
         if (error) {
+                kfree(acct);
                 filp_close(file, NULL);
                 return error;
         }
 
-        spin_lock(&acct_globals.lock);
+        spin_lock(&acct_lock);
+        if (ns->bacct == NULL) {
+                ns->bacct = acct;
+                acct = NULL;
+        }
+
         mnt_pin(file->f_path.mnt);
-        acct_file_reopen(file);
-        spin_unlock(&acct_globals.lock);
+        acct_file_reopen(ns->bacct, file, ns);
+        spin_unlock(&acct_lock);
 
         mntput(file->f_path.mnt); /* it's pinned, now give up active reference */
+        kfree(acct);
 
         return 0;
 }
@@ -269,11 +291,17 @@ asmlinkage long sys_acct(const char __user *name)
                 error = acct_on(tmp);
                 putname(tmp);
         } else {
+                struct bsd_acct_struct *acct;
+
+                acct = task_active_pid_ns(current)->bacct;
+                if (acct == NULL)
+                        return 0;
+
                 error = security_acct(NULL);
                 if (!error) {
-                        spin_lock(&acct_globals.lock);
-                        acct_file_reopen(NULL);
-                        spin_unlock(&acct_globals.lock);
+                        spin_lock(&acct_lock);
+                        acct_file_reopen(acct, NULL, NULL);
+                        spin_unlock(&acct_lock);
                 }
         }
         return error;
@@ -288,10 +316,16 @@ asmlinkage long sys_acct(const char __user *name)
  */
 void acct_auto_close_mnt(struct vfsmount *m)
 {
-        spin_lock(&acct_globals.lock);
-        if (acct_globals.file && acct_globals.file->f_path.mnt == m)
-                acct_file_reopen(NULL);
-        spin_unlock(&acct_globals.lock);
+        struct bsd_acct_struct *acct;
+
+        spin_lock(&acct_lock);
+restart:
+        list_for_each_entry(acct, &acct_list, list)
+                if (acct->file && acct->file->f_path.mnt == m) {
+                        acct_file_reopen(acct, NULL, NULL);
+                        goto restart;
+                }
+        spin_unlock(&acct_lock);
 }
 
 /**
@@ -303,12 +337,31 @@ void acct_auto_close_mnt(struct vfsmount *m)
  */
 void acct_auto_close(struct super_block *sb)
 {
-        spin_lock(&acct_globals.lock);
-        if (acct_globals.file &&
-            acct_globals.file->f_path.mnt->mnt_sb == sb) {
-                acct_file_reopen(NULL);
+        struct bsd_acct_struct *acct;
+
+        spin_lock(&acct_lock);
+restart:
+        list_for_each_entry(acct, &acct_list, list)
+                if (acct->file && acct->file->f_path.mnt->mnt_sb == sb) {
+                        acct_file_reopen(acct, NULL, NULL);
+                        goto restart;
+                }
+        spin_unlock(&acct_lock);
+}
+
+void acct_exit_ns(struct pid_namespace *ns)
+{
+        struct bsd_acct_struct *acct;
+
+        spin_lock(&acct_lock);
+        acct = ns->bacct;
+        if (acct != NULL) {
+                if (acct->file != NULL)
+                        acct_file_reopen(acct, NULL, NULL);
+
+                kfree(acct);
         }
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
 }
 
 /*
@@ -425,7 +478,8 @@ static u32 encode_float(u64 value)
 /*
  *  do_acct_process does all actual work. Caller holds the reference to file.
  */
-static void do_acct_process(struct pid_namespace *ns, struct file *file)
+static void do_acct_process(struct bsd_acct_struct *acct,
+                struct pid_namespace *ns, struct file *file)
 {
         struct pacct_struct *pacct = &current->signal->pacct;
         acct_t ac;
@@ -440,7 +494,7 @@ static void do_acct_process(struct pid_namespace *ns, struct file *file)
          * First check to see if there is enough free_space to continue
          * the process accounting system.
          */
-        if (!check_free_space(file))
+        if (!check_free_space(acct, file))
                 return;
 
         /*
@@ -577,34 +631,46 @@ void acct_collect(long exitcode, int group_dead)
         spin_unlock_irq(&current->sighand->siglock);
 }
 
-/**
- * acct_process - now just a wrapper around do_acct_process
- * @exitcode: task exit code
- *
- * handles process accounting for an exiting task
- */
-void acct_process(void)
+static void acct_process_in_ns(struct pid_namespace *ns)
 {
         struct file *file = NULL;
-        struct pid_namespace *ns;
+        struct bsd_acct_struct *acct;
 
+        acct = ns->bacct;
         /*
          * accelerate the common fastpath:
          */
-        if (!acct_globals.file)
+        if (!acct || !acct->file)
                 return;
 
-        spin_lock(&acct_globals.lock);
-        file = acct_globals.file;
+        spin_lock(&acct_lock);
+        file = acct->file;
         if (unlikely(!file)) {
-                spin_unlock(&acct_globals.lock);
+                spin_unlock(&acct_lock);
                 return;
         }
         get_file(file);
-        ns = get_pid_ns(acct_globals.ns);
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
 
-        do_acct_process(ns, file);
+        do_acct_process(acct, ns, file);
         fput(file);
-        put_pid_ns(ns);
+}
+
+/**
+ * acct_process - now just a wrapper around acct_process_in_ns,
+ * which in turn is a wrapper around do_acct_process.
+ *
+ * handles process accounting for an exiting task
+ */
+void acct_process(void)
+{
+        struct pid_namespace *ns;
+
+        /*
+         * This loop is safe lockless, since current is still
+         * alive and holds its namespace, which in turn holds
+         * its parent.
+         */
+        for (ns = task_active_pid_ns(current); ns != NULL; ns = ns->parent)
+                acct_process_in_ns(ns);
 }
diff --git a/kernel/audit.c b/kernel/audit.c
index e092f1c0ce30..4414e93d8750 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -707,12 +707,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
                 if (status_get->mask & AUDIT_STATUS_ENABLED) {
                         err = audit_set_enabled(status_get->enabled,
                                                 loginuid, sessionid, sid);
-                        if (err < 0) return err;
+                        if (err < 0)
+                                return err;
                 }
                 if (status_get->mask & AUDIT_STATUS_FAILURE) {
                         err = audit_set_failure(status_get->failure,
                                                 loginuid, sessionid, sid);
-                        if (err < 0) return err;
+                        if (err < 0)
+                                return err;
                 }
                 if (status_get->mask & AUDIT_STATUS_PID) {
                         int new_pid = status_get->pid;
@@ -725,9 +727,12 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
                         audit_pid = new_pid;
                         audit_nlk_pid = NETLINK_CB(skb).pid;
                 }
-                if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
+                if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) {
                         err = audit_set_rate_limit(status_get->rate_limit,
                                                    loginuid, sessionid, sid);
+                        if (err < 0)
+                                return err;
+                }
                 if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
                         err = audit_set_backlog_limit(status_get->backlog_limit,
                                                       loginuid, sessionid, sid);
@@ -1366,7 +1371,7 @@ int audit_string_contains_control(const char *string, size_t len)
 {
         const unsigned char *p;
         for (p = string; p < (const unsigned char *)string + len && *p; p++) {
-                if (*p == '"' || *p < 0x21 || *p > 0x7f)
+                if (*p == '"' || *p < 0x21 || *p > 0x7e)
                         return 1;
         }
         return 0;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 98c50cc671bb..b7d354e2b0ef 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1022,8 +1022,11 @@ static void audit_update_watch(struct audit_parent *parent,
                         struct audit_buffer *ab;
                         ab = audit_log_start(NULL, GFP_KERNEL,
                                 AUDIT_CONFIG_CHANGE);
+                        audit_log_format(ab, "auid=%u ses=%u",
+                                audit_get_loginuid(current),
+                                audit_get_sessionid(current));
                         audit_log_format(ab,
-                                "op=updated rules specifying path=");
+                                " op=updated rules specifying path=");
                         audit_log_untrustedstring(ab, owatch->path);
                         audit_log_format(ab, " with dev=%u ino=%lu\n",
                                  dev, ino);
@@ -1058,7 +1061,10 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
                                 struct audit_buffer *ab;
                                 ab = audit_log_start(NULL, GFP_KERNEL,
                                         AUDIT_CONFIG_CHANGE);
-                                audit_log_format(ab, "op=remove rule path=");
+                                audit_log_format(ab, "auid=%u ses=%u",
+                                        audit_get_loginuid(current),
+                                        audit_get_sessionid(current));
+                                audit_log_format(ab, " op=remove rule path=");
                                 audit_log_untrustedstring(ab, w->path);
                                 if (r->filterkey) {
                                         audit_log_format(ab, " key=");
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index c10e7aae04d7..59cedfb040e7 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -243,7 +243,11 @@ static inline int open_arg(int flags, int mask)
 
 static int audit_match_perm(struct audit_context *ctx, int mask)
 {
-        unsigned n = ctx->major;
+        unsigned n;
+        if (unlikely(!ctx))
+                return 0;
+
+        n = ctx->major;
         switch (audit_classify_syscall(ctx->arch, n)) {
         case 0: /* native */
                 if ((mask & AUDIT_PERM_WRITE) &&
@@ -284,6 +288,10 @@ static int audit_match_filetype(struct audit_context *ctx, int which)
 {
         unsigned index = which & ~S_IFMT;
         mode_t mode = which & S_IFMT;
+
+        if (unlikely(!ctx))
+                return 0;
+
         if (index >= ctx->name_count)
                 return 0;
         if (ctx->names[index].ino == -1)
@@ -610,7 +618,7 @@ static int audit_filter_rules(struct task_struct *tsk,
                 if (!result)
                         return 0;
         }
-        if (rule->filterkey)
+        if (rule->filterkey && ctx)
                 ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
         switch (rule->action) {
         case AUDIT_NEVER:    *state = AUDIT_DISABLED;       break;
@@ -1476,7 +1484,8 @@ void audit_syscall_entry(int arch, int major,
         struct audit_context *context = tsk->audit_context;
         enum audit_state     state;
 
-        BUG_ON(!context);
+        if (unlikely(!context))
+                return;
 
         /*
          * This happens only on certain architectures that make system
@@ -2374,7 +2383,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
         struct audit_context *ctx = tsk->audit_context;
 
         if (audit_pid && t->tgid == audit_pid) {
-                if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) {
+                if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
                         audit_sig_pid = tsk->pid;
                         if (tsk->loginuid != -1)
                                 audit_sig_uid = tsk->loginuid;
diff --git a/kernel/capability.c b/kernel/capability.c
index 901e0fdc3fff..33e51e78c2d8 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -115,11 +115,208 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
         return 0;
 }
 
+#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
+
+/*
+ * Without filesystem capability support, we nominally support one process
+ * setting the capabilities of another
+ */
+static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
+                                     kernel_cap_t *pIp, kernel_cap_t *pPp)
+{
+        struct task_struct *target;
+        int ret;
+
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        if (pid && pid != task_pid_vnr(current)) {
+                target = find_task_by_vpid(pid);
+                if (!target) {
+                        ret = -ESRCH;
+                        goto out;
+                }
+        } else
+                target = current;
+
+        ret = security_capget(target, pEp, pIp, pPp);
+
+out:
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        return ret;
+}
+
+/*
+ * cap_set_pg - set capabilities for all processes in a given process
+ * group.  We call this holding task_capability_lock and tasklist_lock.
+ */
+static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
+                             kernel_cap_t *inheritable,
+                             kernel_cap_t *permitted)
+{
+        struct task_struct *g, *target;
+        int ret = -EPERM;
+        int found = 0;
+        struct pid *pgrp;
+
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        pgrp = find_vpid(pgrp_nr);
+        do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
+                target = g;
+                while_each_thread(g, target) {
+                        if (!security_capset_check(target, effective,
+                                                   inheritable, permitted)) {
+                                security_capset_set(target, effective,
+                                                    inheritable, permitted);
+                                ret = 0;
+                        }
+                        found = 1;
+                }
+        } while_each_pid_task(pgrp, PIDTYPE_PGID, g);
+
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        if (!found)
+                ret = 0;
+        return ret;
+}
+
+/*
+ * cap_set_all - set capabilities for all processes other than init
+ * and self.  We call this holding task_capability_lock and tasklist_lock.
+ */
+static inline int cap_set_all(kernel_cap_t *effective,
+                              kernel_cap_t *inheritable,
+                              kernel_cap_t *permitted)
+{
+        struct task_struct *g, *target;
+        int ret = -EPERM;
+        int found = 0;
+
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        do_each_thread(g, target) {
+                if (target == current
+                    || is_container_init(target->group_leader))
+                        continue;
+                found = 1;
+                if (security_capset_check(target, effective, inheritable,
+                                          permitted))
+                        continue;
+                ret = 0;
+                security_capset_set(target, effective, inheritable, permitted);
+        } while_each_thread(g, target);
+
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        if (!found)
+                ret = 0;
+
+        return ret;
+}
+
+/*
+ * Given the target pid does not refer to the current process we
+ * need more elaborate support... (This support is not present when
+ * filesystem capabilities are configured.)
+ */
+static inline int do_sys_capset_other_tasks(pid_t pid, kernel_cap_t *effective,
+                                            kernel_cap_t *inheritable,
+                                            kernel_cap_t *permitted)
+{
+        struct task_struct *target;
+        int ret;
+
+        if (!capable(CAP_SETPCAP))
+                return -EPERM;
+
+        if (pid == -1)            /* all procs other than current and init */
+                return cap_set_all(effective, inheritable, permitted);
+
+        else if (pid < 0)                    /* all procs in process group */
+                return cap_set_pg(-pid, effective, inheritable, permitted);
+
+        /* target != current */
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        target = find_task_by_vpid(pid);
+        if (!target)
+                ret = -ESRCH;
+        else {
+                ret = security_capset_check(target, effective, inheritable,
+                                            permitted);
+
+                /* having verified that the proposed changes are legal,
+                   we now put them into effect. */
+                if (!ret)
+                        security_capset_set(target, effective, inheritable,
+                                            permitted);
+        }
+
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        return ret;
+}
+
+#else /* ie., def CONFIG_SECURITY_FILE_CAPABILITIES */
+
 /*
- * For sys_getproccap() and sys_setproccap(), any of the three
- * capability set pointers may be NULL -- indicating that that set is
- * uninteresting and/or not to be changed.
+ * If we have configured with filesystem capability support, then the
+ * only thing that can change the capabilities of the current process
+ * is the current process. As such, we can't be in this code at the
+ * same time as we are in the process of setting capabilities in this
+ * process. The net result is that we can limit our use of locks to
+ * when we are reading the caps of another process.
  */
+static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
+                                     kernel_cap_t *pIp, kernel_cap_t *pPp)
+{
+        int ret;
+
+        if (pid && (pid != task_pid_vnr(current))) {
+                struct task_struct *target;
+
+                spin_lock(&task_capability_lock);
+                read_lock(&tasklist_lock);
+
+                target = find_task_by_vpid(pid);
+                if (!target)
+                        ret = -ESRCH;
+                else
+                        ret = security_capget(target, pEp, pIp, pPp);
+
+                read_unlock(&tasklist_lock);
+                spin_unlock(&task_capability_lock);
+        } else
+                ret = security_capget(current, pEp, pIp, pPp);
+
+        return ret;
+}
+
+/*
+ * With filesystem capability support configured, the kernel does not
+ * permit the changing of capabilities in one process by another
+ * process. (CAP_SETPCAP has much less broad semantics when configured
+ * this way.)
+ */
+static inline int do_sys_capset_other_tasks(pid_t pid,
+                                            kernel_cap_t *effective,
+                                            kernel_cap_t *inheritable,
+                                            kernel_cap_t *permitted)
+{
+        return -EPERM;
+}
+
+#endif /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */
 
 /*
  * Atomically modify the effective capabilities returning the original
@@ -155,7 +352,6 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
 {
         int ret = 0;
         pid_t pid;
-        struct task_struct *target;
         unsigned tocopy;
         kernel_cap_t pE, pI, pP;
 
@@ -169,23 +365,7 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
         if (pid < 0)
                 return -EINVAL;
 
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        if (pid && pid != task_pid_vnr(current)) {
-                target = find_task_by_vpid(pid);
-                if (!target) {
-                        ret = -ESRCH;
-                        goto out;
-                }
-        } else
-                target = current;
-
-        ret = security_capget(target, &pE, &pI, &pP);
-
-out:
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
+        ret = cap_get_target_pid(pid, &pE, &pI, &pP);
 
         if (!ret) {
                 struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
@@ -216,7 +396,6 @@ out:
                  * before modification is attempted and the application
                  * fails.
                  */
-
                 if (copy_to_user(dataptr, kdata, tocopy
                                  * sizeof(struct __user_cap_data_struct))) {
                         return -EFAULT;
@@ -226,70 +405,8 @@ out:
         return ret;
 }
 
-/*
- * cap_set_pg - set capabilities for all processes in a given process
- * group.  We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
-                              kernel_cap_t *inheritable,
-                              kernel_cap_t *permitted)
-{
-        struct task_struct *g, *target;
-        int ret = -EPERM;
-        int found = 0;
-        struct pid *pgrp;
-
-        pgrp = find_vpid(pgrp_nr);
-        do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
-                target = g;
-                while_each_thread(g, target) {
-                        if (!security_capset_check(target, effective,
-                                                        inheritable,
-                                                        permitted)) {
-                                security_capset_set(target, effective,
-                                                        inheritable,
-                                                        permitted);
-                                ret = 0;
-                        }
-                        found = 1;
-                }
-        } while_each_pid_task(pgrp, PIDTYPE_PGID, g);
-
-        if (!found)
-                ret = 0;
-        return ret;
-}
-
-/*
- * cap_set_all - set capabilities for all processes other than init
- * and self.  We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_all(kernel_cap_t *effective,
-                               kernel_cap_t *inheritable,
-                               kernel_cap_t *permitted)
-{
-     struct task_struct *g, *target;
-     int ret = -EPERM;
-     int found = 0;
-
-     do_each_thread(g, target) {
-             if (target == current || is_container_init(target->group_leader))
-                     continue;
-             found = 1;
-             if (security_capset_check(target, effective, inheritable,
-                                                permitted))
-                     continue;
-             ret = 0;
-             security_capset_set(target, effective, inheritable, permitted);
-     } while_each_thread(g, target);
-
-     if (!found)
-             ret = 0;
-     return ret;
-}
-
 /**
- * sys_capset - set capabilities for a process or a group of processes
+ * sys_capset - set capabilities for a process or (*) a group of processes
  * @header: pointer to struct that contains capability version and
  *      target pid data
  * @data: pointer to struct that contains the effective, permitted,
@@ -313,7 +430,6 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
         struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
         unsigned i, tocopy;
         kernel_cap_t inheritable, permitted, effective;
-        struct task_struct *target;
         int ret;
         pid_t pid;
 
@@ -324,9 +440,6 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
         if (get_user(pid, &header->pid))
                 return -EFAULT;
 
-        if (pid && pid != task_pid_vnr(current) && !capable(CAP_SETPCAP))
-                return -EPERM;
-
         if (copy_from_user(&kdata, data, tocopy
                            * sizeof(struct __user_cap_data_struct))) {
                 return -EFAULT;
@@ -344,55 +457,51 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
                 i++;
         }
 
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        if (pid > 0 && pid != task_pid_vnr(current)) {
-                target = find_task_by_vpid(pid);
-                if (!target) {
-                        ret = -ESRCH;
-                        goto out;
-                }
-        } else
-                target = current;
-
-        ret = 0;
-
-        /* having verified that the proposed changes are legal,
-           we now put them into effect. */
-        if (pid < 0) {
-                if (pid == -1)  /* all procs other than current and init */
-                        ret = cap_set_all(&effective, &inheritable, &permitted);
+        if (pid && (pid != task_pid_vnr(current)))
+                ret = do_sys_capset_other_tasks(pid, &effective, &inheritable,
+                                                &permitted);
+        else {
+                /*
+                 * This lock is required even when filesystem
+                 * capability support is configured - it protects the
+                 * sys_capget() call from returning incorrect data in
+                 * the case that the targeted process is not the
+                 * current one.
+                 */
+                spin_lock(&task_capability_lock);
 
-                else            /* all procs in process group */
-                        ret = cap_set_pg(-pid, &effective, &inheritable,
-                                         &permitted);
-        } else {
-                ret = security_capset_check(target, &effective, &inheritable,
+                ret = security_capset_check(current, &effective, &inheritable,
                                             &permitted);
+                /*
+                 * Having verified that the proposed changes are
+                 * legal, we now put them into effect.
+                 */
                 if (!ret)
-                        security_capset_set(target, &effective, &inheritable,
+                        security_capset_set(current, &effective, &inheritable,
                                             &permitted);
+                spin_unlock(&task_capability_lock);
         }
 
-out:
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
 
         return ret;
 }
 
-int __capable(struct task_struct *t, int cap)
+/**
+ * capable - Determine if the current task has a superior capability in effect
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+int capable(int cap)
 {
-        if (security_capable(t, cap) == 0) {
-                t->flags |= PF_SUPERPRIV;
+        if (has_capability(current, cap)) {
+                current->flags |= PF_SUPERPRIV;
                 return 1;
         }
         return 0;
 }
-
-int capable(int cap)
-{
-        return __capable(current, cap);
-}
 EXPORT_SYMBOL(capable);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 15ac0e1e4f4d..a0123d75ec9a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -45,6 +45,7 @@
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
+#include <linux/namei.h>
 
 #include <asm/atomic.h>
 
@@ -89,11 +90,7 @@ struct cgroupfs_root {
         /* Hierarchy-specific flags */
         unsigned long flags;
 
-        /* The path to use for release notifications. No locking
-         * between setting and use - so if userspace updates this
-         * while child cgroups exist, you could miss a
-         * notification. We ensure that it's always a valid
-         * NUL-terminated string */
+        /* The path to use for release notifications. */
         char release_agent_path[PATH_MAX];
 };
 
@@ -118,7 +115,7 @@ static int root_count;
  * extra work in the fork/exit path if none of the subsystems need to
  * be called.
  */
-static int need_forkexit_callback;
+static int need_forkexit_callback __read_mostly;
 static int need_mm_owner_callback __read_mostly;
 
 /* convenient tests for these bits */
@@ -220,7 +217,7 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
  * compiled into their kernel but not actually in use */
-static int use_task_css_set_links;
+static int use_task_css_set_links __read_mostly;
 
 /* When we create or destroy a css_set, the operation simply
  * takes/releases a reference count on all the cgroups referenced
@@ -241,17 +238,20 @@ static int use_task_css_set_links;
  */
 static void unlink_css_set(struct css_set *cg)
 {
+        struct cg_cgroup_link *link;
+        struct cg_cgroup_link *saved_link;
+
         write_lock(&css_set_lock);
         hlist_del(&cg->hlist);
         css_set_count--;
-        while (!list_empty(&cg->cg_links)) {
-                struct cg_cgroup_link *link;
-                link = list_entry(cg->cg_links.next,
-                                  struct cg_cgroup_link, cg_link_list);
+
+        list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+                                 cg_link_list) {
                 list_del(&link->cg_link_list);
                 list_del(&link->cgrp_link_list);
                 kfree(link);
         }
+
         write_unlock(&css_set_lock);
 }
 
@@ -355,6 +355,17 @@ static struct css_set *find_existing_css_set(
         return NULL;
 }
 
+static void free_cg_links(struct list_head *tmp)
+{
+        struct cg_cgroup_link *link;
+        struct cg_cgroup_link *saved_link;
+
+        list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
+                list_del(&link->cgrp_link_list);
+                kfree(link);
+        }
+}
+
 /*
  * allocate_cg_links() allocates "count" cg_cgroup_link structures
  * and chains them on tmp through their cgrp_link_list fields. Returns 0 on
@@ -368,13 +379,7 @@ static int allocate_cg_links(int count, struct list_head *tmp)
         for (i = 0; i < count; i++) {
                 link = kmalloc(sizeof(*link), GFP_KERNEL);
                 if (!link) {
-                        while (!list_empty(tmp)) {
-                                link = list_entry(tmp->next,
-                                                  struct cg_cgroup_link,
-                                                  cgrp_link_list);
-                                list_del(&link->cgrp_link_list);
-                                kfree(link);
-                        }
+                        free_cg_links(tmp);
                         return -ENOMEM;
                 }
                 list_add(&link->cgrp_link_list, tmp);
@@ -382,18 +387,6 @@ static int allocate_cg_links(int count, struct list_head *tmp)
         return 0;
 }
 
-static void free_cg_links(struct list_head *tmp)
-{
-        while (!list_empty(tmp)) {
-                struct cg_cgroup_link *link;
-                link = list_entry(tmp->next,
-                                  struct cg_cgroup_link,
-                                  cgrp_link_list);
-                list_del(&link->cgrp_link_list);
-                kfree(link);
-        }
-}
-
 /*
  * find_css_set() takes an existing cgroup group and a
  * cgroup object, and returns a css_set object that's
@@ -415,11 +408,11 @@ static struct css_set *find_css_set(
 
         /* First see if we already have a cgroup group that matches
          * the desired set */
-        write_lock(&css_set_lock);
+        read_lock(&css_set_lock);
         res = find_existing_css_set(oldcg, cgrp, template);
         if (res)
                 get_css_set(res);
-        write_unlock(&css_set_lock);
+        read_unlock(&css_set_lock);
 
         if (res)
                 return res;
@@ -507,10 +500,6 @@ static struct css_set *find_css_set(
  * knows that the cgroup won't be removed, as cgroup_rmdir()
  * needs that mutex.
  *
- * The cgroup_common_file_write handler for operations that modify
- * the cgroup hierarchy holds cgroup_mutex across the entire operation,
- * single threading all such cgroup modifications across the system.
- *
  * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
  * (usually) take cgroup_mutex.  These are the two most performance
  * critical pieces of code here.  The exception occurs on cgroup_exit(),
@@ -962,7 +951,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
         struct super_block *sb;
         struct cgroupfs_root *root;
         struct list_head tmp_cg_links;
-        INIT_LIST_HEAD(&tmp_cg_links);
 
         /* First find the desired set of subsystems */
         ret = parse_cgroupfs_options(data, &opts);
@@ -1093,6 +1081,8 @@ static void cgroup_kill_sb(struct super_block *sb) {
         struct cgroupfs_root *root = sb->s_fs_info;
         struct cgroup *cgrp = &root->top_cgroup;
         int ret;
+        struct cg_cgroup_link *link;
+        struct cg_cgroup_link *saved_link;
 
         BUG_ON(!root);
 
@@ -1112,10 +1102,9 @@ static void cgroup_kill_sb(struct super_block *sb) {
          * root cgroup
          */
         write_lock(&css_set_lock);
-        while (!list_empty(&cgrp->css_sets)) {
-                struct cg_cgroup_link *link;
-                link = list_entry(cgrp->css_sets.next,
-                                  struct cg_cgroup_link, cgrp_link_list);
+
+        list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
+                                 cgrp_link_list) {
                 list_del(&link->cg_link_list);
                 list_del(&link->cgrp_link_list);
                 kfree(link);
@@ -1281,18 +1270,14 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 }
 
 /*
- * Attach task with pid 'pid' to cgroup 'cgrp'. Call with
- * cgroup_mutex, may take task_lock of task
+ * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
+ * held. May take task_lock of task
  */
-static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf)
+static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
 {
-        pid_t pid;
         struct task_struct *tsk;
         int ret;
 
-        if (sscanf(pidbuf, "%d", &pid) != 1)
-                return -EIO;
-
         if (pid) {
                 rcu_read_lock();
                 tsk = find_task_by_vpid(pid);
@@ -1318,6 +1303,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf)
         return ret;
 }
 
+static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
+{
+        int ret;
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+        ret = attach_task_by_pid(cgrp, pid);
+        cgroup_unlock();
+        return ret;
+}
+
 /* The various types of files and directories in a cgroup file system */
 enum cgroup_filetype {
         FILE_ROOT,
@@ -1327,12 +1322,54 @@ enum cgroup_filetype {
         FILE_RELEASE_AGENT,
 };
 
+/**
+ * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
+ * @cgrp: the cgroup to be checked for liveness
+ *
+ * On success, returns true; the lock should be later released with
+ * cgroup_unlock(). On failure returns false with no lock held.
+ */
+bool cgroup_lock_live_group(struct cgroup *cgrp)
+{
+        mutex_lock(&cgroup_mutex);
+        if (cgroup_is_removed(cgrp)) {
+                mutex_unlock(&cgroup_mutex);
+                return false;
+        }
+        return true;
+}
+
+static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
+                                      const char *buffer)
+{
+        BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+        strcpy(cgrp->root->release_agent_path, buffer);
+        cgroup_unlock();
+        return 0;
+}
+
+static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
+                                     struct seq_file *seq)
+{
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+        seq_puts(seq, cgrp->root->release_agent_path);
+        seq_putc(seq, '\n');
+        cgroup_unlock();
+        return 0;
+}
+
+/* A buffer size big enough for numbers or short strings */
+#define CGROUP_LOCAL_BUFFER_SIZE 64
+
 static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
                                 struct file *file,
                                 const char __user *userbuf,
                                 size_t nbytes, loff_t *unused_ppos)
 {
-        char buffer[64];
+        char buffer[CGROUP_LOCAL_BUFFER_SIZE];
         int retval = 0;
         char *end;
 
@@ -1361,68 +1398,39 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
         return retval;
 }
 
-static ssize_t cgroup_common_file_write(struct cgroup *cgrp,
-                                           struct cftype *cft,
-                                           struct file *file,
-                                           const char __user *userbuf,
-                                           size_t nbytes, loff_t *unused_ppos)
+static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
+                                   struct file *file,
+                                   const char __user *userbuf,
+                                   size_t nbytes, loff_t *unused_ppos)
 {
-        enum cgroup_filetype type = cft->private;
-        char *buffer;
+        char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
         int retval = 0;
+        size_t max_bytes = cft->max_write_len;
+        char *buffer = local_buffer;
 
-        if (nbytes >= PATH_MAX)
+        if (!max_bytes)
+                max_bytes = sizeof(local_buffer) - 1;
+        if (nbytes >= max_bytes)
                 return -E2BIG;
-
-        /* +1 for nul-terminator */
-        buffer = kmalloc(nbytes + 1, GFP_KERNEL);
-        if (buffer == NULL)
-                return -ENOMEM;
-
-        if (copy_from_user(buffer, userbuf, nbytes)) {
+        /* Allocate a dynamic buffer if we need one */
+        if (nbytes >= sizeof(local_buffer)) {
+                buffer = kmalloc(nbytes + 1, GFP_KERNEL);
+                if (buffer == NULL)
+                        return -ENOMEM;
+        }
+        if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
                 retval = -EFAULT;
-                goto out1;
+                goto out;
         }
-        buffer[nbytes] = 0;     /* nul-terminate */
-        strstrip(buffer);       /* strip -just- trailing whitespace */
 
-        mutex_lock(&cgroup_mutex);
-
-        /*
-         * This was already checked for in cgroup_file_write(), but
-         * check again now we're holding cgroup_mutex.
-         */
-        if (cgroup_is_removed(cgrp)) {
-                retval = -ENODEV;
-                goto out2;
-        }
-
-        switch (type) {
-        case FILE_TASKLIST:
-                retval = attach_task_by_pid(cgrp, buffer);
-                break;
-        case FILE_NOTIFY_ON_RELEASE:
-                clear_bit(CGRP_RELEASABLE, &cgrp->flags);
-                if (simple_strtoul(buffer, NULL, 10) != 0)
-                        set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
-                else
-                        clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
-                break;
-        case FILE_RELEASE_AGENT:
-                BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
-                strcpy(cgrp->root->release_agent_path, buffer);
-                break;
-        default:
-                retval = -EINVAL;
-                goto out2;
-        }
-
-        if (retval == 0)
+        buffer[nbytes] = 0;     /* nul-terminate */
+        strstrip(buffer);
+        retval = cft->write_string(cgrp, cft, buffer);
+        if (!retval)
                 retval = nbytes;
-out2:
-        mutex_unlock(&cgroup_mutex);
-out1:
-        kfree(buffer);
+out:
+        if (buffer != local_buffer)
+                kfree(buffer);
         return retval;
 }
 
@@ -1438,6 +1446,8 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
                 return cft->write(cgrp, cft, file, buf, nbytes, ppos);
         if (cft->write_u64 || cft->write_s64)
                 return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
+        if (cft->write_string)
+                return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
         if (cft->trigger) {
                 int ret = cft->trigger(cgrp, (unsigned int)cft->private);
                 return ret ? ret : nbytes;
@@ -1450,7 +1460,7 @@ static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
                                char __user *buf, size_t nbytes,
                                loff_t *ppos)
 {
-        char tmp[64];
+        char tmp[CGROUP_LOCAL_BUFFER_SIZE];
         u64 val = cft->read_u64(cgrp, cft);
         int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
 
@@ -1462,56 +1472,13 @@ static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
                                char __user *buf, size_t nbytes,
                                loff_t *ppos)
 {
-        char tmp[64];
+        char tmp[CGROUP_LOCAL_BUFFER_SIZE];
         s64 val = cft->read_s64(cgrp, cft);
         int len = sprintf(tmp, "%lld\n", (long long) val);
 
         return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
 }
 
-static ssize_t cgroup_common_file_read(struct cgroup *cgrp,
-                                          struct cftype *cft,
-                                          struct file *file,
-                                          char __user *buf,
-                                          size_t nbytes, loff_t *ppos)
-{
-        enum cgroup_filetype type = cft->private;
-        char *page;
-        ssize_t retval = 0;
-        char *s;
-
-        if (!(page = (char *)__get_free_page(GFP_KERNEL)))
-                return -ENOMEM;
-
-        s = page;
-
-        switch (type) {
-        case FILE_RELEASE_AGENT:
-        {
-                struct cgroupfs_root *root;
-                size_t n;
-                mutex_lock(&cgroup_mutex);
-                root = cgrp->root;
-                n = strnlen(root->release_agent_path,
-                            sizeof(root->release_agent_path));
-                n = min(n, (size_t) PAGE_SIZE);
-                strncpy(s, root->release_agent_path, n);
-                mutex_unlock(&cgroup_mutex);
-                s += n;
-                break;
-        }
-        default:
-                retval = -EINVAL;
-                goto out;
-        }
-        *s++ = '\n';
-
-        retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
-out:
-        free_page((unsigned long)page);
-        return retval;
-}
-
 static ssize_t cgroup_file_read(struct file *file, char __user *buf,
                                    size_t nbytes, loff_t *ppos)
 {
@@ -1560,7 +1527,7 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
         return cft->read_seq_string(state->cgroup, cft, m);
 }
 
-int cgroup_seqfile_release(struct inode *inode, struct file *file)
+static int cgroup_seqfile_release(struct inode *inode, struct file *file)
 {
         struct seq_file *seq = file->private_data;
         kfree(seq->private);
@@ -1569,6 +1536,7 @@ int cgroup_seqfile_release(struct inode *inode, struct file *file)
 
 static struct file_operations cgroup_seqfile_operations = {
         .read = seq_read,
+        .write = cgroup_file_write,
         .llseek = seq_lseek,
         .release = cgroup_seqfile_release,
 };
@@ -1756,15 +1724,11 @@ int cgroup_add_files(struct cgroup *cgrp,
 int cgroup_task_count(const struct cgroup *cgrp)
 {
         int count = 0;
-        struct list_head *l;
+        struct cg_cgroup_link *link;
 
         read_lock(&css_set_lock);
-        l = cgrp->css_sets.next;
-        while (l != &cgrp->css_sets) {
-                struct cg_cgroup_link *link =
-                        list_entry(l, struct cg_cgroup_link, cgrp_link_list);
+        list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
                 count += atomic_read(&link->cg->ref.refcount);
-                l = l->next;
         }
         read_unlock(&css_set_lock);
         return count;
@@ -2227,6 +2191,18 @@ static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
         return notify_on_release(cgrp);
 }
 
+static int cgroup_write_notify_on_release(struct cgroup *cgrp,
+                                          struct cftype *cft,
+                                          u64 val)
+{
+        clear_bit(CGRP_RELEASABLE, &cgrp->flags);
+        if (val)
+                set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+        else
+                clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+        return 0;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -2235,7 +2211,7 @@ static struct cftype files[] = {
                 .name = "tasks",
                 .open = cgroup_tasks_open,
                 .read = cgroup_tasks_read,
-                .write = cgroup_common_file_write,
+                .write_u64 = cgroup_tasks_write,
                 .release = cgroup_tasks_release,
                 .private = FILE_TASKLIST,
         },
@@ -2243,15 +2219,16 @@ static struct cftype files[] = {
         {
                 .name = "notify_on_release",
                 .read_u64 = cgroup_read_notify_on_release,
-                .write = cgroup_common_file_write,
+                .write_u64 = cgroup_write_notify_on_release,
                 .private = FILE_NOTIFY_ON_RELEASE,
         },
 };
 
 static struct cftype cft_release_agent = {
         .name = "release_agent",
-        .read = cgroup_common_file_read,
-        .write = cgroup_common_file_write,
+        .read_seq_string = cgroup_release_agent_show,
+        .write_string = cgroup_release_agent_write,
+        .max_write_len = PATH_MAX,
         .private = FILE_RELEASE_AGENT,
 };
 
@@ -2391,7 +2368,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         return cgroup_create(c_parent, dentry, mode | S_IFDIR);
 }
 
-static inline int cgroup_has_css_refs(struct cgroup *cgrp)
+static int cgroup_has_css_refs(struct cgroup *cgrp)
 {
         /* Check the reference count on each subsystem. Since we
          * already established that there are no tasks in the
@@ -2761,14 +2738,15 @@ void cgroup_fork_callbacks(struct task_struct *child)
  */
 void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 {
-        struct cgroup *oldcgrp, *newcgrp;
+        struct cgroup *oldcgrp, *newcgrp = NULL;
 
         if (need_mm_owner_callback) {
                 int i;
                 for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                         struct cgroup_subsys *ss = subsys[i];
                         oldcgrp = task_cgroup(old, ss->subsys_id);
-                        newcgrp = task_cgroup(new, ss->subsys_id);
+                        if (new)
+                                newcgrp = task_cgroup(new, ss->subsys_id);
                         if (oldcgrp == newcgrp)
                                 continue;
                         if (ss->mm_owner_changed)
@@ -2869,16 +2847,17 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
  * cgroup_clone - clone the cgroup the given subsystem is attached to
  * @tsk: the task to be moved
  * @subsys: the given subsystem
+ * @nodename: the name for the new cgroup
  *
  * Duplicate the current cgroup in the hierarchy that the given
  * subsystem is attached to, and move this task into the new
  * child.
  */
-int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
+int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
+                                                        char *nodename)
 {
         struct dentry *dentry;
         int ret = 0;
-        char nodename[MAX_CGROUP_TYPE_NAMELEN];
         struct cgroup *parent, *child;
         struct inode *inode;
         struct css_set *cg;
@@ -2903,8 +2882,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
         cg = tsk->cgroups;
         parent = task_cgroup(tsk, subsys->subsys_id);
 
-        snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "%d", tsk->pid);
-
         /* Pin the hierarchy */
         atomic_inc(&parent->root->sb->s_active);
 
@@ -3078,27 +3055,24 @@ static void cgroup_release_agent(struct work_struct *work)
         while (!list_empty(&release_list)) {
                 char *argv[3], *envp[3];
                 int i;
-                char *pathbuf;
+                char *pathbuf = NULL, *agentbuf = NULL;
                 struct cgroup *cgrp = list_entry(release_list.next,
                                                     struct cgroup,
                                                     release_list);
                 list_del_init(&cgrp->release_list);
                 spin_unlock(&release_list_lock);
                 pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
-                if (!pathbuf) {
-                        spin_lock(&release_list_lock);
-                        continue;
-                }
-
-                if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0) {
-                        kfree(pathbuf);
-                        spin_lock(&release_list_lock);
-                        continue;
-                }
+                if (!pathbuf)
+                        goto continue_free;
+                if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
+                        goto continue_free;
+                agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
+                if (!agentbuf)
+                        goto continue_free;
 
                 i = 0;
-                argv[i++] = cgrp->root->release_agent_path;
-                argv[i++] = (char *)pathbuf;
+                argv[i++] = agentbuf;
+                argv[i++] = pathbuf;
                 argv[i] = NULL;
 
                 i = 0;
@@ -3112,8 +3086,10 @@ static void cgroup_release_agent(struct work_struct *work)
                  * be a slow process */
                 mutex_unlock(&cgroup_mutex);
                 call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-                kfree(pathbuf);
                 mutex_lock(&cgroup_mutex);
+ continue_free:
+                kfree(pathbuf);
+                kfree(agentbuf);
                 spin_lock(&release_list_lock);
         }
         spin_unlock(&release_list_lock);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index cfb1d43ab801..f17e9854c246 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -64,6 +64,8 @@ void __init cpu_hotplug_init(void)
         cpu_hotplug.refcount = 0;
 }
 
+cpumask_t cpu_active_map;
+
 #ifdef CONFIG_HOTPLUG_CPU
 
 void get_online_cpus(void)
@@ -214,7 +216,6 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
         int err, nr_calls = 0;
-        struct task_struct *p;
         cpumask_t old_allowed, tmp;
         void *hcpu = (void *)(long)cpu;
         unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
@@ -247,21 +248,18 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
         cpus_setall(tmp);
         cpu_clear(cpu, tmp);
         set_cpus_allowed_ptr(current, &tmp);
+        tmp = cpumask_of_cpu(cpu);
 
-        p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
-
-        if (IS_ERR(p) || cpu_online(cpu)) {
+        err = __stop_machine(take_cpu_down, &tcd_param, &tmp);
+        if (err) {
                 /* CPU didn't die: tell everyone.  Can't complain. */
                 if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
                                             hcpu) == NOTIFY_BAD)
                         BUG();
 
-                if (IS_ERR(p)) {
-                        err = PTR_ERR(p);
-                        goto out_allowed;
-                }
-                goto out_thread;
+                goto out_allowed;
         }
+        BUG_ON(cpu_online(cpu));
 
         /* Wait for it to sleep (leaving idle task). */
         while (!idle_cpu(cpu))
@@ -277,12 +275,15 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
         check_for_tasks(cpu);
 
-out_thread:
-        err = kthread_stop(p);
 out_allowed:
         set_cpus_allowed_ptr(current, &old_allowed);
 out_release:
         cpu_hotplug_done();
+        if (!err) {
+                if (raw_notifier_call_chain(&cpu_chain, CPU_POST_DEAD | mod,
+                                            hcpu) == NOTIFY_BAD)
+                        BUG();
+        }
         return err;
 }
 
@@ -291,11 +292,30 @@ int __ref cpu_down(unsigned int cpu)
         int err = 0;
 
         cpu_maps_update_begin();
-        if (cpu_hotplug_disabled)
+
+        if (cpu_hotplug_disabled) {
                 err = -EBUSY;
-        else
-                err = _cpu_down(cpu, 0);
+                goto out;
+        }
+
+        cpu_clear(cpu, cpu_active_map);
+
+        /*
+         * Make sure the all cpus did the reschedule and are not
+         * using stale version of the cpu_active_map.
+         * This is not strictly necessary becuase stop_machine()
+         * that we run down the line already provides the required
+         * synchronization. But it's really a side effect and we do not
+         * want to depend on the innards of the stop_machine here.
+         */
+        synchronize_sched();
+
+        err = _cpu_down(cpu, 0);
+
+        if (cpu_online(cpu))
+                cpu_set(cpu, cpu_active_map);
 
+out:
         cpu_maps_update_done();
         return err;
 }
@@ -329,6 +349,8 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
                 goto out_notify;
         BUG_ON(!cpu_online(cpu));
 
+        cpu_set(cpu, cpu_active_map);
+
         /* Now call notifier in preparation. */
         raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
 
@@ -347,7 +369,7 @@ int __cpuinit cpu_up(unsigned int cpu)
         if (!cpu_isset(cpu, cpu_possible_map)) {
                 printk(KERN_ERR "can't online cpu %d because it is not "
                         "configured as may-hotadd at boot time\n", cpu);
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) || defined(CONFIG_S390)
+#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
                 printk(KERN_ERR "please check additional_cpus= boot "
                                 "parameter\n");
 #endif
@@ -355,11 +377,15 @@ int __cpuinit cpu_up(unsigned int cpu)
         }
 
         cpu_maps_update_begin();
-        if (cpu_hotplug_disabled)
+
+        if (cpu_hotplug_disabled) {
                 err = -EBUSY;
-        else
-                err = _cpu_up(cpu, 0);
+                goto out;
+        }
+
+        err = _cpu_up(cpu, 0);
 
+out:
         cpu_maps_update_done();
         return err;
 }
@@ -413,7 +439,7 @@ void __ref enable_nonboot_cpus(void)
                 goto out;
 
         printk("Enabling non-boot CPUs ...\n");
-        for_each_cpu_mask(cpu, frozen_cpus) {
+        for_each_cpu_mask_nr(cpu, frozen_cpus) {
                 error = _cpu_up(cpu, 1);
                 if (!error) {
                         printk("CPU%d is up\n", cpu);
@@ -428,3 +454,28 @@ out:
 #endif /* CONFIG_PM_SLEEP_SMP */
 
 #endif /* CONFIG_SMP */
+
+/*
+ * cpu_bit_bitmap[] is a special, "compressed" data structure that
+ * represents all NR_CPUS bits binary values of 1<<nr.
+ *
+ * It is used by cpumask_of_cpu() to get a constant address to a CPU
+ * mask value that has a single bit set only.
+ */
+
+/* cpu_bit_bitmap[0] is empty - so we can back into it */
+#define MASK_DECLARE_1(x)       [x+1][0] = 1UL << (x)
+#define MASK_DECLARE_2(x)       MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
+#define MASK_DECLARE_4(x)       MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
+#define MASK_DECLARE_8(x)       MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
+
+const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
+
+        MASK_DECLARE_8(0),      MASK_DECLARE_8(8),
+        MASK_DECLARE_8(16),     MASK_DECLARE_8(24),
+#if BITS_PER_LONG > 32
+        MASK_DECLARE_8(32),     MASK_DECLARE_8(40),
+        MASK_DECLARE_8(48),     MASK_DECLARE_8(56),
+#endif
+};
+EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 459d601947a8..827cd9adccb2 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -14,6 +14,8 @@
  *  2003-10-22 Updates by Stephen Hemminger.
  *  2004 May-July Rework by Paul Jackson.
  *  2006 Rework by Paul Menage to use generic cgroups
+ *  2008 Rework of the scheduler domains and CPU hotplug handling
+ *       by Max Krasnyansky
  *
  *  This file is subject to the terms and conditions of the GNU General Public
  *  License.  See the file COPYING in the main directory of the Linux
@@ -54,7 +56,6 @@
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
 #include <linux/mutex.h>
-#include <linux/kfifo.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 
@@ -227,10 +228,6 @@ static struct cpuset top_cpuset = {
  * The task_struct fields mems_allowed and mems_generation may only
  * be accessed in the context of that task, so require no locks.
  *
- * The cpuset_common_file_write handler for operations that modify
- * the cpuset hierarchy holds cgroup_mutex across the entire operation,
- * single threading all such cpuset modifications across the system.
- *
  * The cpuset_common_file_read() handlers only hold callback_mutex across
  * small pieces of code, such as when reading out possibly multi-word
  * cpumasks and nodemasks.
@@ -241,9 +238,11 @@ static struct cpuset top_cpuset = {
 
 static DEFINE_MUTEX(callback_mutex);
 
-/* This is ugly, but preserves the userspace API for existing cpuset
+/*
+ * This is ugly, but preserves the userspace API for existing cpuset
  * users. If someone tries to mount the "cpuset" filesystem, we
- * silently switch it to mount "cgroup" instead */
+ * silently switch it to mount "cgroup" instead
+ */
 static int cpuset_get_sb(struct file_system_type *fs_type,
                          int flags, const char *unused_dev_name,
                          void *data, struct vfsmount *mnt)
@@ -369,7 +368,7 @@ void cpuset_update_task_memory_state(void)
                 my_cpusets_mem_gen = top_cpuset.mems_generation;
         } else {
                 rcu_read_lock();
-                my_cpusets_mem_gen = task_cs(current)->mems_generation;
+                my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
                 rcu_read_unlock();
         }
 
@@ -478,10 +477,9 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 }
 
 /*
- * Helper routine for rebuild_sched_domains().
+ * Helper routine for generate_sched_domains().
  * Do cpusets a, b have overlapping cpus_allowed masks?
  */
-
 static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 {
         return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
@@ -490,29 +488,48 @@ static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 static void
 update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
 {
-        if (!dattr)
-                return;
         if (dattr->relax_domain_level < c->relax_domain_level)
                 dattr->relax_domain_level = c->relax_domain_level;
         return;
 }
 
+static void
+update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
+{
+        LIST_HEAD(q);
+
+        list_add(&c->stack_list, &q);
+        while (!list_empty(&q)) {
+                struct cpuset *cp;
+                struct cgroup *cont;
+                struct cpuset *child;
+
+                cp = list_first_entry(&q, struct cpuset, stack_list);
+                list_del(q.next);
+
+                if (cpus_empty(cp->cpus_allowed))
+                        continue;
+
+                if (is_sched_load_balance(cp))
+                        update_domain_attr(dattr, cp);
+
+                list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+                        child = cgroup_cs(cont);
+                        list_add_tail(&child->stack_list, &q);
+                }
+        }
+}
+
 /*
- * rebuild_sched_domains()
+ * generate_sched_domains()
  *
- * If the flag 'sched_load_balance' of any cpuset with non-empty
- * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
- * which has that flag enabled, or if any cpuset with a non-empty
- * 'cpus' is removed, then call this routine to rebuild the
- * scheduler's dynamic sched domains.
- *
- * This routine builds a partial partition of the systems CPUs
- * (the set of non-overlappping cpumask_t's in the array 'part'
- * below), and passes that partial partition to the kernel/sched.c
- * partition_sched_domains() routine, which will rebuild the
- * schedulers load balancing domains (sched domains) as specified
- * by that partial partition.  A 'partial partition' is a set of
- * non-overlapping subsets whose union is a subset of that set.
+ * This function builds a partial partition of the systems CPUs
+ * A 'partial partition' is a set of non-overlapping subsets whose
+ * union is a subset of that set.
+ * The output of this function needs to be passed to kernel/sched.c
+ * partition_sched_domains() routine, which will rebuild the scheduler's
+ * load balancing domains (sched domains) as specified by that partial
+ * partition.
  *
  * See "What is sched_load_balance" in Documentation/cpusets.txt
  * for a background explanation of this.
@@ -522,16 +539,10 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
  * domains when operating in the severe memory shortage situations
  * that could cause allocation failures below.
  *
- * Call with cgroup_mutex held.  May take callback_mutex during
- * call due to the kfifo_alloc() and kmalloc() calls.  May nest
- * a call to the get_online_cpus()/put_online_cpus() pair.
- * Must not be called holding callback_mutex, because we must not
- * call get_online_cpus() while holding callback_mutex.  Elsewhere
- * the kernel nests callback_mutex inside get_online_cpus() calls.
- * So the reverse nesting would risk an ABBA deadlock.
+ * Must be called with cgroup_lock held.
  *
  * The three key local variables below are:
- *    q  - a kfifo queue of cpuset pointers, used to implement a
+ *    q  - a linked-list queue of cpuset pointers, used to implement a
  *         top-down scan of all cpusets.  This scan loads a pointer
  *         to each cpuset marked is_sched_load_balance into the
  *         array 'csa'.  For our purposes, rebuilding the schedulers
@@ -563,10 +574,10 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
  *      element of the partition (one sched domain) to be passed to
  *      partition_sched_domains().
  */
-
-static void rebuild_sched_domains(void)
+static int generate_sched_domains(cpumask_t **domains,
+                        struct sched_domain_attr **attributes)
 {
-        struct kfifo *q;        /* queue of cpusets to be scanned */
+        LIST_HEAD(q);           /* queue of cpusets to be scanned */
         struct cpuset *cp;      /* scans q */
         struct cpuset **csa;    /* array of all cpuset ptrs */
         int csn;                /* how many cpuset ptrs in csa so far */
@@ -576,44 +587,58 @@ static void rebuild_sched_domains(void)
         int ndoms;              /* number of sched domains in result */
         int nslot;              /* next empty doms[] cpumask_t slot */
 
-        q = NULL;
-        csa = NULL;
+        ndoms = 0;
         doms = NULL;
         dattr = NULL;
+        csa = NULL;
 
         /* Special case for the 99% of systems with one, full, sched domain */
         if (is_sched_load_balance(&top_cpuset)) {
-                ndoms = 1;
                 doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
                 if (!doms)
-                        goto rebuild;
+                        goto done;
+
                 dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
                 if (dattr) {
                         *dattr = SD_ATTR_INIT;
-                        update_domain_attr(dattr, &top_cpuset);
+                        update_domain_attr_tree(dattr, &top_cpuset);
                 }
                 *doms = top_cpuset.cpus_allowed;
-                goto rebuild;
-        }
 
-        q = kfifo_alloc(number_of_cpusets * sizeof(cp), GFP_KERNEL, NULL);
-        if (IS_ERR(q))
+                ndoms = 1;
                 goto done;
+        }
+
         csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
         if (!csa)
                 goto done;
         csn = 0;
 
-        cp = &top_cpuset;
-        __kfifo_put(q, (void *)&cp, sizeof(cp));
-        while (__kfifo_get(q, (void *)&cp, sizeof(cp))) {
+        list_add(&top_cpuset.stack_list, &q);
+        while (!list_empty(&q)) {
                 struct cgroup *cont;
                 struct cpuset *child;   /* scans child cpusets of cp */
-                if (is_sched_load_balance(cp))
+
+                cp = list_first_entry(&q, struct cpuset, stack_list);
+                list_del(q.next);
+
+                if (cpus_empty(cp->cpus_allowed))
+                        continue;
+
+                /*
+                 * All child cpusets contain a subset of the parent's cpus, so
+                 * just skip them, and then we call update_domain_attr_tree()
+                 * to calc relax_domain_level of the corresponding sched
+                 * domain.
+                 */
+                if (is_sched_load_balance(cp)) {
                         csa[csn++] = cp;
+                        continue;
+                }
+
                 list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
                         child = cgroup_cs(cont);
-                        __kfifo_put(q, (void *)&child, sizeof(cp));
+                        list_add_tail(&child->stack_list, &q);
                 }
         }
 
@@ -644,91 +669,141 @@ restart:
                 }
         }
 
-        /* Convert <csn, csa> to <ndoms, doms> */
+        /*
+         * Now we know how many domains to create.
+         * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
+         */
         doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
-        if (!doms)
-                goto rebuild;
+        if (!doms) {
+                ndoms = 0;
+                goto done;
+        }
+
+        /*
+         * The rest of the code, including the scheduler, can deal with
+         * dattr==NULL case. No need to abort if alloc fails.
+         */
         dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);
 
         for (nslot = 0, i = 0; i < csn; i++) {
                 struct cpuset *a = csa[i];
+                cpumask_t *dp;
                 int apn = a->pn;
 
-                if (apn >= 0) {
-                        cpumask_t *dp = doms + nslot;
-
-                        if (nslot == ndoms) {
-                                static int warnings = 10;
-                                if (warnings) {
-                                        printk(KERN_WARNING
-                                         "rebuild_sched_domains confused:"
-                                          " nslot %d, ndoms %d, csn %d, i %d,"
-                                          " apn %d\n",
-                                          nslot, ndoms, csn, i, apn);
-                                        warnings--;
-                                }
-                                continue;
+                if (apn < 0) {
+                        /* Skip completed partitions */
+                        continue;
+                }
+
+                dp = doms + nslot;
+
+                if (nslot == ndoms) {
+                        static int warnings = 10;
+                        if (warnings) {
+                                printk(KERN_WARNING
+                                 "rebuild_sched_domains confused:"
+                                  " nslot %d, ndoms %d, csn %d, i %d,"
+                                  " apn %d\n",
+                                  nslot, ndoms, csn, i, apn);
+                                warnings--;
                         }
+                        continue;
+                }
 
-                        cpus_clear(*dp);
-                        if (dattr)
-                                *(dattr + nslot) = SD_ATTR_INIT;
-                        for (j = i; j < csn; j++) {
-                                struct cpuset *b = csa[j];
+                cpus_clear(*dp);
+                if (dattr)
+                        *(dattr + nslot) = SD_ATTR_INIT;
+                for (j = i; j < csn; j++) {
+                        struct cpuset *b = csa[j];
 
-                                if (apn == b->pn) {
-                                        cpus_or(*dp, *dp, b->cpus_allowed);
-                                        b->pn = -1;
-                                        update_domain_attr(dattr, b);
-                                }
+                        if (apn == b->pn) {
+                                cpus_or(*dp, *dp, b->cpus_allowed);
+                                if (dattr)
+                                        update_domain_attr_tree(dattr + nslot, b);
+
+                                /* Done with this partition */
+                                b->pn = -1;
                         }
-                        nslot++;
                 }
+                nslot++;
         }
         BUG_ON(nslot != ndoms);
 
-rebuild:
-        /* Have scheduler rebuild sched domains */
-        get_online_cpus();
-        partition_sched_domains(ndoms, doms, dattr);
-        put_online_cpus();
-
 done:
-        if (q && !IS_ERR(q))
-                kfifo_free(q);
         kfree(csa);
-        /* Don't kfree(doms) -- partition_sched_domains() does that. */
-        /* Don't kfree(dattr) -- partition_sched_domains() does that. */
+
+        *domains    = doms;
+        *attributes = dattr;
+        return ndoms;
 }
 
-static inline int started_after_time(struct task_struct *t1,
-                                     struct timespec *time,
-                                     struct task_struct *t2)
+/*
+ * Rebuild scheduler domains.
+ *
+ * Call with neither cgroup_mutex held nor within get_online_cpus().
+ * Takes both cgroup_mutex and get_online_cpus().
+ *
+ * Cannot be directly called from cpuset code handling changes
+ * to the cpuset pseudo-filesystem, because it cannot be called
+ * from code that already holds cgroup_mutex.
+ */
+static void do_rebuild_sched_domains(struct work_struct *unused)
 {
-        int start_diff = timespec_compare(&t1->start_time, time);
-        if (start_diff > 0) {
-                return 1;
-        } else if (start_diff < 0) {
-                return 0;
-        } else {
-                /*
-                 * Arbitrarily, if two processes started at the same
-                 * time, we'll say that the lower pointer value
-                 * started first. Note that t2 may have exited by now
-                 * so this may not be a valid pointer any longer, but
-                 * that's fine - it still serves to distinguish
-                 * between two tasks started (effectively)
-                 * simultaneously.
-                 */
-                return t1 > t2;
-        }
+        struct sched_domain_attr *attr;
+        cpumask_t *doms;
+        int ndoms;
+
+        get_online_cpus();
+
+        /* Generate domain masks and attrs */
+        cgroup_lock();
+        ndoms = generate_sched_domains(&doms, &attr);
+        cgroup_unlock();
+
+        /* Have scheduler rebuild the domains */
+        partition_sched_domains(ndoms, doms, attr);
+
+        put_online_cpus();
+}
+
+static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
+
+/*
+ * Rebuild scheduler domains, asynchronously via workqueue.
+ *
+ * If the flag 'sched_load_balance' of any cpuset with non-empty
+ * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
+ * which has that flag enabled, or if any cpuset with a non-empty
+ * 'cpus' is removed, then call this routine to rebuild the
+ * scheduler's dynamic sched domains.
+ *
+ * The rebuild_sched_domains() and partition_sched_domains()
+ * routines must nest cgroup_lock() inside get_online_cpus(),
+ * but such cpuset changes as these must nest that locking the
+ * other way, holding cgroup_lock() for much of the code.
+ *
+ * So in order to avoid an ABBA deadlock, the cpuset code handling
+ * these user changes delegates the actual sched domain rebuilding
+ * to a separate workqueue thread, which ends up processing the
+ * above do_rebuild_sched_domains() function.
+ */
+static void async_rebuild_sched_domains(void)
+{
+        schedule_work(&rebuild_sched_domains_work);
 }
 
-static inline int started_after(void *p1, void *p2)
+/*
+ * Accomplishes the same scheduler domain rebuild as the above
+ * async_rebuild_sched_domains(), however it directly calls the
+ * rebuild routine synchronously rather than calling it via an
+ * asynchronous work thread.
+ *
+ * This can only be called from code that is not holding
+ * cgroup_mutex (not nested in a cgroup_lock() call.)
+ */
+void rebuild_sched_domains(void)
 {
-        struct task_struct *t1 = p1;
-        struct task_struct *t2 = p2;
-        return started_after_time(t1, &t2->start_time, t2);
+        do_rebuild_sched_domains(NULL);
 }
 
 /**
@@ -766,15 +841,38 @@ static void cpuset_change_cpumask(struct task_struct *tsk,
 }
 
 /**
+ * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
+ * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
+ *
+ * Called with cgroup_mutex held
+ *
+ * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
+ * calling callback functions for each.
+ *
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
+ */
+static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
+{
+        struct cgroup_scanner scan;
+
+        scan.cg = cs->css.cgroup;
+        scan.test_task = cpuset_test_cpumask;
+        scan.process_task = cpuset_change_cpumask;
+        scan.heap = heap;
+        cgroup_scan_tasks(&scan);
+}
+
+/**
  * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
  * @cs: the cpuset to consider
  * @buf: buffer of cpu numbers written to this cpuset
  */
-static int update_cpumask(struct cpuset *cs, char *buf)
+static int update_cpumask(struct cpuset *cs, const char *buf)
 {
-        struct cpuset trialcs;
-        struct cgroup_scanner scan;
         struct ptr_heap heap;
+        struct cpuset trialcs;
         int retval;
         int is_load_balanced;
 
@@ -790,7 +888,6 @@ static int update_cpumask(struct cpuset *cs, char *buf)
          * that parsing.  The validate_change() call ensures that cpusets
          * with tasks have cpus.
          */
-        buf = strstrip(buf);
         if (!*buf) {
                 cpus_clear(trialcs.cpus_allowed);
         } else {
@@ -809,7 +906,7 @@ static int update_cpumask(struct cpuset *cs, char *buf)
         if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
                 return 0;
 
-        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, &started_after);
+        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
         if (retval)
                 return retval;
 
@@ -823,15 +920,12 @@ static int update_cpumask(struct cpuset *cs, char *buf)
          * Scan tasks in the cpuset, and update the cpumasks of any
          * that need an update.
          */
-        scan.cg = cs->css.cgroup;
-        scan.test_task = cpuset_test_cpumask;
-        scan.process_task = cpuset_change_cpumask;
-        scan.heap = &heap;
-        cgroup_scan_tasks(&scan);
+        update_tasks_cpumask(cs, &heap);
+
         heap_free(&heap);
 
         if (is_load_balanced)
-                rebuild_sched_domains();
+                async_rebuild_sched_domains();
         return 0;
 }
 
@@ -884,74 +978,25 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
         mutex_unlock(&callback_mutex);
 }
 
-/*
- * Handle user request to change the 'mems' memory placement
- * of a cpuset.  Needs to validate the request, update the
- * cpusets mems_allowed and mems_generation, and for each
- * task in the cpuset, rebind any vma mempolicies and if
- * the cpuset is marked 'memory_migrate', migrate the tasks
- * pages to the new memory.
- *
- * Call with cgroup_mutex held.  May take callback_mutex during call.
- * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
- * lock each such tasks mm->mmap_sem, scan its vma's and rebind
- * their mempolicies to the cpusets new mems_allowed.
- */
-
 static void *cpuset_being_rebound;
 
-static int update_nodemask(struct cpuset *cs, char *buf)
+/**
+ * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
+ * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
+ * @oldmem: old mems_allowed of cpuset cs
+ *
+ * Called with cgroup_mutex held
+ * Return 0 if successful, -errno if not.
+ */
+static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
 {
-        struct cpuset trialcs;
-        nodemask_t oldmem;
         struct task_struct *p;
         struct mm_struct **mmarray;
         int i, n, ntasks;
         int migrate;
         int fudge;
-        int retval;
         struct cgroup_iter it;
-
-        /*
-         * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
-         * it's read-only
-         */
-        if (cs == &top_cpuset)
-                return -EACCES;
-
-        trialcs = *cs;
-
-        /*
-         * An empty mems_allowed is ok iff there are no tasks in the cpuset.
-         * Since nodelist_parse() fails on an empty mask, we special case
-         * that parsing.  The validate_change() call ensures that cpusets
-         * with tasks have memory.
-         */
-        buf = strstrip(buf);
-        if (!*buf) {
-                nodes_clear(trialcs.mems_allowed);
-        } else {
-                retval = nodelist_parse(buf, trialcs.mems_allowed);
-                if (retval < 0)
-                        goto done;
-
-                if (!nodes_subset(trialcs.mems_allowed,
-                                node_states[N_HIGH_MEMORY]))
-                        return -EINVAL;
-        }
-        oldmem = cs->mems_allowed;
-        if (nodes_equal(oldmem, trialcs.mems_allowed)) {
-                retval = 0;             /* Too easy - nothing to do */
-                goto done;
-        }
-        retval = validate_change(cs, &trialcs);
-        if (retval < 0)
-                goto done;
-
-        mutex_lock(&callback_mutex);
-        cs->mems_allowed = trialcs.mems_allowed;
-        cs->mems_generation = cpuset_mems_generation++;
-        mutex_unlock(&callback_mutex);
+        int retval;
 
         cpuset_being_rebound = cs;              /* causes mpol_dup() rebind */
 
@@ -1018,7 +1063,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 
                 mpol_rebind_mm(mm, &cs->mems_allowed);
                 if (migrate)
-                        cpuset_migrate_mm(mm, &oldmem, &cs->mems_allowed);
+                        cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
                 mmput(mm);
         }
 
@@ -1030,6 +1075,70 @@ done:
         return retval;
 }
 
+/*
+ * Handle user request to change the 'mems' memory placement
+ * of a cpuset.  Needs to validate the request, update the
+ * cpusets mems_allowed and mems_generation, and for each
+ * task in the cpuset, rebind any vma mempolicies and if
+ * the cpuset is marked 'memory_migrate', migrate the tasks
+ * pages to the new memory.
+ *
+ * Call with cgroup_mutex held.  May take callback_mutex during call.
+ * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
+ * lock each such tasks mm->mmap_sem, scan its vma's and rebind
+ * their mempolicies to the cpusets new mems_allowed.
+ */
+static int update_nodemask(struct cpuset *cs, const char *buf)
+{
+        struct cpuset trialcs;
+        nodemask_t oldmem;
+        int retval;
+
+        /*
+         * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
+         * it's read-only
+         */
+        if (cs == &top_cpuset)
+                return -EACCES;
+
+        trialcs = *cs;
+
+        /*
+         * An empty mems_allowed is ok iff there are no tasks in the cpuset.
+         * Since nodelist_parse() fails on an empty mask, we special case
+         * that parsing.  The validate_change() call ensures that cpusets
+         * with tasks have memory.
+         */
+        if (!*buf) {
+                nodes_clear(trialcs.mems_allowed);
+        } else {
+                retval = nodelist_parse(buf, trialcs.mems_allowed);
+                if (retval < 0)
+                        goto done;
+
+                if (!nodes_subset(trialcs.mems_allowed,
+                                node_states[N_HIGH_MEMORY]))
+                        return -EINVAL;
+        }
+        oldmem = cs->mems_allowed;
+        if (nodes_equal(oldmem, trialcs.mems_allowed)) {
+                retval = 0;             /* Too easy - nothing to do */
+                goto done;
+        }
+        retval = validate_change(cs, &trialcs);
+        if (retval < 0)
+                goto done;
+
+        mutex_lock(&callback_mutex);
+        cs->mems_allowed = trialcs.mems_allowed;
+        cs->mems_generation = cpuset_mems_generation++;
+        mutex_unlock(&callback_mutex);
+
+        retval = update_tasks_nodemask(cs, &oldmem);
+done:
+        return retval;
+}
+
 int current_cpuset_is_being_rebound(void)
 {
         return task_cs(current) == cpuset_being_rebound;
@@ -1042,7 +1151,8 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 
         if (val != cs->relax_domain_level) {
                 cs->relax_domain_level = val;
-                rebuild_sched_domains();
+                if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs))
+                        async_rebuild_sched_domains();
         }
 
         return 0;
@@ -1083,7 +1193,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
         mutex_unlock(&callback_mutex);
 
         if (cpus_nonempty && balance_flag_changed)
-                rebuild_sched_domains();
+                async_rebuild_sched_domains();
 
         return 0;
 }
@@ -1254,72 +1364,14 @@ typedef enum {
         FILE_SPREAD_SLAB,
 } cpuset_filetype_t;
 
-static ssize_t cpuset_common_file_write(struct cgroup *cont,
-                                        struct cftype *cft,
-                                        struct file *file,
-                                        const char __user *userbuf,
-                                        size_t nbytes, loff_t *unused_ppos)
-{
-        struct cpuset *cs = cgroup_cs(cont);
-        cpuset_filetype_t type = cft->private;
-        char *buffer;
-        int retval = 0;
-
-        /* Crude upper limit on largest legitimate cpulist user might write. */
-        if (nbytes > 100U + 6 * max(NR_CPUS, MAX_NUMNODES))
-                return -E2BIG;
-
-        /* +1 for nul-terminator */
-        buffer = kmalloc(nbytes + 1, GFP_KERNEL);
-        if (!buffer)
-                return -ENOMEM;
-
-        if (copy_from_user(buffer, userbuf, nbytes)) {
-                retval = -EFAULT;
-                goto out1;
-        }
-        buffer[nbytes] = 0;     /* nul-terminate */
-
-        cgroup_lock();
-
-        if (cgroup_is_removed(cont)) {
-                retval = -ENODEV;
-                goto out2;
-        }
-
-        switch (type) {
-        case FILE_CPULIST:
-                retval = update_cpumask(cs, buffer);
-                break;
-        case FILE_MEMLIST:
-                retval = update_nodemask(cs, buffer);
-                break;
-        default:
-                retval = -EINVAL;
-                goto out2;
-        }
-
-        if (retval == 0)
-                retval = nbytes;
-out2:
-        cgroup_unlock();
-out1:
-        kfree(buffer);
-        return retval;
-}
-
 static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 {
         int retval = 0;
         struct cpuset *cs = cgroup_cs(cgrp);
         cpuset_filetype_t type = cft->private;
 
-        cgroup_lock();
-
-        if (cgroup_is_removed(cgrp)) {
-                cgroup_unlock();
+        if (!cgroup_lock_live_group(cgrp))
                 return -ENODEV;
-        }
 
         switch (type) {
         case FILE_CPU_EXCLUSIVE:
@@ -1365,12 +1417,9 @@ static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
         struct cpuset *cs = cgroup_cs(cgrp);
         cpuset_filetype_t type = cft->private;
 
-        cgroup_lock();
-
-        if (cgroup_is_removed(cgrp)) {
-                cgroup_unlock();
+        if (!cgroup_lock_live_group(cgrp))
                 return -ENODEV;
-        }
+
         switch (type) {
         case FILE_SCHED_RELAX_DOMAIN_LEVEL:
                 retval = update_relax_domain_level(cs, val);
@@ -1384,6 +1433,32 @@ static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
 }
 
 /*
+ * Common handling for a write to a "cpus" or "mems" file.
+ */
+static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
+                                const char *buf)
+{
+        int retval = 0;
+
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+
+        switch (cft->private) {
+        case FILE_CPULIST:
+                retval = update_cpumask(cgroup_cs(cgrp), buf);
+                break;
+        case FILE_MEMLIST:
+                retval = update_nodemask(cgroup_cs(cgrp), buf);
+                break;
+        default:
+                retval = -EINVAL;
+                break;
+        }
+        cgroup_unlock();
+        return retval;
+}
+
+/*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
  * chunks, there is no guarantee of atomicity.  Since the display format
@@ -1479,6 +1554,9 @@ static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
         default:
                 BUG();
         }
+
+        /* Unreachable but makes gcc happy */
+        return 0;
 }
 
 static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
@@ -1491,6 +1569,9 @@ static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
         default:
                 BUG();
         }
+
+        /* Unrechable but makes gcc happy */
+        return 0;
 }
 
 
@@ -1502,14 +1583,16 @@ static struct cftype files[] = {
         {
                 .name = "cpus",
                 .read = cpuset_common_file_read,
-                .write = cpuset_common_file_write,
+                .write_string = cpuset_write_resmask,
+                .max_write_len = (100U + 6 * NR_CPUS),
                 .private = FILE_CPULIST,
         },
 
         {
                 .name = "mems",
                 .read = cpuset_common_file_read,
-                .write = cpuset_common_file_write,
+                .write_string = cpuset_write_resmask,
+                .max_write_len = (100U + 6 * MAX_NUMNODES),
                 .private = FILE_MEMLIST,
         },
 
@@ -1677,15 +1760,9 @@ static struct cgroup_subsys_state *cpuset_create(
 }
 
 /*
- * Locking note on the strange update_flag() call below:
- *
  * If the cpuset being removed has its flag 'sched_load_balance'
  * enabled, then simulate turning sched_load_balance off, which
- * will call rebuild_sched_domains().  The get_online_cpus()
- * call in rebuild_sched_domains() must not be made while holding
- * callback_mutex.  Elsewhere the kernel nests callback_mutex inside
- * get_online_cpus() calls.  So the reverse nesting would risk an
- * ABBA deadlock.
+ * will call async_rebuild_sched_domains().
  */
 
 static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
@@ -1704,7 +1781,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 struct cgroup_subsys cpuset_subsys = {
         .name = "cpuset",
         .create = cpuset_create,
-        .destroy  = cpuset_destroy,
+        .destroy = cpuset_destroy,
         .can_attach = cpuset_can_attach,
         .attach = cpuset_attach,
         .populate = cpuset_populate,
@@ -1790,13 +1867,13 @@ static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to)
         scan.scan.heap = NULL;
         scan.to = to->css.cgroup;
 
-        if (cgroup_scan_tasks((struct cgroup_scanner *)&scan))
+        if (cgroup_scan_tasks(&scan.scan))
                 printk(KERN_ERR "move_member_tasks_to_cpuset: "
                                 "cgroup_scan_tasks failed\n");
 }
 
 /*
- * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * If CPU and/or memory hotplug handlers, below, unplug any CPUs
  * or memory nodes, we need to walk over the cpuset hierarchy,
  * removing that CPU or node from all cpusets.  If this removes the
  * last CPU or node from a cpuset, then move the tasks in the empty
@@ -1846,29 +1923,29 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  */
 static void scan_for_empty_cpusets(const struct cpuset *root)
 {
+        LIST_HEAD(queue);
         struct cpuset *cp;      /* scans cpusets being updated */
         struct cpuset *child;   /* scans child cpusets of cp */
-        struct list_head queue;
         struct cgroup *cont;
-
-        INIT_LIST_HEAD(&queue);
+        nodemask_t oldmems;
 
         list_add_tail((struct list_head *)&root->stack_list, &queue);
 
         while (!list_empty(&queue)) {
-                cp = container_of(queue.next, struct cpuset, stack_list);
+                cp = list_first_entry(&queue, struct cpuset, stack_list);
                 list_del(queue.next);
                 list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
                         child = cgroup_cs(cont);
                         list_add_tail(&child->stack_list, &queue);
                 }
-                cont = cp->css.cgroup;
 
                 /* Continue past cpusets with all cpus, mems online */
                 if (cpus_subset(cp->cpus_allowed, cpu_online_map) &&
                     nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
                         continue;
 
+                oldmems = cp->mems_allowed;
+
                 /* Remove offline cpus and mems from this cpuset. */
                 mutex_lock(&callback_mutex);
                 cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map);
@@ -1880,39 +1957,14 @@ static void scan_for_empty_cpusets(const struct cpuset *root)
                 if (cpus_empty(cp->cpus_allowed) ||
                      nodes_empty(cp->mems_allowed))
                         remove_tasks_in_empty_cpuset(cp);
+                else {
+                        update_tasks_cpumask(cp, NULL);
+                        update_tasks_nodemask(cp, &oldmems);
+                }
         }
 }
 
 /*
- * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
- * cpu_online_map and node_states[N_HIGH_MEMORY].  Force the top cpuset to
- * track what's online after any CPU or memory node hotplug or unplug event.
- *
- * Since there are two callers of this routine, one for CPU hotplug
- * events and one for memory node hotplug events, we could have coded
- * two separate routines here.  We code it as a single common routine
- * in order to minimize text size.
- */
-
-static void common_cpu_mem_hotplug_unplug(int rebuild_sd)
-{
-        cgroup_lock();
-
-        top_cpuset.cpus_allowed = cpu_online_map;
-        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-        scan_for_empty_cpusets(&top_cpuset);
-
-        /*
-         * Scheduler destroys domains on hotplug events.
-         * Rebuild them based on the current settings.
-         */
-        if (rebuild_sd)
-                rebuild_sched_domains();
-
-        cgroup_unlock();
-}
-
-/*
  * The top_cpuset tracks what CPUs and Memory Nodes are online,
  * period.  This is necessary in order to make cpusets transparent
  * (of no affect) on systems that are actively using CPU hotplug
@@ -1920,40 +1972,52 @@ static void common_cpu_mem_hotplug_unplug(int rebuild_sd)
  *
  * This routine ensures that top_cpuset.cpus_allowed tracks
  * cpu_online_map on each CPU hotplug (cpuhp) event.
+ *
+ * Called within get_online_cpus().  Needs to call cgroup_lock()
+ * before calling generate_sched_domains().
  */
-
-static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
+static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
                                 unsigned long phase, void *unused_cpu)
 {
+        struct sched_domain_attr *attr;
+        cpumask_t *doms;
+        int ndoms;
+
         switch (phase) {
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-        case CPU_DOWN_FAILED:
-        case CPU_DOWN_FAILED_FROZEN:
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                common_cpu_mem_hotplug_unplug(1);
                 break;
+
         default:
                 return NOTIFY_DONE;
         }
 
+        cgroup_lock();
+        top_cpuset.cpus_allowed = cpu_online_map;
+        scan_for_empty_cpusets(&top_cpuset);
+        ndoms = generate_sched_domains(&doms, &attr);
+        cgroup_unlock();
+
+        /* Have scheduler rebuild the domains */
+        partition_sched_domains(ndoms, doms, attr);
+
         return NOTIFY_OK;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
- * Call this routine anytime after you change
- * node_states[N_HIGH_MEMORY].
- * See also the previous routine cpuset_handle_cpuhp().
+ * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
+ * See also the previous routine cpuset_track_online_cpus().
  */
-
 void cpuset_track_online_nodes(void)
 {
-        common_cpu_mem_hotplug_unplug(0);
+        cgroup_lock();
+        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+        scan_for_empty_cpusets(&top_cpuset);
+        cgroup_unlock();
 }
 #endif
 
@@ -1968,11 +2032,10 @@ void __init cpuset_init_smp(void)
         top_cpuset.cpus_allowed = cpu_online_map;
         top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
-        hotcpu_notifier(cpuset_handle_cpuhp, 0);
+        hotcpu_notifier(cpuset_track_online_cpus, 0);
 }
 
 /**
-
  * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
  * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
  * @pmask: pointer to cpumask_t variable to receive cpus_allowed set.
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 10e43fd8b721..b3179dad71be 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -145,8 +145,11 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
         d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
         tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
         d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
+        tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
+        d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
         d->blkio_count += tsk->delays->blkio_count;
         d->swapin_count += tsk->delays->swapin_count;
+        d->freepages_count += tsk->delays->freepages_count;
         spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 done:
@@ -165,3 +168,16 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
         return ret;
 }
 
+void __delayacct_freepages_start(void)
+{
+        delayacct_start(&current->delays->freepages_start);
+}
+
+void __delayacct_freepages_end(void)
+{
+        delayacct_end(&current->delays->freepages_start,
+                        &current->delays->freepages_end,
+                        &current->delays->freepages_delay,
+                        &current->delays->freepages_count);
+}
+
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
new file mode 100644
index 000000000000..c1d4d5b4c61c
--- /dev/null
+++ b/kernel/dma-coherent.c
@@ -0,0 +1,153 @@
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+        void            *virt_base;
+        u32             device_base;
+        int             size;
+        int             flags;
+        unsigned long   *bitmap;
+};
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+                                dma_addr_t device_addr, size_t size, int flags)
+{
+        void __iomem *mem_base = NULL;
+        int pages = size >> PAGE_SHIFT;
+        int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+        if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+                goto out;
+        if (!size)
+                goto out;
+        if (dev->dma_mem)
+                goto out;
+
+        /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+        mem_base = ioremap(bus_addr, size);
+        if (!mem_base)
+                goto out;
+
+        dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+        if (!dev->dma_mem)
+                goto out;
+        dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+        if (!dev->dma_mem->bitmap)
+                goto free1_out;
+
+        dev->dma_mem->virt_base = mem_base;
+        dev->dma_mem->device_base = device_addr;
+        dev->dma_mem->size = pages;
+        dev->dma_mem->flags = flags;
+
+        if (flags & DMA_MEMORY_MAP)
+                return DMA_MEMORY_MAP;
+
+        return DMA_MEMORY_IO;
+
+ free1_out:
+        kfree(dev->dma_mem);
+ out:
+        if (mem_base)
+                iounmap(mem_base);
+        return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+        struct dma_coherent_mem *mem = dev->dma_mem;
+
+        if (!mem)
+                return;
+        dev->dma_mem = NULL;
+        iounmap(mem->virt_base);
+        kfree(mem->bitmap);
+        kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+                                        dma_addr_t device_addr, size_t size)
+{
+        struct dma_coherent_mem *mem = dev->dma_mem;
+        int pos, err;
+
+        size += device_addr & ~PAGE_MASK;
+
+        if (!mem)
+                return ERR_PTR(-EINVAL);
+
+        pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+        err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+        if (err != 0)
+                return ERR_PTR(err);
+        return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+/**
+ * dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
+ *
+ * @dev:        device from which we allocate memory
+ * @size:       size of requested memory area
+ * @dma_handle: This will be filled with the correct dma handle
+ * @ret:        This pointer will be filled with the virtual address
+ *              to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+                                       dma_addr_t *dma_handle, void **ret)
+{
+        struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+        int order = get_order(size);
+
+        if (mem) {
+                int page = bitmap_find_free_region(mem->bitmap, mem->size,
+                                                     order);
+                if (page >= 0) {
+                        *dma_handle = mem->device_base + (page << PAGE_SHIFT);
+                        *ret = mem->virt_base + (page << PAGE_SHIFT);
+                        memset(*ret, 0, size);
+                } else if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+                        *ret = NULL;
+        }
+        return (mem != NULL);
+}
+
+/**
+ * dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
+ * @dev:        device from which the memory was allocated
+ * @order:      the order of pages allocated
+ * @vaddr:      virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+        struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+        if (mem && vaddr >= mem->virt_base && vaddr <
+                   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+                int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+                bitmap_release_region(mem->bitmap, page, order);
+                return 1;
+        }
+        return 0;
+}
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index a9e6bad9f706..0d407e886735 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -65,7 +65,7 @@ lookup_exec_domain(u_long personality)
                                 goto out;
         }
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
         read_unlock(&exec_domains_lock);
         request_module("personality-%ld", pers);
         read_lock(&exec_domains_lock);
@@ -168,7 +168,6 @@ __set_personality(u_long personality)
         current->personality = personality;
         oep = current_thread_info()->exec_domain;
         current_thread_info()->exec_domain = ep;
-        set_fs_altroot();
 
         module_put(oep->module);
         return 0;
diff --git a/kernel/exit.c b/kernel/exit.c
index 93d2711b9381..85a83c831856 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,6 +46,7 @@
 #include <linux/resource.h>
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/tracehook.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -85,7 +86,6 @@ static void __exit_signal(struct task_struct *tsk)
         BUG_ON(!sig);
         BUG_ON(!atomic_read(&sig->count));
 
-        rcu_read_lock();
         sighand = rcu_dereference(tsk->sighand);
         spin_lock(&sighand->siglock);
 
@@ -112,15 +112,16 @@ static void __exit_signal(struct task_struct *tsk)
                  * We won't ever get here for the group leader, since it
                  * will have been the last reference on the signal_struct.
                  */
-                sig->utime = cputime_add(sig->utime, tsk->utime);
-                sig->stime = cputime_add(sig->stime, tsk->stime);
-                sig->gtime = cputime_add(sig->gtime, tsk->gtime);
+                sig->utime = cputime_add(sig->utime, task_utime(tsk));
+                sig->stime = cputime_add(sig->stime, task_stime(tsk));
+                sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
                 sig->min_flt += tsk->min_flt;
                 sig->maj_flt += tsk->maj_flt;
                 sig->nvcsw += tsk->nvcsw;
                 sig->nivcsw += tsk->nivcsw;
                 sig->inblock += task_io_get_inblock(tsk);
                 sig->oublock += task_io_get_oublock(tsk);
+                task_io_accounting_add(&sig->ioac, &tsk->ioac);
                 sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
                 sig = NULL; /* Marker for below. */
         }
@@ -136,7 +137,6 @@ static void __exit_signal(struct task_struct *tsk)
         tsk->signal = NULL;
         tsk->sighand = NULL;
         spin_unlock(&sighand->siglock);
-        rcu_read_unlock();
 
         __cleanup_sighand(sighand);
         clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
@@ -152,27 +152,17 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
         put_task_struct(container_of(rhp, struct task_struct, rcu));
 }
 
-/*
- * Do final ptrace-related cleanup of a zombie being reaped.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-static void ptrace_release_task(struct task_struct *p)
-{
-        BUG_ON(!list_empty(&p->ptraced));
-        ptrace_unlink(p);
-        BUG_ON(!list_empty(&p->ptrace_entry));
-}
 
 void release_task(struct task_struct * p)
 {
         struct task_struct *leader;
         int zap_leader;
 repeat:
+        tracehook_prepare_release_task(p);
         atomic_dec(&p->user->processes);
         proc_flush_task(p);
         write_lock_irq(&tasklist_lock);
-        ptrace_release_task(p);
+        tracehook_finish_release_task(p);
         __exit_signal(p);
 
         /*
@@ -194,6 +184,13 @@ repeat:
                  * that case.
                  */
                 zap_leader = task_detached(leader);
+
+                /*
+                 * This maintains the invariant that release_task()
+                 * only runs on a task in EXIT_DEAD, just for sanity.
+                 */
+                if (zap_leader)
+                        leader->exit_state = EXIT_DEAD;
         }
 
         write_unlock_irq(&tasklist_lock);
@@ -432,7 +429,7 @@ void daemonize(const char *name, ...)
          * We don't want to have TIF_FREEZE set if the system-wide hibernation
          * or suspend transition begins right now.
          */
-        current->flags |= PF_NOFREEZE;
+        current->flags |= (PF_NOFREEZE | PF_KTHREAD);
 
         if (current->nsproxy != &init_nsproxy) {
                 get_nsproxy(&init_nsproxy);
@@ -557,8 +554,6 @@ void put_fs_struct(struct fs_struct *fs)
         if (atomic_dec_and_test(&fs->count)) {
                 path_put(&fs->root);
                 path_put(&fs->pwd);
-                if (fs->altroot.dentry)
-                        path_put(&fs->altroot);
                 kmem_cache_free(fs_cachep, fs);
         }
 }
@@ -588,8 +583,6 @@ mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
          * If there are other users of the mm and the owner (us) is exiting
          * we need to find a new owner to take on the responsibility.
          */
-        if (!mm)
-                return 0;
         if (atomic_read(&mm->mm_users) <= 1)
                 return 0;
         if (mm->owner != p)
@@ -632,6 +625,16 @@ retry:
         } while_each_thread(g, c);
 
         read_unlock(&tasklist_lock);
+        /*
+         * We found no owner yet mm_users > 1: this implies that we are
+         * most likely racing with swapoff (try_to_unuse()) or /proc or
+         * ptrace or page migration (get_task_mm()).  Mark owner as NULL,
+         * so that subsystems can understand the callback and take action.
+         */
+        down_write(&mm->mmap_sem);
+        cgroup_mm_owner_callbacks(mm->owner, NULL);
+        mm->owner = NULL;
+        up_write(&mm->mmap_sem);
         return;
 
 assign_new_owner:
@@ -666,26 +669,40 @@ assign_new_owner:
 static void exit_mm(struct task_struct * tsk)
 {
         struct mm_struct *mm = tsk->mm;
+        struct core_state *core_state;
 
         mm_release(tsk, mm);
         if (!mm)
                 return;
         /*
          * Serialize with any possible pending coredump.
-         * We must hold mmap_sem around checking core_waiters
+         * We must hold mmap_sem around checking core_state
          * and clearing tsk->mm.  The core-inducing thread
-         * will increment core_waiters for each thread in the
+         * will increment ->nr_threads for each thread in the
          * group with ->mm != NULL.
          */
         down_read(&mm->mmap_sem);
-        if (mm->core_waiters) {
+        core_state = mm->core_state;
+        if (core_state) {
+                struct core_thread self;
                 up_read(&mm->mmap_sem);
-                down_write(&mm->mmap_sem);
-                if (!--mm->core_waiters)
-                        complete(mm->core_startup_done);
-                up_write(&mm->mmap_sem);
 
-                wait_for_completion(&mm->core_done);
+                self.task = tsk;
+                self.next = xchg(&core_state->dumper.next, &self);
+                /*
+                 * Implies mb(), the result of xchg() must be visible
+                 * to core_state->dumper.
+                 */
+                if (atomic_dec_and_test(&core_state->nr_threads))
+                        complete(&core_state->startup);
+
+                for (;;) {
+                        set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+                        if (!self.task) /* see coredump_finish() */
+                                break;
+                        schedule();
+                }
+                __set_task_state(tsk, TASK_RUNNING);
                 down_read(&mm->mmap_sem);
         }
         atomic_inc(&mm->mm_count);
@@ -822,26 +839,50 @@ static void reparent_thread(struct task_struct *p, struct task_struct *father)
  * the child reaper process (ie "init") in our pid
  * space.
  */
+static struct task_struct *find_new_reaper(struct task_struct *father)
+{
+        struct pid_namespace *pid_ns = task_active_pid_ns(father);
+        struct task_struct *thread;
+
+        thread = father;
+        while_each_thread(father, thread) {
+                if (thread->flags & PF_EXITING)
+                        continue;
+                if (unlikely(pid_ns->child_reaper == father))
+                        pid_ns->child_reaper = thread;
+                return thread;
+        }
+
+        if (unlikely(pid_ns->child_reaper == father)) {
+                write_unlock_irq(&tasklist_lock);
+                if (unlikely(pid_ns == &init_pid_ns))
+                        panic("Attempted to kill init!");
+
+                zap_pid_ns_processes(pid_ns);
+                write_lock_irq(&tasklist_lock);
+                /*
+                 * We can not clear ->child_reaper or leave it alone.
+                 * There may by stealth EXIT_DEAD tasks on ->children,
+                 * forget_original_parent() must move them somewhere.
+                 */
+                pid_ns->child_reaper = init_pid_ns.child_reaper;
+        }
+
+        return pid_ns->child_reaper;
+}
+
 static void forget_original_parent(struct task_struct *father)
 {
-        struct task_struct *p, *n, *reaper = father;
+        struct task_struct *p, *n, *reaper;
         LIST_HEAD(ptrace_dead);
 
         write_lock_irq(&tasklist_lock);
-
+        reaper = find_new_reaper(father);
         /*
          * First clean up ptrace if we were using it.
          */
         ptrace_exit(father, &ptrace_dead);
 
-        do {
-                reaper = next_thread(reaper);
-                if (reaper == father) {
-                        reaper = task_child_reaper(father);
-                        break;
-                }
-        } while (reaper->flags & PF_EXITING);
-
         list_for_each_entry_safe(p, n, &father->children, sibling) {
                 p->real_parent = reaper;
                 if (p->parent == father) {
@@ -863,7 +904,8 @@ static void forget_original_parent(struct task_struct *father)
  */
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
-        int state;
+        int signal;
+        void *cookie;
 
         /*
          * This does two things:
@@ -900,33 +942,24 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
             !capable(CAP_KILL))
                 tsk->exit_signal = SIGCHLD;
 
-        /* If something other than our normal parent is ptracing us, then
-         * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
-         * only has special meaning to our real parent.
-         */
-        if (!task_detached(tsk) && thread_group_empty(tsk)) {
-                int signal = ptrace_reparented(tsk) ?
-                                SIGCHLD : tsk->exit_signal;
-                do_notify_parent(tsk, signal);
-        } else if (tsk->ptrace) {
-                do_notify_parent(tsk, SIGCHLD);
-        }
+        signal = tracehook_notify_death(tsk, &cookie, group_dead);
+        if (signal >= 0)
+                signal = do_notify_parent(tsk, signal);
 
-        state = EXIT_ZOMBIE;
-        if (task_detached(tsk) && likely(!tsk->ptrace))
-                state = EXIT_DEAD;
-        tsk->exit_state = state;
+        tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
 
         /* mt-exec, de_thread() is waiting for us */
         if (thread_group_leader(tsk) &&
-            tsk->signal->notify_count < 0 &&
-            tsk->signal->group_exit_task)
+            tsk->signal->group_exit_task &&
+            tsk->signal->notify_count < 0)
                 wake_up_process(tsk->signal->group_exit_task);
 
         write_unlock_irq(&tasklist_lock);
 
+        tracehook_report_death(tsk, signal, cookie, group_dead);
+
         /* If the process is dead, release it - nobody will wait for it */
-        if (state == EXIT_DEAD)
+        if (signal == DEATH_REAP)
                 release_task(tsk);
 }
 
@@ -958,39 +991,6 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
-static inline void exit_child_reaper(struct task_struct *tsk)
-{
-        if (likely(tsk->group_leader != task_child_reaper(tsk)))
-                return;
-
-        if (tsk->nsproxy->pid_ns == &init_pid_ns)
-                panic("Attempted to kill init!");
-
-        /*
-         * @tsk is the last thread in the 'cgroup-init' and is exiting.
-         * Terminate all remaining processes in the namespace and reap them
-         * before exiting @tsk.
-         *
-         * Note that @tsk (last thread of cgroup-init) may not necessarily
-         * be the child-reaper (i.e main thread of cgroup-init) of the
-         * namespace i.e the child_reaper may have already exited.
-         *
-         * Even after a child_reaper exits, we let it inherit orphaned children,
-         * because, pid_ns->child_reaper remains valid as long as there is
-         * at least one living sub-thread in the cgroup init.
-
-         * This living sub-thread of the cgroup-init will be notified when
-         * a child inherited by the 'child-reaper' exits (do_notify_parent()
-         * uses __group_send_sig_info()). Further, when reaping child processes,
-         * do_wait() iterates over children of all living sub threads.
-
-         * i.e even though 'child_reaper' thread is listed as the parent of the
-         * orphaned children, any living sub-thread in the cgroup-init can
-         * perform the role of the child_reaper.
-         */
-        zap_pid_ns_processes(tsk->nsproxy->pid_ns);
-}
-
 NORET_TYPE void do_exit(long code)
 {
         struct task_struct *tsk = current;
@@ -1005,10 +1005,7 @@ NORET_TYPE void do_exit(long code)
         if (unlikely(!tsk->pid))
                 panic("Attempted to kill the idle task!");
 
-        if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
-                current->ptrace_message = code;
-                ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
-        }
+        tracehook_report_exit(&code);
 
         /*
          * We're taking recursive faults here in do_exit. Safest is to just
@@ -1053,7 +1050,6 @@ NORET_TYPE void do_exit(long code)
         }
         group_dead = atomic_dec_and_test(&tsk->signal->live);
         if (group_dead) {
-                exit_child_reaper(tsk);
                 hrtimer_cancel(&tsk->signal->real_timer);
                 exit_itimers(tsk->signal);
         }
@@ -1354,6 +1350,8 @@ static int wait_task_zombie(struct task_struct *p, int options,
                 psig->coublock +=
                         task_io_get_oublock(p) +
                         sig->oublock + sig->coublock;
+                task_io_accounting_add(&psig->ioac, &p->ioac);
+                task_io_accounting_add(&psig->ioac, &sig->ioac);
                 spin_unlock_irq(&p->parent->sighand->siglock);
         }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index adefc1131f27..7ce2ebe84796 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -27,15 +27,18 @@
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>
+#include <linux/mmu_notifier.h>
 #include <linux/fs.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cgroup.h>
 #include <linux/security.h>
+#include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
+#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
@@ -92,6 +95,23 @@ int nr_processes(void)
 static struct kmem_cache *task_struct_cachep;
 #endif
 
+#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
+{
+#ifdef CONFIG_DEBUG_STACK_USAGE
+        gfp_t mask = GFP_KERNEL | __GFP_ZERO;
+#else
+        gfp_t mask = GFP_KERNEL;
+#endif
+        return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
+}
+
+static inline void free_thread_info(struct thread_info *ti)
+{
+        free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+}
+#endif
+
 /* SLAB cache for signal_struct structures (tsk->signal) */
 static struct kmem_cache *signal_cachep;
 
@@ -307,6 +327,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
                 }
 
                 /*
+                 * Clear hugetlb-related page reserves for children. This only
+                 * affects MAP_PRIVATE mappings. Faults generated by the child
+                 * are not guaranteed to succeed, even if read-only
+                 */
+                if (is_vm_hugetlb_page(tmp))
+                        reset_vma_resv_huge_pages(tmp);
+
+                /*
                  * Link in the new vma and copy the page table entries.
                  */
                 *pprev = tmp;
@@ -374,7 +402,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
         INIT_LIST_HEAD(&mm->mmlist);
         mm->flags = (current->mm) ? current->mm->flags
                                   : MMF_DUMP_FILTER_DEFAULT;
-        mm->core_waiters = 0;
+        mm->core_state = NULL;
         mm->nr_ptes = 0;
         set_mm_counter(mm, file_rss, 0);
         set_mm_counter(mm, anon_rss, 0);
@@ -387,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 
         if (likely(!mm_alloc_pgd(mm))) {
                 mm->def_flags = 0;
+                mmu_notifier_mm_init(mm);
                 return mm;
         }
 
@@ -419,6 +448,7 @@ void __mmdrop(struct mm_struct *mm)
         BUG_ON(mm == &init_mm);
         mm_free_pgd(mm);
         destroy_context(mm);
+        mmu_notifier_mm_destroy(mm);
         free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -448,7 +478,7 @@ EXPORT_SYMBOL_GPL(mmput);
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
- * Returns %NULL if the task has no mm.  Checks PF_BORROWED_MM (meaning
+ * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
  * this kernel workthread has transiently adopted a user mm with use_mm,
  * to do its AIO) is not set and if so returns a reference to it, after
  * bumping up the use count.  User must release the mm via mmput()
@@ -461,7 +491,7 @@ struct mm_struct *get_task_mm(struct task_struct *task)
         task_lock(task);
         mm = task->mm;
         if (mm) {
-                if (task->flags & PF_BORROWED_MM)
+                if (task->flags & PF_KTHREAD)
                         mm = NULL;
                 else
                         atomic_inc(&mm->mm_users);
@@ -630,13 +660,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
                 path_get(&old->root);
                 fs->pwd = old->pwd;
                 path_get(&old->pwd);
-                if (old->altroot.dentry) {
-                        fs->altroot = old->altroot;
-                        path_get(&old->altroot);
-                } else {
-                        fs->altroot.mnt = NULL;
-                        fs->altroot.dentry = NULL;
-                }
                 read_unlock(&old->lock);
         }
         return fs;
@@ -786,6 +809,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
         sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
         sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
+        task_io_accounting_init(&sig->ioac);
         sig->sum_sched_runtime = 0;
         INIT_LIST_HEAD(&sig->cpu_timers[0]);
         INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -833,8 +857,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
         new_flags &= ~PF_SUPERPRIV;
         new_flags |= PF_FORKNOEXEC;
-        if (!(clone_flags & CLONE_PTRACE))
-                p->ptrace = 0;
+        new_flags |= PF_STARTING;
         p->flags = new_flags;
         clear_freeze_flag(p);
 }
@@ -875,7 +898,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                                         struct pt_regs *regs,
                                         unsigned long stack_size,
                                         int __user *child_tidptr,
-                                        struct pid *pid)
+                                        struct pid *pid,
+                                        int trace)
 {
         int retval;
         struct task_struct *p;
@@ -968,13 +992,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->last_switch_timestamp = 0;
 #endif
 
-#ifdef CONFIG_TASK_XACCT
-        p->rchar = 0;           /* I/O counter: bytes read */
-        p->wchar = 0;           /* I/O counter: bytes written */
-        p->syscr = 0;           /* I/O counter: read syscalls */
-        p->syscw = 0;           /* I/O counter: write syscalls */
-#endif
-        task_io_accounting_init(p);
+        task_io_accounting_init(&p->ioac);
         acct_clear_integrals(p);
 
         p->it_virt_expires = cputime_zero;
@@ -1081,6 +1099,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (clone_flags & CLONE_THREAD)
                 p->tgid = current->tgid;
 
+        if (current->nsproxy != p->nsproxy) {
+                retval = ns_cgroup_clone(p, pid);
+                if (retval)
+                        goto bad_fork_free_pid;
+        }
+
         p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
         /*
          * Clear TID on mm_release()?
@@ -1125,8 +1149,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
          */
         p->group_leader = p;
         INIT_LIST_HEAD(&p->thread_group);
-        INIT_LIST_HEAD(&p->ptrace_entry);
-        INIT_LIST_HEAD(&p->ptraced);
 
         /* Now that the task is set up, run cgroup callbacks if
          * necessary. We need to run them before the task is visible
@@ -1157,7 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 p->real_parent = current->real_parent;
         else
                 p->real_parent = current;
-        p->parent = p->real_parent;
 
         spin_lock(&current->sighand->siglock);
 
@@ -1199,8 +1220,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
         if (likely(p->pid)) {
                 list_add_tail(&p->sibling, &p->real_parent->children);
-                if (unlikely(p->ptrace & PT_PTRACED))
-                        __ptrace_link(p, current->parent);
+                tracehook_finish_clone(p, clone_flags, trace);
 
                 if (thread_group_leader(p)) {
                         if (clone_flags & CLONE_NEWPID)
@@ -1285,29 +1305,13 @@ struct task_struct * __cpuinit fork_idle(int cpu)
         struct pt_regs regs;
 
         task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
-                                &init_struct_pid);
+                            &init_struct_pid, 0);
         if (!IS_ERR(task))
                 init_idle(task, cpu);
 
         return task;
 }
 
-static int fork_traceflag(unsigned clone_flags)
-{
-        if (clone_flags & CLONE_UNTRACED)
-                return 0;
-        else if (clone_flags & CLONE_VFORK) {
-                if (current->ptrace & PT_TRACE_VFORK)
-                        return PTRACE_EVENT_VFORK;
-        } else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-                if (current->ptrace & PT_TRACE_CLONE)
-                        return PTRACE_EVENT_CLONE;
-        } else if (current->ptrace & PT_TRACE_FORK)
-                return PTRACE_EVENT_FORK;
-
-        return 0;
-}
-
 /*
  *  Ok, this is the main fork-routine.
  *
@@ -1342,14 +1346,14 @@ long do_fork(unsigned long clone_flags,
                 }
         }
 
-        if (unlikely(current->ptrace)) {
-                trace = fork_traceflag (clone_flags);
-                if (trace)
-                        clone_flags |= CLONE_PTRACE;
-        }
+        /*
+         * When called from kernel_thread, don't do user tracing stuff.
+         */
+        if (likely(user_mode(regs)))
+                trace = tracehook_prepare_clone(clone_flags);
 
         p = copy_process(clone_flags, stack_start, regs, stack_size,
-                        child_tidptr, NULL);
+                         child_tidptr, NULL, trace);
         /*
          * Do this prior waking up the new thread - the thread pointer
          * might get invalid after that point, if the thread exits quickly.
@@ -1367,32 +1371,35 @@ long do_fork(unsigned long clone_flags,
                         init_completion(&vfork);
                 }
 
-                if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
+                tracehook_report_clone(trace, regs, clone_flags, nr, p);
+
+                /*
+                 * We set PF_STARTING at creation in case tracing wants to
+                 * use this to distinguish a fully live task from one that
+                 * hasn't gotten to tracehook_report_clone() yet.  Now we
+                 * clear it and set the child going.
+                 */
+                p->flags &= ~PF_STARTING;
+
+                if (unlikely(clone_flags & CLONE_STOPPED)) {
                         /*
                          * We'll start up with an immediate SIGSTOP.
                          */
                         sigaddset(&p->pending.signal, SIGSTOP);
                         set_tsk_thread_flag(p, TIF_SIGPENDING);
-                }
-
-                if (!(clone_flags & CLONE_STOPPED))
-                        wake_up_new_task(p, clone_flags);
-                else
                         __set_task_state(p, TASK_STOPPED);
-
-                if (unlikely (trace)) {
-                        current->ptrace_message = nr;
-                        ptrace_notify ((trace << 8) | SIGTRAP);
+                } else {
+                        wake_up_new_task(p, clone_flags);
                 }
 
+                tracehook_report_clone_complete(trace, regs,
+                                                clone_flags, nr, p);
+
                 if (clone_flags & CLONE_VFORK) {
                         freezer_do_not_count();
                         wait_for_completion(&vfork);
                         freezer_count();
-                        if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
-                                current->ptrace_message = nr;
-                                ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
-                        }
+                        tracehook_report_vfork_done(p, nr);
                 }
         } else {
                 nr = PTR_ERR(p);
@@ -1404,7 +1411,7 @@ long do_fork(unsigned long clone_flags,
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
 
-static void sighand_ctor(struct kmem_cache *cachep, void *data)
+static void sighand_ctor(void *data)
 {
         struct sighand_struct *sighand = data;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 240c64d59267..d663338cb4a8 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -28,8 +28,7 @@ void dynamic_irq_init(unsigned int irq)
         unsigned long flags;
 
         if (irq >= NR_IRQS) {
-                printk(KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-                WARN_ON(1);
+                WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
                 return;
         }
 
@@ -62,8 +61,7 @@ void dynamic_irq_cleanup(unsigned int irq)
         unsigned long flags;
 
         if (irq >= NR_IRQS) {
-                printk(KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-                WARN_ON(1);
+                WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
                 return;
         }
 
@@ -71,9 +69,8 @@ void dynamic_irq_cleanup(unsigned int irq)
         spin_lock_irqsave(&desc->lock, flags);
         if (desc->action) {
                 spin_unlock_irqrestore(&desc->lock, flags);
-                printk(KERN_ERR "Destroying IRQ%d without calling free_irq\n",
+                WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
                         irq);
-                WARN_ON(1);
                 return;
         }
         desc->msi_desc = NULL;
@@ -96,8 +93,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
         unsigned long flags;
 
         if (irq >= NR_IRQS) {
-                printk(KERN_ERR "Trying to install chip for IRQ%d\n", irq);
-                WARN_ON(1);
+                WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
                 return -EINVAL;
         }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9aa3e7b81389..d62f69ba7453 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -177,8 +177,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
 {
         switch (desc->depth) {
         case 0:
-                printk(KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
-                WARN_ON(1);
+                WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
                 break;
         case 1: {
                 unsigned int status = desc->status & ~IRQ_DISABLED;
@@ -217,6 +216,17 @@ void enable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(enable_irq);
 
+int set_irq_wake_real(unsigned int irq, unsigned int on)
+{
+        struct irq_desc *desc = irq_desc + irq;
+        int ret = -ENXIO;
+
+        if (desc->chip->set_wake)
+                ret = desc->chip->set_wake(irq, on);
+
+        return ret;
+}
+
 /**
  *      set_irq_wake - control irq power management wakeup
  *      @irq:   interrupt to control
@@ -233,30 +243,32 @@ 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;
+        int ret = 0;
 
         /* wakeup-capable irqs can be shared between drivers that
          * don't need to have the same sleep mode behaviors.
          */
         spin_lock_irqsave(&desc->lock, flags);
         if (on) {
-                if (desc->wake_depth++ == 0)
-                        desc->status |= IRQ_WAKEUP;
-                else
-                        set_wake = NULL;
+                if (desc->wake_depth++ == 0) {
+                        ret = set_irq_wake_real(irq, on);
+                        if (ret)
+                                desc->wake_depth = 0;
+                        else
+                                desc->status |= IRQ_WAKEUP;
+                }
         } else {
                 if (desc->wake_depth == 0) {
-                        printk(KERN_WARNING "Unbalanced IRQ %d "
-                                        "wake disable\n", irq);
-                        WARN_ON(1);
-                } else if (--desc->wake_depth == 0)
-                        desc->status &= ~IRQ_WAKEUP;
-                else
-                        set_wake = NULL;
+                        WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
+                } else if (--desc->wake_depth == 0) {
+                        ret = set_irq_wake_real(irq, on);
+                        if (ret)
+                                desc->wake_depth = 1;
+                        else
+                                desc->status &= ~IRQ_WAKEUP;
+                }
         }
-        if (set_wake)
-                ret = desc->chip->set_wake(irq, on);
+
         spin_unlock_irqrestore(&desc->lock, flags);
         return ret;
 }
@@ -293,6 +305,31 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
                 desc->handle_irq = NULL;
 }
 
+static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
+                unsigned long flags)
+{
+        int ret;
+
+        if (!chip || !chip->set_type) {
+                /*
+                 * IRQF_TRIGGER_* but the PIC does not support multiple
+                 * flow-types?
+                 */
+                pr_warning("No set_type function for IRQ %d (%s)\n", irq,
+                                chip ? (chip->name ? : "unknown") : "unknown");
+                return 0;
+        }
+
+        ret = chip->set_type(irq, flags & IRQF_TRIGGER_MASK);
+
+        if (ret)
+                pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
+                                (int)(flags & IRQF_TRIGGER_MASK),
+                                irq, chip->set_type);
+
+        return ret;
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -304,6 +341,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
         const char *old_name = NULL;
         unsigned long flags;
         int shared = 0;
+        int ret;
 
         if (irq >= NR_IRQS)
                 return -EINVAL;
@@ -361,35 +399,23 @@ int setup_irq(unsigned int irq, struct irqaction *new)
                 shared = 1;
         }
 
-        *p = new;
-
-        /* Exclude IRQ from balancing */
-        if (new->flags & IRQF_NOBALANCING)
-                desc->status |= IRQ_NO_BALANCING;
-
         if (!shared) {
                 irq_chip_set_defaults(desc->chip);
 
-#if defined(CONFIG_IRQ_PER_CPU)
-                if (new->flags & IRQF_PERCPU)
-                        desc->status |= IRQ_PER_CPU;
-#endif
-
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
-                        if (desc->chip->set_type)
-                                desc->chip->set_type(irq,
-                                                new->flags & IRQF_TRIGGER_MASK);
-                        else
-                                /*
-                                 * IRQF_TRIGGER_* but the PIC does not support
-                                 * multiple flow-types?
-                                 */
-                                printk(KERN_WARNING "No IRQF_TRIGGER set_type "
-                                       "function for IRQ %d (%s)\n", irq,
-                                       desc->chip->name);
+                        ret = __irq_set_trigger(desc->chip, irq, new->flags);
+
+                        if (ret) {
+                                spin_unlock_irqrestore(&desc->lock, flags);
+                                return ret;
+                        }
                 } else
                         compat_irq_chip_set_default_handler(desc);
+#if defined(CONFIG_IRQ_PER_CPU)
+                if (new->flags & IRQF_PERCPU)
+                        desc->status |= IRQ_PER_CPU;
+#endif
 
                 desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING |
                                   IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
@@ -405,6 +431,13 @@ int setup_irq(unsigned int irq, struct irqaction *new)
                 /* Set default affinity mask once everything is setup */
                 irq_select_affinity(irq);
         }
+
+        *p = new;
+
+        /* Exclude IRQ from balancing */
+        if (new->flags & IRQF_NOBALANCING)
+                desc->status |= IRQ_NO_BALANCING;
+
         /* Reset broken irq detection when installing new handler */
         desc->irq_count = 0;
         desc->irqs_unhandled = 0;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6c6d35d68ee9..a09dd29c2fd7 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -8,6 +8,7 @@
 
 #include <linux/irq.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/interrupt.h>
 
 #include "internals.h"
@@ -16,23 +17,18 @@ static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
 
-static int irq_affinity_read_proc(char *page, char **start, off_t off,
-                                  int count, int *eof, void *data)
+static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
-        struct irq_desc *desc = irq_desc + (long)data;
+        struct irq_desc *desc = irq_desc + (long)m->private;
         cpumask_t *mask = &desc->affinity;
-        int len;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PENDING)
                 mask = &desc->pending_mask;
 #endif
-        len = cpumask_scnprintf(page, count, *mask);
-
-        if (count - len < 2)
-                return -EINVAL;
-        len += sprintf(page + len, "\n");
-        return len;
+        seq_cpumask(m, mask);
+        seq_putc(m, '\n');
+        return 0;
 }
 
 #ifndef is_affinity_mask_valid
@@ -40,11 +36,12 @@ static int irq_affinity_read_proc(char *page, char **start, off_t off,
 #endif
 
 int no_irq_affinity;
-static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
-                                   unsigned long count, void *data)
+static ssize_t irq_affinity_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *pos)
 {
-        unsigned int irq = (int)(long)data, full_count = count, err;
+        unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data;
         cpumask_t new_value;
+        int err;
 
         if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
             irq_balancing_disabled(irq))
@@ -65,28 +62,38 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
         if (!cpus_intersects(new_value, cpu_online_map))
                 /* Special case for empty set - allow the architecture
                    code to set default SMP affinity. */
-                return irq_select_affinity(irq) ? -EINVAL : full_count;
+                return irq_select_affinity(irq) ? -EINVAL : count;
 
         irq_set_affinity(irq, new_value);
 
-        return full_count;
+        return count;
 }
 
-static int default_affinity_read(char *page, char **start, off_t off,
-                                  int count, int *eof, void *data)
+static int irq_affinity_proc_open(struct inode *inode, struct file *file)
 {
-        int len = cpumask_scnprintf(page, count, irq_default_affinity);
-        if (count - len < 2)
-                return -EINVAL;
-        len += sprintf(page + len, "\n");
-        return len;
+        return single_open(file, irq_affinity_proc_show, PDE(inode)->data);
 }
 
-static int default_affinity_write(struct file *file, const char __user *buffer,
-                                   unsigned long count, void *data)
+static const struct file_operations irq_affinity_proc_fops = {
+        .open           = irq_affinity_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = irq_affinity_proc_write,
+};
+
+static int default_affinity_show(struct seq_file *m, void *v)
+{
+        seq_cpumask(m, &irq_default_affinity);
+        seq_putc(m, '\n');
+        return 0;
+}
+
+static ssize_t default_affinity_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
-        unsigned int full_count = count, err;
         cpumask_t new_value;
+        int err;
 
         err = cpumask_parse_user(buffer, count, new_value);
         if (err)
@@ -105,8 +112,21 @@ static int default_affinity_write(struct file *file, const char __user *buffer,
 
         irq_default_affinity = new_value;
 
-        return full_count;
+        return count;
 }
+
+static int default_affinity_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, default_affinity_show, NULL);
+}
+
+static const struct file_operations default_affinity_proc_fops = {
+        .open           = default_affinity_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = default_affinity_write,
+};
 #endif
 
 static int irq_spurious_read(char *page, char **start, off_t off,
@@ -178,16 +198,9 @@ void register_irq_proc(unsigned int irq)
         irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
 
 #ifdef CONFIG_SMP
-        {
-                /* create /proc/irq/<irq>/smp_affinity */
-                entry = create_proc_entry("smp_affinity", 0600, irq_desc[irq].dir);
-
-                if (entry) {
-                        entry->data = (void *)(long)irq;
-                        entry->read_proc = irq_affinity_read_proc;
-                        entry->write_proc = irq_affinity_write_proc;
-                }
-        }
+        /* create /proc/irq/<irq>/smp_affinity */
+        proc_create_data("smp_affinity", 0600, irq_desc[irq].dir,
+                         &irq_affinity_proc_fops, (void *)(long)irq);
 #endif
 
         entry = create_proc_entry("spurious", 0444, irq_desc[irq].dir);
@@ -208,15 +221,8 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 void register_default_affinity_proc(void)
 {
 #ifdef CONFIG_SMP
-        struct proc_dir_entry *entry;
-
-        /* create /proc/irq/default_smp_affinity */
-        entry = create_proc_entry("default_smp_affinity", 0600, root_irq_dir);
-        if (entry) {
-                entry->data = NULL;
-                entry->read_proc  = default_affinity_read;
-                entry->write_proc = default_affinity_write;
-        }
+        proc_create("irq/default_smp_affinity", 0600, NULL,
+                    &default_affinity_proc_fops);
 #endif
 }
 
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 6fc0040f3e3a..38fc10ac7541 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -176,7 +176,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
         high = kallsyms_num_syms;
 
         while (high - low > 1) {
-                mid = (low + high) / 2;
+                mid = low + (high - low) / 2;
                 if (kallsyms_addresses[mid] <= addr)
                         low = mid;
                 else
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 1c5fcacbcf33..aef265325cd3 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/kexec.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/highmem.h>
 #include <linux/syscalls.h>
@@ -24,6 +24,12 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -71,7 +77,7 @@ int kexec_should_crash(struct task_struct *p)
  *
  * The code for the transition from the current kernel to the
  * the new kernel is placed in the control_code_buffer, whose size
- * is given by KEXEC_CONTROL_CODE_SIZE.  In the best case only a single
+ * is given by KEXEC_CONTROL_PAGE_SIZE.  In the best case only a single
  * page of memory is necessary, but some architectures require more.
  * Because this memory must be identity mapped in the transition from
  * virtual to physical addresses it must live in the range
@@ -236,12 +242,18 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
          */
         result = -ENOMEM;
         image->control_code_page = kimage_alloc_control_pages(image,
-                                           get_order(KEXEC_CONTROL_CODE_SIZE));
+                                           get_order(KEXEC_CONTROL_PAGE_SIZE));
         if (!image->control_code_page) {
                 printk(KERN_ERR "Could not allocate control_code_buffer\n");
                 goto out;
         }
 
+        image->swap_page = kimage_alloc_control_pages(image, 0);
+        if (!image->swap_page) {
+                printk(KERN_ERR "Could not allocate swap buffer\n");
+                goto out;
+        }
+
         result = 0;
  out:
         if (result == 0)
@@ -305,7 +317,7 @@ static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
          */
         result = -ENOMEM;
         image->control_code_page = kimage_alloc_control_pages(image,
-                                           get_order(KEXEC_CONTROL_CODE_SIZE));
+                                           get_order(KEXEC_CONTROL_PAGE_SIZE));
         if (!image->control_code_page) {
                 printk(KERN_ERR "Could not allocate control_code_buffer\n");
                 goto out;
@@ -589,14 +601,12 @@ static void kimage_free_extra_pages(struct kimage *image)
         kimage_free_page_list(&image->unuseable_pages);
 
 }
-static int kimage_terminate(struct kimage *image)
+static void kimage_terminate(struct kimage *image)
 {
         if (*image->entry != 0)
                 image->entry++;
 
         *image->entry = IND_DONE;
-
-        return 0;
 }
 
 #define for_each_kimage_entry(image, ptr, entry) \
@@ -743,8 +753,14 @@ static struct page *kimage_alloc_page(struct kimage *image,
                         *old = addr | (*old & ~PAGE_MASK);
 
                         /* The old page I have found cannot be a
-                         * destination page, so return it.
+                         * destination page, so return it if it's
+                         * gfp_flags honor the ones passed in.
                          */
+                        if (!(gfp_mask & __GFP_HIGHMEM) &&
+                            PageHighMem(old_page)) {
+                                kimage_free_pages(old_page);
+                                continue;
+                        }
                         addr = old_addr;
                         page = old_page;
                         break;
@@ -914,19 +930,14 @@ static int kimage_load_segment(struct kimage *image,
  */
 struct kimage *kexec_image;
 struct kimage *kexec_crash_image;
-/*
- * A home grown binary mutex.
- * Nothing can wait so this mutex is safe to use
- * in interrupt context :)
- */
-static int kexec_lock;
+
+static DEFINE_MUTEX(kexec_mutex);
 
 asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
                                 struct kexec_segment __user *segments,
                                 unsigned long flags)
 {
         struct kimage **dest_image, *image;
-        int locked;
         int result;
 
         /* We only trust the superuser with rebooting the system. */
@@ -962,8 +973,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
          *
          * KISS: always take the mutex.
          */
-        locked = xchg(&kexec_lock, 1);
-        if (locked)
+        if (!mutex_trylock(&kexec_mutex))
                 return -EBUSY;
 
         dest_image = &kexec_image;
@@ -988,6 +998,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
                 if (result)
                         goto out;
 
+                if (flags & KEXEC_PRESERVE_CONTEXT)
+                        image->preserve_context = 1;
                 result = machine_kexec_prepare(image);
                 if (result)
                         goto out;
@@ -997,16 +1009,13 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
                         if (result)
                                 goto out;
                 }
-                result = kimage_terminate(image);
-                if (result)
-                        goto out;
+                kimage_terminate(image);
         }
         /* Install the new kernel, and  Uninstall the old */
         image = xchg(dest_image, image);
 
 out:
-        locked = xchg(&kexec_lock, 0); /* Release the mutex */
-        BUG_ON(!locked);
+        mutex_unlock(&kexec_mutex);
         kimage_free(image);
 
         return result;
@@ -1053,10 +1062,7 @@ asmlinkage long compat_sys_kexec_load(unsigned long entry,
 
 void crash_kexec(struct pt_regs *regs)
 {
-        int locked;
-
-
-        /* Take the kexec_lock here to prevent sys_kexec_load
+        /* Take the kexec_mutex here to prevent sys_kexec_load
          * running on one cpu from replacing the crash kernel
          * we are using after a panic on a different cpu.
          *
@@ -1064,8 +1070,7 @@ void crash_kexec(struct pt_regs *regs)
          * of memory the xchg(&kexec_crash_image) would be
          * sufficient.  But since I reuse the memory...
          */
-        locked = xchg(&kexec_lock, 1);
-        if (!locked) {
+        if (mutex_trylock(&kexec_mutex)) {
                 if (kexec_crash_image) {
                         struct pt_regs fixed_regs;
                         crash_setup_regs(&fixed_regs, regs);
@@ -1073,8 +1078,7 @@ void crash_kexec(struct pt_regs *regs)
                         machine_crash_shutdown(&fixed_regs);
                         machine_kexec(kexec_crash_image);
                 }
-                locked = xchg(&kexec_lock, 0);
-                BUG_ON(!locked);
+                mutex_unlock(&kexec_mutex);
         }
 }
 
@@ -1415,3 +1419,79 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+/*
+ * Move into place and start executing a preloaded standalone
+ * executable.  If nothing was preloaded return an error.
+ */
+int kernel_kexec(void)
+{
+        int error = 0;
+
+        if (!mutex_trylock(&kexec_mutex))
+                return -EBUSY;
+        if (!kexec_image) {
+                error = -EINVAL;
+                goto Unlock;
+        }
+
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context) {
+                mutex_lock(&pm_mutex);
+                pm_prepare_console();
+                error = freeze_processes();
+                if (error) {
+                        error = -EBUSY;
+                        goto Restore_console;
+                }
+                suspend_console();
+                error = device_suspend(PMSG_FREEZE);
+                if (error)
+                        goto Resume_console;
+                error = disable_nonboot_cpus();
+                if (error)
+                        goto Resume_devices;
+                device_pm_lock();
+                local_irq_disable();
+                /* At this point, device_suspend() has been called,
+                 * but *not* device_power_down(). We *must*
+                 * device_power_down() now.  Otherwise, drivers for
+                 * some devices (e.g. interrupt controllers) become
+                 * desynchronized with the actual state of the
+                 * hardware at resume time, and evil weirdness ensues.
+                 */
+                error = device_power_down(PMSG_FREEZE);
+                if (error)
+                        goto Enable_irqs;
+        } else
+#endif
+        {
+                kernel_restart_prepare(NULL);
+                printk(KERN_EMERG "Starting new kernel\n");
+                machine_shutdown();
+        }
+
+        machine_kexec(kexec_image);
+
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context) {
+                device_power_up(PMSG_RESTORE);
+ Enable_irqs:
+                local_irq_enable();
+                device_pm_unlock();
+                enable_nonboot_cpus();
+ Resume_devices:
+                device_resume(PMSG_RESTORE);
+ Resume_console:
+                resume_console();
+                thaw_processes();
+ Restore_console:
+                pm_restore_console();
+                mutex_unlock(&pm_mutex);
+        }
+#endif
+
+ Unlock:
+        mutex_unlock(&kexec_mutex);
+        return error;
+}
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 3ec23c3ec97f..25d955dbb989 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -56,12 +56,14 @@
 
 static int kgdb_break_asap;
 
+#define KGDB_MAX_THREAD_QUERY 17
 struct kgdb_state {
         int                     ex_vector;
         int                     signo;
         int                     err_code;
         int                     cpu;
         int                     pass_exception;
+        unsigned long           thr_query;
         unsigned long           threadid;
         long                    kgdb_usethreadid;
         struct pt_regs          *linux_regs;
@@ -166,13 +168,6 @@ early_param("nokgdbroundup", opt_nokgdbroundup);
  * Weak aliases for breakpoint management,
  * can be overriden by architectures when needed:
  */
-int __weak kgdb_validate_break_address(unsigned long addr)
-{
-        char tmp_variable[BREAK_INSTR_SIZE];
-
-        return probe_kernel_read(tmp_variable, (char *)addr, BREAK_INSTR_SIZE);
-}
-
 int __weak kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr)
 {
         int err;
@@ -191,6 +186,25 @@ int __weak kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle)
                                   (char *)bundle, BREAK_INSTR_SIZE);
 }
 
+int __weak kgdb_validate_break_address(unsigned long addr)
+{
+        char tmp_variable[BREAK_INSTR_SIZE];
+        int err;
+        /* Validate setting the breakpoint and then removing it.  In the
+         * remove fails, the kernel needs to emit a bad message because we
+         * are deep trouble not being able to put things back the way we
+         * found them.
+         */
+        err = kgdb_arch_set_breakpoint(addr, tmp_variable);
+        if (err)
+                return err;
+        err = kgdb_arch_remove_breakpoint(addr, tmp_variable);
+        if (err)
+                printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
+                   "memory destroyed at: %lx", addr);
+        return err;
+}
+
 unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs)
 {
         return instruction_pointer(regs);
@@ -433,9 +447,14 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val)
 {
         int hex_val;
         int num = 0;
+        int negate = 0;
 
         *long_val = 0;
 
+        if (**ptr == '-') {
+                negate = 1;
+                (*ptr)++;
+        }
         while (**ptr) {
                 hex_val = hex(**ptr);
                 if (hex_val < 0)
@@ -446,6 +465,9 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val)
                 (*ptr)++;
         }
 
+        if (negate)
+                *long_val = -*long_val;
+
         return num;
 }
 
@@ -466,7 +488,7 @@ static int write_mem_msg(int binary)
                 if (err)
                         return err;
                 if (CACHE_FLUSH_IS_SAFE)
-                        flush_icache_range(addr, addr + length + 1);
+                        flush_icache_range(addr, addr + length);
                 return 0;
         }
 
@@ -515,10 +537,16 @@ static void int_to_threadref(unsigned char *id, int value)
 static struct task_struct *getthread(struct pt_regs *regs, int tid)
 {
         /*
-         * Non-positive TIDs are remapped idle tasks:
+         * Non-positive TIDs are remapped to the cpu shadow information
          */
-        if (tid <= 0)
-                return idle_task(-tid);
+        if (tid == 0 || tid == -1)
+                tid = -atomic_read(&kgdb_active) - 2;
+        if (tid < 0) {
+                if (kgdb_info[-tid - 2].task)
+                        return kgdb_info[-tid - 2].task;
+                else
+                        return idle_task(-tid - 2);
+        }
 
         /*
          * find_task_by_pid_ns() does not take the tasklist lock anymore
@@ -725,14 +753,15 @@ setundefined:
 }
 
 /*
- * Remap normal tasks to their real PID, idle tasks to -1 ... -NR_CPUs:
+ * Remap normal tasks to their real PID,
+ * CPU shadow threads are mapped to -CPU - 2
  */
 static inline int shadow_pid(int realpid)
 {
         if (realpid)
                 return realpid;
 
-        return -1-raw_smp_processor_id();
+        return -raw_smp_processor_id() - 2;
 }
 
 static char gdbmsgbuf[BUFMAX + 1];
@@ -826,7 +855,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks)
                 local_debuggerinfo = kgdb_info[ks->cpu].debuggerinfo;
         } else {
                 local_debuggerinfo = NULL;
-                for (i = 0; i < NR_CPUS; i++) {
+                for_each_online_cpu(i) {
                         /*
                          * Try to find the task on some other
                          * or possibly this node if we do not
@@ -960,10 +989,13 @@ static int gdb_cmd_reboot(struct kgdb_state *ks)
 /* Handle the 'q' query packets */
 static void gdb_cmd_query(struct kgdb_state *ks)
 {
-        struct task_struct *thread;
+        struct task_struct *g;
+        struct task_struct *p;
         unsigned char thref[8];
         char *ptr;
         int i;
+        int cpu;
+        int finished = 0;
 
         switch (remcom_in_buffer[1]) {
         case 's':
@@ -973,22 +1005,34 @@ static void gdb_cmd_query(struct kgdb_state *ks)
                         break;
                 }
 
-                if (remcom_in_buffer[1] == 'f')
-                        ks->threadid = 1;
-
+                i = 0;
                 remcom_out_buffer[0] = 'm';
                 ptr = remcom_out_buffer + 1;
-
-                for (i = 0; i < 17; ks->threadid++) {
-                        thread = getthread(ks->linux_regs, ks->threadid);
-                        if (thread) {
-                                int_to_threadref(thref, ks->threadid);
+                if (remcom_in_buffer[1] == 'f') {
+                        /* Each cpu is a shadow thread */
+                        for_each_online_cpu(cpu) {
+                                ks->thr_query = 0;
+                                int_to_threadref(thref, -cpu - 2);
                                 pack_threadid(ptr, thref);
                                 ptr += BUF_THREAD_ID_SIZE;
                                 *(ptr++) = ',';
                                 i++;
                         }
                 }
+
+                do_each_thread(g, p) {
+                        if (i >= ks->thr_query && !finished) {
+                                int_to_threadref(thref, p->pid);
+                                pack_threadid(ptr, thref);
+                                ptr += BUF_THREAD_ID_SIZE;
+                                *(ptr++) = ',';
+                                ks->thr_query++;
+                                if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0)
+                                        finished = 1;
+                        }
+                        i++;
+                } while_each_thread(g, p);
+
                 *(--ptr) = '\0';
                 break;
 
@@ -1011,15 +1055,15 @@ static void gdb_cmd_query(struct kgdb_state *ks)
                         error_packet(remcom_out_buffer, -EINVAL);
                         break;
                 }
-                if (ks->threadid > 0) {
+                if ((int)ks->threadid > 0) {
                         kgdb_mem2hex(getthread(ks->linux_regs,
                                         ks->threadid)->comm,
                                         remcom_out_buffer, 16);
                 } else {
                         static char tmpstr[23 + BUF_THREAD_ID_SIZE];
 
-                        sprintf(tmpstr, "Shadow task %d for pid 0",
-                                        (int)(-ks->threadid-1));
+                        sprintf(tmpstr, "shadowCPU%d",
+                                        (int)(-ks->threadid - 2));
                         kgdb_mem2hex(tmpstr, remcom_out_buffer, strlen(tmpstr));
                 }
                 break;
@@ -1418,7 +1462,7 @@ acquirelock:
          * Get the passive CPU lock which will hold all the non-primary
          * CPU in a spin state while the debugger is active
          */
-        if (!kgdb_single_step || !kgdb_contthread) {
+        if (!kgdb_single_step) {
                 for (i = 0; i < NR_CPUS; i++)
                         atomic_set(&passive_cpu_wait[i], 1);
         }
@@ -1431,7 +1475,7 @@ acquirelock:
 
 #ifdef CONFIG_SMP
         /* Signal the other CPUs to enter kgdb_wait() */
-        if ((!kgdb_single_step || !kgdb_contthread) && kgdb_do_roundup)
+        if ((!kgdb_single_step) && kgdb_do_roundup)
                 kgdb_roundup_cpus(flags);
 #endif
 
@@ -1450,7 +1494,7 @@ acquirelock:
         kgdb_post_primary_code(ks->linux_regs, ks->ex_vector, ks->err_code);
         kgdb_deactivate_sw_breakpoints();
         kgdb_single_step = 0;
-        kgdb_contthread = NULL;
+        kgdb_contthread = current;
         exception_level = 0;
 
         /* Talk to debugger with gdbserial protocol */
@@ -1464,7 +1508,7 @@ acquirelock:
         kgdb_info[ks->cpu].task = NULL;
         atomic_set(&cpu_in_kgdb[ks->cpu], 0);
 
-        if (!kgdb_single_step || !kgdb_contthread) {
+        if (!kgdb_single_step) {
                 for (i = NR_CPUS-1; i >= 0; i--)
                         atomic_set(&passive_cpu_wait[i], 0);
                 /*
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 8df97d3dfda8..2456d1a0befb 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -42,7 +42,7 @@ extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
 
 /*
         modprobe_path is set via /proc/sys.
@@ -352,16 +352,17 @@ static inline void register_pm_notifier_callback(void) {}
  * @path: path to usermode executable
  * @argv: arg vector for process
  * @envp: environment for process
+ * @gfp_mask: gfp mask for memory allocation
  *
  * Returns either %NULL on allocation failure, or a subprocess_info
  * structure.  This should be passed to call_usermodehelper_exec to
  * exec the process and free the structure.
  */
-struct subprocess_info *call_usermodehelper_setup(char *path,
-                                                  char **argv, char **envp)
+struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
+                                                  char **envp, gfp_t gfp_mask)
 {
         struct subprocess_info *sub_info;
-        sub_info = kzalloc(sizeof(struct subprocess_info),  GFP_ATOMIC);
+        sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
         if (!sub_info)
                 goto out;
 
@@ -417,12 +418,12 @@ int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info,
 {
         struct file *f;
 
-        f = create_write_pipe();
+        f = create_write_pipe(0);
         if (IS_ERR(f))
                 return PTR_ERR(f);
         *filp = f;
 
-        f = create_read_pipe(f);
+        f = create_read_pipe(f, 0);
         if (IS_ERR(f)) {
                 free_write_pipe(*filp);
                 return PTR_ERR(f);
@@ -494,7 +495,7 @@ int call_usermodehelper_pipe(char *path, char **argv, char **envp,
         struct subprocess_info *sub_info;
         int ret;
 
-        sub_info = call_usermodehelper_setup(path, argv, envp);
+        sub_info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL);
         if (sub_info == NULL)
                 return -ENOMEM;
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1485ca8d0e00..75bc2cd9ebc6 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -62,6 +62,7 @@
         addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
 #endif
 
+static int kprobes_initialized;
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
 static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
@@ -69,8 +70,15 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 static bool kprobe_enabled;
 
 DEFINE_MUTEX(kprobe_mutex);             /* Protects kprobe_table */
-DEFINE_SPINLOCK(kretprobe_lock);        /* Protects kretprobe_inst_table */
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
+static struct {
+        spinlock_t lock ____cacheline_aligned;
+} kretprobe_table_locks[KPROBE_TABLE_SIZE];
+
+static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
+{
+        return &(kretprobe_table_locks[hash].lock);
+}
 
 /*
  * Normally, functions that we'd want to prohibit kprobes in, are marked
@@ -368,26 +376,53 @@ void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
         return;
 }
 
-/* Called with kretprobe_lock held */
 void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
                                 struct hlist_head *head)
 {
+        struct kretprobe *rp = ri->rp;
+
         /* remove rp inst off the rprobe_inst_table */
         hlist_del(&ri->hlist);
-        if (ri->rp) {
-                /* remove rp inst off the used list */
-                hlist_del(&ri->uflist);
-                /* put rp inst back onto the free list */
-                INIT_HLIST_NODE(&ri->uflist);
-                hlist_add_head(&ri->uflist, &ri->rp->free_instances);
+        INIT_HLIST_NODE(&ri->hlist);
+        if (likely(rp)) {
+                spin_lock(&rp->lock);
+                hlist_add_head(&ri->hlist, &rp->free_instances);
+                spin_unlock(&rp->lock);
         } else
                 /* Unregistering */
                 hlist_add_head(&ri->hlist, head);
 }
 
-struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk)
+void kretprobe_hash_lock(struct task_struct *tsk,
+                         struct hlist_head **head, unsigned long *flags)
 {
-        return &kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)];
+        unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+        spinlock_t *hlist_lock;
+
+        *head = &kretprobe_inst_table[hash];
+        hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_lock_irqsave(hlist_lock, *flags);
+}
+
+void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
+{
+        spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_lock_irqsave(hlist_lock, *flags);
+}
+
+void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags)
+{
+        unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+        spinlock_t *hlist_lock;
+
+        hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_unlock_irqrestore(hlist_lock, *flags);
+}
+
+void kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
+{
+        spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
 /*
@@ -401,17 +436,21 @@ void __kprobes kprobe_flush_task(struct task_struct *tk)
         struct kretprobe_instance *ri;
         struct hlist_head *head, empty_rp;
         struct hlist_node *node, *tmp;
-        unsigned long flags = 0;
+        unsigned long hash, flags = 0;
 
-        INIT_HLIST_HEAD(&empty_rp);
-        spin_lock_irqsave(&kretprobe_lock, flags);
-        head = kretprobe_inst_table_head(tk);
+        if (unlikely(!kprobes_initialized))
+                /* Early boot.  kretprobe_table_locks not yet initialized. */
+                return;
+
+        hash = hash_ptr(tk, KPROBE_HASH_BITS);
+        head = &kretprobe_inst_table[hash];
+        kretprobe_table_lock(hash, &flags);
         hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
                 if (ri->task == tk)
                         recycle_rp_inst(ri, &empty_rp);
         }
-        spin_unlock_irqrestore(&kretprobe_lock, flags);
-
+        kretprobe_table_unlock(hash, &flags);
+        INIT_HLIST_HEAD(&empty_rp);
         hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
                 hlist_del(&ri->hlist);
                 kfree(ri);
@@ -423,24 +462,29 @@ static inline void free_rp_inst(struct kretprobe *rp)
         struct kretprobe_instance *ri;
         struct hlist_node *pos, *next;
 
-        hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, uflist) {
-                hlist_del(&ri->uflist);
+        hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, hlist) {
+                hlist_del(&ri->hlist);
                 kfree(ri);
         }
 }
 
 static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
 {
-        unsigned long flags;
+        unsigned long flags, hash;
         struct kretprobe_instance *ri;
         struct hlist_node *pos, *next;
+        struct hlist_head *head;
+
         /* No race here */
-        spin_lock_irqsave(&kretprobe_lock, flags);
-        hlist_for_each_entry_safe(ri, pos, next, &rp->used_instances, uflist) {
-                ri->rp = NULL;
-                hlist_del(&ri->uflist);
+        for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
+                kretprobe_table_lock(hash, &flags);
+                head = &kretprobe_inst_table[hash];
+                hlist_for_each_entry_safe(ri, pos, next, head, hlist) {
+                        if (ri->rp == rp)
+                                ri->rp = NULL;
+                }
+                kretprobe_table_unlock(hash, &flags);
         }
-        spin_unlock_irqrestore(&kretprobe_lock, flags);
         free_rp_inst(rp);
 }
 
@@ -831,32 +875,37 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
                                            struct pt_regs *regs)
 {
         struct kretprobe *rp = container_of(p, struct kretprobe, kp);
-        unsigned long flags = 0;
+        unsigned long hash, flags = 0;
+        struct kretprobe_instance *ri;
 
         /*TODO: consider to only swap the RA after the last pre_handler fired */
-        spin_lock_irqsave(&kretprobe_lock, flags);
+        hash = hash_ptr(current, KPROBE_HASH_BITS);
+        spin_lock_irqsave(&rp->lock, flags);
         if (!hlist_empty(&rp->free_instances)) {
-                struct kretprobe_instance *ri;
-
                 ri = hlist_entry(rp->free_instances.first,
-                                 struct kretprobe_instance, uflist);
+                                struct kretprobe_instance, hlist);
+                hlist_del(&ri->hlist);
+                spin_unlock_irqrestore(&rp->lock, flags);
+
                 ri->rp = rp;
                 ri->task = current;
 
                 if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-                        spin_unlock_irqrestore(&kretprobe_lock, flags);
+                        spin_unlock_irqrestore(&rp->lock, flags);
                         return 0;
                 }
 
                 arch_prepare_kretprobe(ri, regs);
 
                 /* XXX(hch): why is there no hlist_move_head? */
-                hlist_del(&ri->uflist);
-                hlist_add_head(&ri->uflist, &ri->rp->used_instances);
-                hlist_add_head(&ri->hlist, kretprobe_inst_table_head(ri->task));
-        } else
+                INIT_HLIST_NODE(&ri->hlist);
+                kretprobe_table_lock(hash, &flags);
+                hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
+                kretprobe_table_unlock(hash, &flags);
+        } else {
                 rp->nmissed++;
-        spin_unlock_irqrestore(&kretprobe_lock, flags);
+                spin_unlock_irqrestore(&rp->lock, flags);
+        }
         return 0;
 }
 
@@ -892,7 +941,7 @@ static int __kprobes __register_kretprobe(struct kretprobe *rp,
                 rp->maxactive = NR_CPUS;
 #endif
         }
-        INIT_HLIST_HEAD(&rp->used_instances);
+        spin_lock_init(&rp->lock);
         INIT_HLIST_HEAD(&rp->free_instances);
         for (i = 0; i < rp->maxactive; i++) {
                 inst = kmalloc(sizeof(struct kretprobe_instance) +
@@ -901,8 +950,8 @@ static int __kprobes __register_kretprobe(struct kretprobe *rp,
                         free_rp_inst(rp);
                         return -ENOMEM;
                 }
-                INIT_HLIST_NODE(&inst->uflist);
-                hlist_add_head(&inst->uflist, &rp->free_instances);
+                INIT_HLIST_NODE(&inst->hlist);
+                hlist_add_head(&inst->hlist, &rp->free_instances);
         }
 
         rp->nmissed = 0;
@@ -1009,6 +1058,7 @@ static int __init init_kprobes(void)
         for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
                 INIT_HLIST_HEAD(&kprobe_table[i]);
                 INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
+                spin_lock_init(&(kretprobe_table_locks[i].lock));
         }
 
         /*
@@ -1050,6 +1100,7 @@ static int __init init_kprobes(void)
         err = arch_init_kprobes();
         if (!err)
                 err = register_die_notifier(&kprobe_exceptions_nb);
+        kprobes_initialized = (err == 0);
 
         if (!err)
                 init_test_probes();
@@ -1286,13 +1337,8 @@ EXPORT_SYMBOL_GPL(register_jprobe);
 EXPORT_SYMBOL_GPL(unregister_jprobe);
 EXPORT_SYMBOL_GPL(register_jprobes);
 EXPORT_SYMBOL_GPL(unregister_jprobes);
-#ifdef CONFIG_KPROBES
 EXPORT_SYMBOL_GPL(jprobe_return);
-#endif
-
-#ifdef CONFIG_KPROBES
 EXPORT_SYMBOL_GPL(register_kretprobe);
 EXPORT_SYMBOL_GPL(unregister_kretprobe);
 EXPORT_SYMBOL_GPL(register_kretprobes);
 EXPORT_SYMBOL_GPL(unregister_kretprobes);
-#endif
diff --git a/kernel/kthread.c b/kernel/kthread.c
index ac3fb7326641..96cff2f8710b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -106,7 +106,7 @@ static void create_kthread(struct kthread_create_info *create)
                  */
                 sched_setscheduler(create->result, SCHED_NORMAL, &param);
                 set_user_nice(create->result, KTHREAD_NICE_LEVEL);
-                set_cpus_allowed(create->result, CPU_MASK_ALL);
+                set_cpus_allowed_ptr(create->result, CPU_MASK_ALL_PTR);
         }
         complete(&create->done);
 }
@@ -176,7 +176,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
                 return;
         }
         /* Must have done schedule() in kthread() before we set_task_cpu */
-        wait_task_inactive(k);
+        wait_task_inactive(k, 0);
         set_task_cpu(k, cpu);
         k->cpus_allowed = cpumask_of_cpu(cpu);
         k->rt.nr_cpus_allowed = 1;
@@ -233,7 +233,7 @@ int kthreadd(void *unused)
         set_task_comm(tsk, "kthreadd");
         ignore_signals(tsk);
         set_user_nice(tsk, KTHREAD_NICE_LEVEL);
-        set_cpus_allowed(tsk, CPU_MASK_ALL);
+        set_cpus_allowed_ptr(tsk, CPU_MASK_ALL_PTR);
 
         current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index d38a64362973..dbda475b13bd 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -124,6 +124,15 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
 unsigned long nr_lock_classes;
 static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
+static inline struct lock_class *hlock_class(struct held_lock *hlock)
+{
+        if (!hlock->class_idx) {
+                DEBUG_LOCKS_WARN_ON(1);
+                return NULL;
+        }
+        return lock_classes + hlock->class_idx - 1;
+}
+
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
@@ -222,7 +231,7 @@ static void lock_release_holdtime(struct held_lock *hlock)
 
         holdtime = sched_clock() - hlock->holdtime_stamp;
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (hlock->read)
                 lock_time_inc(&stats->read_holdtime, holdtime);
         else
@@ -372,6 +381,19 @@ unsigned int nr_process_chains;
 unsigned int max_lockdep_depth;
 unsigned int max_recursion_depth;
 
+static unsigned int lockdep_dependency_gen_id;
+
+static bool lockdep_dependency_visit(struct lock_class *source,
+                                     unsigned int depth)
+{
+        if (!depth)
+                lockdep_dependency_gen_id++;
+        if (source->dep_gen_id == lockdep_dependency_gen_id)
+                return true;
+        source->dep_gen_id = lockdep_dependency_gen_id;
+        return false;
+}
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
  * We cannot printk in early bootup code. Not even early_printk()
@@ -505,7 +527,7 @@ static void print_lockdep_cache(struct lockdep_map *lock)
 
 static void print_lock(struct held_lock *hlock)
 {
-        print_lock_name(hlock->class);
+        print_lock_name(hlock_class(hlock));
         printk(", at: ");
         print_ip_sym(hlock->acquire_ip);
 }
@@ -558,6 +580,9 @@ static void print_lock_dependencies(struct lock_class *class, int depth)
 {
         struct lock_list *entry;
 
+        if (lockdep_dependency_visit(class, depth))
+                return;
+
         if (DEBUG_LOCKS_WARN_ON(depth >= 20))
                 return;
 
@@ -850,11 +875,11 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
         if (!entry)
                 return 0;
 
-        entry->class = this;
-        entry->distance = distance;
         if (!save_trace(&entry->trace))
                 return 0;
 
+        entry->class = this;
+        entry->distance = distance;
         /*
          * Since we never remove from the dependency list, the list can
          * be walked lockless by other CPUs, it's only allocation
@@ -932,7 +957,7 @@ static noinline int print_circular_bug_tail(void)
         if (debug_locks_silent)
                 return 0;
 
-        this.class = check_source->class;
+        this.class = hlock_class(check_source);
         if (!save_trace(&this.trace))
                 return 0;
 
@@ -959,6 +984,67 @@ static int noinline print_infinite_recursion_bug(void)
         return 0;
 }
 
+unsigned long __lockdep_count_forward_deps(struct lock_class *class,
+                                           unsigned int depth)
+{
+        struct lock_list *entry;
+        unsigned long ret = 1;
+
+        if (lockdep_dependency_visit(class, depth))
+                return 0;
+
+        /*
+         * Recurse this class's dependency list:
+         */
+        list_for_each_entry(entry, &class->locks_after, entry)
+                ret += __lockdep_count_forward_deps(entry->class, depth + 1);
+
+        return ret;
+}
+
+unsigned long lockdep_count_forward_deps(struct lock_class *class)
+{
+        unsigned long ret, flags;
+
+        local_irq_save(flags);
+        __raw_spin_lock(&lockdep_lock);
+        ret = __lockdep_count_forward_deps(class, 0);
+        __raw_spin_unlock(&lockdep_lock);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
+unsigned long __lockdep_count_backward_deps(struct lock_class *class,
+                                            unsigned int depth)
+{
+        struct lock_list *entry;
+        unsigned long ret = 1;
+
+        if (lockdep_dependency_visit(class, depth))
+                return 0;
+        /*
+         * Recurse this class's dependency list:
+         */
+        list_for_each_entry(entry, &class->locks_before, entry)
+                ret += __lockdep_count_backward_deps(entry->class, depth + 1);
+
+        return ret;
+}
+
+unsigned long lockdep_count_backward_deps(struct lock_class *class)
+{
+        unsigned long ret, flags;
+
+        local_irq_save(flags);
+        __raw_spin_lock(&lockdep_lock);
+        ret = __lockdep_count_backward_deps(class, 0);
+        __raw_spin_unlock(&lockdep_lock);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
 /*
  * Prove that the dependency graph starting at <entry> can not
  * lead to <target>. Print an error and return 0 if it does.
@@ -968,6 +1054,9 @@ check_noncircular(struct lock_class *source, unsigned int depth)
 {
         struct lock_list *entry;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         debug_atomic_inc(&nr_cyclic_check_recursions);
         if (depth > max_recursion_depth)
                 max_recursion_depth = depth;
@@ -977,7 +1066,7 @@ check_noncircular(struct lock_class *source, unsigned int depth)
          * Check this lock's dependency list:
          */
         list_for_each_entry(entry, &source->locks_after, entry) {
-                if (entry->class == check_target->class)
+                if (entry->class == hlock_class(check_target))
                         return print_circular_bug_header(entry, depth+1);
                 debug_atomic_inc(&nr_cyclic_checks);
                 if (!check_noncircular(entry->class, depth+1))
@@ -1011,6 +1100,9 @@ find_usage_forwards(struct lock_class *source, unsigned int depth)
         struct lock_list *entry;
         int ret;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         if (depth > max_recursion_depth)
                 max_recursion_depth = depth;
         if (depth >= RECURSION_LIMIT)
@@ -1050,6 +1142,9 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
         struct lock_list *entry;
         int ret;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         if (!__raw_spin_is_locked(&lockdep_lock))
                 return DEBUG_LOCKS_WARN_ON(1);
 
@@ -1064,6 +1159,11 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
                 return 2;
         }
 
+        if (!source && debug_locks_off_graph_unlock()) {
+                WARN_ON(1);
+                return 0;
+        }
+
         /*
          * Check this lock's dependency list:
          */
@@ -1103,9 +1203,9 @@ print_bad_irq_dependency(struct task_struct *curr,
         printk("\nand this task is already holding:\n");
         print_lock(prev);
         printk("which would create a new lock dependency:\n");
-        print_lock_name(prev->class);
+        print_lock_name(hlock_class(prev));
         printk(" ->");
-        print_lock_name(next->class);
+        print_lock_name(hlock_class(next));
         printk("\n");
 
         printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
@@ -1146,12 +1246,12 @@ check_usage(struct task_struct *curr, struct held_lock *prev,
 
         find_usage_bit = bit_backwards;
         /* fills in <backwards_match> */
-        ret = find_usage_backwards(prev->class, 0);
+        ret = find_usage_backwards(hlock_class(prev), 0);
         if (!ret || ret == 1)
                 return ret;
 
         find_usage_bit = bit_forwards;
-        ret = find_usage_forwards(next->class, 0);
+        ret = find_usage_forwards(hlock_class(next), 0);
         if (!ret || ret == 1)
                 return ret;
         /* ret == 2 */
@@ -1272,18 +1372,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
                struct lockdep_map *next_instance, int read)
 {
         struct held_lock *prev;
+        struct held_lock *nest = NULL;
         int i;
 
         for (i = 0; i < curr->lockdep_depth; i++) {
                 prev = curr->held_locks + i;
-                if (prev->class != next->class)
+
+                if (prev->instance == next->nest_lock)
+                        nest = prev;
+
+                if (hlock_class(prev) != hlock_class(next))
                         continue;
+
                 /*
                  * Allow read-after-read recursion of the same
                  * lock class (i.e. read_lock(lock)+read_lock(lock)):
                  */
                 if ((read == 2) && prev->read)
                         return 2;
+
+                /*
+                 * We're holding the nest_lock, which serializes this lock's
+                 * nesting behaviour.
+                 */
+                if (nest)
+                        return 2;
+
                 return print_deadlock_bug(curr, prev, next);
         }
         return 1;
@@ -1329,7 +1443,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          */
         check_source = next;
         check_target = prev;
-        if (!(check_noncircular(next->class, 0)))
+        if (!(check_noncircular(hlock_class(next), 0)))
                 return print_circular_bug_tail();
 
         if (!check_prev_add_irq(curr, prev, next))
@@ -1353,8 +1467,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          *  chains - the second one will be new, but L1 already has
          *  L2 added to its dependency list, due to the first chain.)
          */
-        list_for_each_entry(entry, &prev->class->locks_after, entry) {
-                if (entry->class == next->class) {
+        list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) {
+                if (entry->class == hlock_class(next)) {
                         if (distance == 1)
                                 entry->distance = 1;
                         return 2;
@@ -1365,26 +1479,28 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          * Ok, all validations passed, add the new lock
          * to the previous lock's dependency list:
          */
-        ret = add_lock_to_list(prev->class, next->class,
-                               &prev->class->locks_after, next->acquire_ip, distance);
+        ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
+                               &hlock_class(prev)->locks_after,
+                               next->acquire_ip, distance);
 
         if (!ret)
                 return 0;
 
-        ret = add_lock_to_list(next->class, prev->class,
-                               &next->class->locks_before, next->acquire_ip, distance);
+        ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
+                               &hlock_class(next)->locks_before,
+                               next->acquire_ip, distance);
         if (!ret)
                 return 0;
 
         /*
          * Debugging printouts:
          */
-        if (verbose(prev->class) || verbose(next->class)) {
+        if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
                 graph_unlock();
                 printk("\n new dependency: ");
-                print_lock_name(prev->class);
+                print_lock_name(hlock_class(prev));
                 printk(" => ");
-                print_lock_name(next->class);
+                print_lock_name(hlock_class(next));
                 printk("\n");
                 dump_stack();
                 return graph_lock();
@@ -1481,7 +1597,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
                                      struct held_lock *hlock,
                                      u64 chain_key)
 {
-        struct lock_class *class = hlock->class;
+        struct lock_class *class = hlock_class(hlock);
         struct list_head *hash_head = chainhashentry(chain_key);
         struct lock_chain *chain;
         struct held_lock *hlock_curr, *hlock_next;
@@ -1554,7 +1670,7 @@ cache_hit:
         if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
                 chain->base = cn;
                 for (j = 0; j < chain->depth - 1; j++, i++) {
-                        int lock_id = curr->held_locks[i].class - lock_classes;
+                        int lock_id = curr->held_locks[i].class_idx - 1;
                         chain_hlocks[chain->base + j] = lock_id;
                 }
                 chain_hlocks[chain->base + j] = class - lock_classes;
@@ -1643,14 +1759,13 @@ static void check_chain_key(struct task_struct *curr)
                 hlock = curr->held_locks + i;
                 if (chain_key != hlock->prev_chain_key) {
                         debug_locks_off();
-                        printk("hm#1, depth: %u [%u], %016Lx != %016Lx\n",
+                        WARN(1, "hm#1, depth: %u [%u], %016Lx != %016Lx\n",
                                 curr->lockdep_depth, i,
                                 (unsigned long long)chain_key,
                                 (unsigned long long)hlock->prev_chain_key);
-                        WARN_ON(1);
                         return;
                 }
-                id = hlock->class - lock_classes;
+                id = hlock->class_idx - 1;
                 if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
                         return;
 
@@ -1662,11 +1777,10 @@ static void check_chain_key(struct task_struct *curr)
         }
         if (chain_key != curr->curr_chain_key) {
                 debug_locks_off();
-                printk("hm#2, depth: %u [%u], %016Lx != %016Lx\n",
+                WARN(1, "hm#2, depth: %u [%u], %016Lx != %016Lx\n",
                         curr->lockdep_depth, i,
                         (unsigned long long)chain_key,
                         (unsigned long long)curr->curr_chain_key);
-                WARN_ON(1);
         }
 #endif
 }
@@ -1695,7 +1809,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
         print_lock(this);
 
         printk("{%s} state was registered at:\n", usage_str[prev_bit]);
-        print_stack_trace(this->class->usage_traces + prev_bit, 1);
+        print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
 
         print_irqtrace_events(curr);
         printk("\nother info that might help us debug this:\n");
@@ -1714,7 +1828,7 @@ static inline int
 valid_state(struct task_struct *curr, struct held_lock *this,
             enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
 {
-        if (unlikely(this->class->usage_mask & (1 << bad_bit)))
+        if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit)))
                 return print_usage_bug(curr, this, bad_bit, new_bit);
         return 1;
 }
@@ -1753,7 +1867,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
         lockdep_print_held_locks(curr);
 
         printk("\nthe first lock's dependencies:\n");
-        print_lock_dependencies(this->class, 0);
+        print_lock_dependencies(hlock_class(this), 0);
 
         printk("\nthe second lock's dependencies:\n");
         print_lock_dependencies(other, 0);
@@ -1776,7 +1890,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 
         find_usage_bit = bit;
         /* fills in <forwards_match> */
-        ret = find_usage_forwards(this->class, 0);
+        ret = find_usage_forwards(hlock_class(this), 0);
         if (!ret || ret == 1)
                 return ret;
 
@@ -1795,7 +1909,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
         find_usage_bit = bit;
         /* fills in <backwards_match> */
-        ret = find_usage_backwards(this->class, 0);
+        ret = find_usage_backwards(hlock_class(this), 0);
         if (!ret || ret == 1)
                 return ret;
 
@@ -1861,7 +1975,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                 LOCK_ENABLED_HARDIRQS_READ, "hard-read"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_SOFTIRQ:
@@ -1886,7 +2000,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                 LOCK_ENABLED_SOFTIRQS_READ, "soft-read"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_HARDIRQ_READ:
@@ -1899,7 +2013,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                 if (!check_usage_forwards(curr, this,
                                           LOCK_ENABLED_HARDIRQS, "hard"))
                         return 0;
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_SOFTIRQ_READ:
@@ -1912,7 +2026,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                 if (!check_usage_forwards(curr, this,
                                           LOCK_ENABLED_SOFTIRQS, "soft"))
                         return 0;
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_HARDIRQS:
@@ -1938,7 +2052,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                    LOCK_USED_IN_HARDIRQ_READ, "hard-read"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_SOFTIRQS:
@@ -1964,7 +2078,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                    LOCK_USED_IN_SOFTIRQ_READ, "soft-read"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_HARDIRQS_READ:
@@ -1979,7 +2093,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                            LOCK_USED_IN_HARDIRQ, "hard"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_SOFTIRQS_READ:
@@ -1994,7 +2108,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                            LOCK_USED_IN_SOFTIRQ, "soft"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         default:
@@ -2310,7 +2424,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
          * If already set then do not dirty the cacheline,
          * nor do any checks:
          */
-        if (likely(this->class->usage_mask & new_mask))
+        if (likely(hlock_class(this)->usage_mask & new_mask))
                 return 1;
 
         if (!graph_lock())
@@ -2318,14 +2432,14 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
         /*
          * Make sure we didnt race:
          */
-        if (unlikely(this->class->usage_mask & new_mask)) {
+        if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
                 graph_unlock();
                 return 1;
         }
 
-        this->class->usage_mask |= new_mask;
+        hlock_class(this)->usage_mask |= new_mask;
 
-        if (!save_trace(this->class->usage_traces + new_bit))
+        if (!save_trace(hlock_class(this)->usage_traces + new_bit))
                 return 0;
 
         switch (new_bit) {
@@ -2405,7 +2519,7 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
  */
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
                           int trylock, int read, int check, int hardirqs_off,
-                          unsigned long ip)
+                          struct lockdep_map *nest_lock, unsigned long ip)
 {
         struct task_struct *curr = current;
         struct lock_class *class = NULL;
@@ -2459,14 +2573,16 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
                 return 0;
 
         hlock = curr->held_locks + depth;
-
-        hlock->class = class;
+        if (DEBUG_LOCKS_WARN_ON(!class))
+                return 0;
+        hlock->class_idx = class - lock_classes + 1;
         hlock->acquire_ip = ip;
         hlock->instance = lock;
+        hlock->nest_lock = nest_lock;
         hlock->trylock = trylock;
         hlock->read = read;
         hlock->check = check;
-        hlock->hardirqs_off = hardirqs_off;
+        hlock->hardirqs_off = !!hardirqs_off;
 #ifdef CONFIG_LOCK_STAT
         hlock->waittime_stamp = 0;
         hlock->holdtime_stamp = sched_clock();
@@ -2574,6 +2690,55 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
         return 1;
 }
 
+static int
+__lock_set_subclass(struct lockdep_map *lock,
+                    unsigned int subclass, unsigned long ip)
+{
+        struct task_struct *curr = current;
+        struct held_lock *hlock, *prev_hlock;
+        struct lock_class *class;
+        unsigned int depth;
+        int i;
+
+        depth = curr->lockdep_depth;
+        if (DEBUG_LOCKS_WARN_ON(!depth))
+                return 0;
+
+        prev_hlock = NULL;
+        for (i = depth-1; i >= 0; i--) {
+                hlock = curr->held_locks + i;
+                /*
+                 * We must not cross into another context:
+                 */
+                if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
+                        break;
+                if (hlock->instance == lock)
+                        goto found_it;
+                prev_hlock = hlock;
+        }
+        return print_unlock_inbalance_bug(curr, lock, ip);
+
+found_it:
+        class = register_lock_class(lock, subclass, 0);
+        hlock->class_idx = class - lock_classes + 1;
+
+        curr->lockdep_depth = i;
+        curr->curr_chain_key = hlock->prev_chain_key;
+
+        for (; i < depth; i++) {
+                hlock = curr->held_locks + i;
+                if (!__lock_acquire(hlock->instance,
+                        hlock_class(hlock)->subclass, hlock->trylock,
+                                hlock->read, hlock->check, hlock->hardirqs_off,
+                                hlock->nest_lock, hlock->acquire_ip))
+                        return 0;
+        }
+
+        if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+                return 0;
+        return 1;
+}
+
 /*
  * Remove the lock to the list of currently held locks in a
  * potentially non-nested (out of order) manner. This is a
@@ -2624,9 +2789,9 @@ found_it:
         for (i++; i < depth; i++) {
                 hlock = curr->held_locks + i;
                 if (!__lock_acquire(hlock->instance,
-                        hlock->class->subclass, hlock->trylock,
+                        hlock_class(hlock)->subclass, hlock->trylock,
                                 hlock->read, hlock->check, hlock->hardirqs_off,
-                                hlock->acquire_ip))
+                                hlock->nest_lock, hlock->acquire_ip))
                         return 0;
         }
 
@@ -2669,7 +2834,7 @@ static int lock_release_nested(struct task_struct *curr,
 
 #ifdef CONFIG_DEBUG_LOCKDEP
         hlock->prev_chain_key = 0;
-        hlock->class = NULL;
+        hlock->class_idx = 0;
         hlock->acquire_ip = 0;
         hlock->irq_context = 0;
 #endif
@@ -2738,18 +2903,36 @@ static void check_flags(unsigned long flags)
 #endif
 }
 
+void
+lock_set_subclass(struct lockdep_map *lock,
+                  unsigned int subclass, unsigned long ip)
+{
+        unsigned long flags;
+
+        if (unlikely(current->lockdep_recursion))
+                return;
+
+        raw_local_irq_save(flags);
+        current->lockdep_recursion = 1;
+        check_flags(flags);
+        if (__lock_set_subclass(lock, subclass, ip))
+                check_chain_key(current);
+        current->lockdep_recursion = 0;
+        raw_local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL_GPL(lock_set_subclass);
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
  */
 void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
-                          int trylock, int read, int check, unsigned long ip)
+                          int trylock, int read, int check,
+                          struct lockdep_map *nest_lock, unsigned long ip)
 {
         unsigned long flags;
 
-        if (unlikely(!lock_stat && !prove_locking))
-                return;
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -2758,7 +2941,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
         current->lockdep_recursion = 1;
         __lock_acquire(lock, subclass, trylock, read, check,
-                       irqs_disabled_flags(flags), ip);
+                       irqs_disabled_flags(flags), nest_lock, ip);
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
 }
@@ -2770,9 +2953,6 @@ void lock_release(struct lockdep_map *lock, int nested,
 {
         unsigned long flags;
 
-        if (unlikely(!lock_stat && !prove_locking))
-                return;
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -2845,11 +3025,11 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
         hlock->waittime_stamp = sched_clock();
 
-        point = lock_contention_point(hlock->class, ip);
+        point = lock_contention_point(hlock_class(hlock), ip);
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (point < ARRAY_SIZE(stats->contention_point))
-                stats->contention_point[i]++;
+                stats->contention_point[point]++;
         if (lock->cpu != smp_processor_id())
                 stats->bounces[bounce_contended + !!hlock->read]++;
         put_lock_stats(stats);
@@ -2893,7 +3073,7 @@ found_it:
                 hlock->holdtime_stamp = now;
         }
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (waittime) {
                 if (hlock->read)
                         lock_time_inc(&stats->read_waittime, waittime);
@@ -2988,6 +3168,7 @@ static void zap_class(struct lock_class *class)
         list_del_rcu(&class->hash_entry);
         list_del_rcu(&class->lock_entry);
 
+        class->key = NULL;
 }
 
 static inline int within(const void *addr, void *start, unsigned long size)
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index c3600a091a28..56b196932c08 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -17,9 +17,6 @@
  */
 #define MAX_LOCKDEP_ENTRIES     8192UL
 
-#define MAX_LOCKDEP_KEYS_BITS   11
-#define MAX_LOCKDEP_KEYS        (1UL << MAX_LOCKDEP_KEYS_BITS)
-
 #define MAX_LOCKDEP_CHAINS_BITS 14
 #define MAX_LOCKDEP_CHAINS      (1UL << MAX_LOCKDEP_CHAINS_BITS)
 
@@ -53,6 +50,22 @@ extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
 extern unsigned int max_recursion_depth;
 
+#ifdef CONFIG_PROVE_LOCKING
+extern unsigned long lockdep_count_forward_deps(struct lock_class *);
+extern unsigned long lockdep_count_backward_deps(struct lock_class *);
+#else
+static inline unsigned long
+lockdep_count_forward_deps(struct lock_class *class)
+{
+        return 0;
+}
+static inline unsigned long
+lockdep_count_backward_deps(struct lock_class *class)
+{
+        return 0;
+}
+#endif
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
  * Various lockdep statistics:
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 9b0e940e2545..20dbcbf9c7dd 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -63,34 +63,6 @@ static void l_stop(struct seq_file *m, void *v)
 {
 }
 
-static unsigned long count_forward_deps(struct lock_class *class)
-{
-        struct lock_list *entry;
-        unsigned long ret = 1;
-
-        /*
-         * Recurse this class's dependency list:
-         */
-        list_for_each_entry(entry, &class->locks_after, entry)
-                ret += count_forward_deps(entry->class);
-
-        return ret;
-}
-
-static unsigned long count_backward_deps(struct lock_class *class)
-{
-        struct lock_list *entry;
-        unsigned long ret = 1;
-
-        /*
-         * Recurse this class's dependency list:
-         */
-        list_for_each_entry(entry, &class->locks_before, entry)
-                ret += count_backward_deps(entry->class);
-
-        return ret;
-}
-
 static void print_name(struct seq_file *m, struct lock_class *class)
 {
         char str[128];
@@ -110,7 +82,6 @@ static void print_name(struct seq_file *m, struct lock_class *class)
 
 static int l_show(struct seq_file *m, void *v)
 {
-        unsigned long nr_forward_deps, nr_backward_deps;
         struct lock_class *class = v;
         struct lock_list *entry;
         char c1, c2, c3, c4;
@@ -124,11 +95,10 @@ static int l_show(struct seq_file *m, void *v)
 #ifdef CONFIG_DEBUG_LOCKDEP
         seq_printf(m, " OPS:%8ld", class->ops);
 #endif
-        nr_forward_deps = count_forward_deps(class);
-        seq_printf(m, " FD:%5ld", nr_forward_deps);
-
-        nr_backward_deps = count_backward_deps(class);
-        seq_printf(m, " BD:%5ld", nr_backward_deps);
+#ifdef CONFIG_PROVE_LOCKING
+        seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class));
+        seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class));
+#endif
 
         get_usage_chars(class, &c1, &c2, &c3, &c4);
         seq_printf(m, " %c%c%c%c", c1, c2, c3, c4);
@@ -229,6 +199,9 @@ static int lc_show(struct seq_file *m, void *v)
 
         for (i = 0; i < chain->depth; i++) {
                 class = lock_chain_get_class(chain, i);
+                if (!class->key)
+                        continue;
+
                 seq_printf(m, "[%p] ", class->key);
                 print_name(m, class);
                 seq_puts(m, "\n");
@@ -350,7 +323,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
                 if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
                         nr_hardirq_read_unsafe++;
 
-                sum_forward_deps += count_forward_deps(class);
+#ifdef CONFIG_PROVE_LOCKING
+                sum_forward_deps += lockdep_count_forward_deps(class);
+#endif
         }
 #ifdef CONFIG_DEBUG_LOCKDEP
         DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
@@ -497,8 +472,9 @@ static void snprint_time(char *buf, size_t bufsiz, s64 nr)
 {
         unsigned long rem;
 
+        nr += 5; /* for display rounding */
         rem = do_div(nr, 1000); /* XXX: do_div_signed */
-        snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, ((int)rem+5)/10);
+        snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
 }
 
 static void seq_time(struct seq_file *m, s64 time)
diff --git a/kernel/marker.c b/kernel/marker.c
index 1abfb923b761..7d1faecd7a51 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -126,6 +126,11 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
                 struct marker_probe_closure *multi;
                 int i;
                 /*
+                 * Read mdata->ptype before mdata->multi.
+                 */
+                smp_rmb();
+                multi = mdata->multi;
+                /*
                  * multi points to an array, therefore accessing the array
                  * depends on reading multi. However, even in this case,
                  * we must insure that the pointer is read _before_ the array
@@ -133,7 +138,6 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
                  * in the fast path, so put the explicit barrier here.
                  */
                 smp_read_barrier_depends();
-                multi = mdata->multi;
                 for (i = 0; multi[i].func; i++) {
                         va_start(args, call_private);
                         multi[i].func(multi[i].probe_private, call_private,
@@ -175,6 +179,11 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
                 struct marker_probe_closure *multi;
                 int i;
                 /*
+                 * Read mdata->ptype before mdata->multi.
+                 */
+                smp_rmb();
+                multi = mdata->multi;
+                /*
                  * multi points to an array, therefore accessing the array
                  * depends on reading multi. However, even in this case,
                  * we must insure that the pointer is read _before_ the array
@@ -182,7 +191,6 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
                  * in the fast path, so put the explicit barrier here.
                  */
                 smp_read_barrier_depends();
-                multi = mdata->multi;
                 for (i = 0; multi[i].func; i++)
                         multi[i].func(multi[i].probe_private, call_private,
                                 mdata->format, &args);
@@ -441,7 +449,7 @@ static int remove_marker(const char *name)
         hlist_del(&e->hlist);
         /* Make sure the call_rcu has been executed */
         if (e->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         kfree(e);
         return 0;
 }
@@ -476,7 +484,7 @@ static int marker_set_format(struct marker_entry **entry, const char *format)
         hlist_del(&(*entry)->hlist);
         /* Make sure the call_rcu has been executed */
         if ((*entry)->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         kfree(*entry);
         *entry = e;
         trace_mark(core_marker_format, "name %s format %s",
@@ -655,7 +663,7 @@ int marker_probe_register(const char *name, const char *format,
          * make sure it's executed now.
          */
         if (entry->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         old = marker_entry_add_probe(entry, probe, probe_private);
         if (IS_ERR(old)) {
                 ret = PTR_ERR(old);
@@ -670,10 +678,7 @@ 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);
+        call_rcu_sched(&entry->rcu, free_old_closure);
 end:
         mutex_unlock(&markers_mutex);
         return ret;
@@ -704,7 +709,7 @@ int marker_probe_unregister(const char *name,
         if (!entry)
                 goto end;
         if (entry->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         old = marker_entry_remove_probe(entry, probe, probe_private);
         mutex_unlock(&markers_mutex);
         marker_update_probes();         /* may update entry */
@@ -716,10 +721,7 @@ 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);
+        call_rcu_sched(&entry->rcu, free_old_closure);
         remove_marker(name);    /* Ignore busy error message */
         ret = 0;
 end:
@@ -786,7 +788,7 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
                 goto end;
         }
         if (entry->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         old = marker_entry_remove_probe(entry, NULL, probe_private);
         mutex_unlock(&markers_mutex);
         marker_update_probes();         /* may update entry */
@@ -797,10 +799,7 @@ 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);
+        call_rcu_sched(&entry->rcu, free_old_closure);
         remove_marker(entry->name);     /* Ignore busy error message */
 end:
         mutex_unlock(&markers_mutex);
diff --git a/kernel/module.c b/kernel/module.c
index 5f80478b746d..9db11911e04b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -70,6 +70,9 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
 static BLOCKING_NOTIFIER_HEAD(module_notify_list);
 
+/* Bounds of module allocation, for speeding __module_text_address */
+static unsigned long module_addr_min = -1UL, module_addr_max = 0;
+
 int register_module_notifier(struct notifier_block * nb)
 {
         return blocking_notifier_chain_register(&module_notify_list, nb);
@@ -134,17 +137,19 @@ extern const struct kernel_symbol __start___ksymtab_gpl[];
 extern const struct kernel_symbol __stop___ksymtab_gpl[];
 extern const struct kernel_symbol __start___ksymtab_gpl_future[];
 extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
-extern const struct kernel_symbol __start___ksymtab_unused[];
-extern const struct kernel_symbol __stop___ksymtab_unused[];
-extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
-extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
 extern const struct kernel_symbol __start___ksymtab_gpl_future[];
 extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
 extern const unsigned long __start___kcrctab[];
 extern const unsigned long __start___kcrctab_gpl[];
 extern const unsigned long __start___kcrctab_gpl_future[];
+#ifdef CONFIG_UNUSED_SYMBOLS
+extern const struct kernel_symbol __start___ksymtab_unused[];
+extern const struct kernel_symbol __stop___ksymtab_unused[];
+extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
+extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
 extern const unsigned long __start___kcrctab_unused[];
 extern const unsigned long __start___kcrctab_unused_gpl[];
+#endif
 
 #ifndef CONFIG_MODVERSIONS
 #define symversion(base, idx) NULL
@@ -152,152 +157,170 @@ extern const unsigned long __start___kcrctab_unused_gpl[];
 #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL)
 #endif
 
-/* lookup symbol in given range of kernel_symbols */
-static const struct kernel_symbol *lookup_symbol(const char *name,
-        const struct kernel_symbol *start,
-        const struct kernel_symbol *stop)
-{
-        const struct kernel_symbol *ks = start;
-        for (; ks < stop; ks++)
-                if (strcmp(ks->name, name) == 0)
-                        return ks;
-        return NULL;
-}
-
-static bool always_ok(bool gplok, bool warn, const char *name)
-{
-        return true;
-}
-
-static bool printk_unused_warning(bool gplok, bool warn, const char *name)
-{
-        if (warn) {
-                printk(KERN_WARNING "Symbol %s is marked as UNUSED, "
-                       "however this module is using it.\n", name);
-                printk(KERN_WARNING
-                       "This symbol will go away in the future.\n");
-                printk(KERN_WARNING
-                       "Please evalute if this is the right api to use and if "
-                       "it really is, submit a report the linux kernel "
-                       "mailinglist together with submitting your code for "
-                       "inclusion.\n");
-        }
-        return true;
-}
-
-static bool gpl_only_unused_warning(bool gplok, bool warn, const char *name)
-{
-        if (!gplok)
-                return false;
-        return printk_unused_warning(gplok, warn, name);
-}
-
-static bool gpl_only(bool gplok, bool warn, const char *name)
-{
-        return gplok;
-}
-
-static bool warn_if_not_gpl(bool gplok, bool warn, const char *name)
-{
-        if (!gplok && warn) {
-                printk(KERN_WARNING "Symbol %s is being used "
-                       "by a non-GPL module, which will not "
-                       "be allowed in the future\n", name);
-                printk(KERN_WARNING "Please see the file "
-                       "Documentation/feature-removal-schedule.txt "
-                       "in the kernel source tree for more details.\n");
-        }
-        return true;
-}
-
 struct symsearch {
         const struct kernel_symbol *start, *stop;
         const unsigned long *crcs;
-        bool (*check)(bool gplok, bool warn, const char *name);
+        enum {
+                NOT_GPL_ONLY,
+                GPL_ONLY,
+                WILL_BE_GPL_ONLY,
+        } licence;
+        bool unused;
 };
 
-/* Look through this array of symbol tables for a symbol match which
- * passes the check function. */
-static const struct kernel_symbol *search_symarrays(const struct symsearch *arr,
-                                                    unsigned int num,
-                                                    const char *name,
-                                                    bool gplok,
-                                                    bool warn,
-                                                    const unsigned long **crc)
+static bool each_symbol_in_section(const struct symsearch *arr,
+                                   unsigned int arrsize,
+                                   struct module *owner,
+                                   bool (*fn)(const struct symsearch *syms,
+                                              struct module *owner,
+                                              unsigned int symnum, void *data),
+                                   void *data)
 {
-        unsigned int i;
-        const struct kernel_symbol *ks;
-
-        for (i = 0; i < num; i++) {
-                ks = lookup_symbol(name, arr[i].start, arr[i].stop);
-                if (!ks || !arr[i].check(gplok, warn, name))
-                        continue;
+        unsigned int i, j;
 
-                if (crc)
-                        *crc = symversion(arr[i].crcs, ks - arr[i].start);
-                return ks;
+        for (j = 0; j < arrsize; j++) {
+                for (i = 0; i < arr[j].stop - arr[j].start; i++)
+                        if (fn(&arr[j], owner, i, data))
+                                return true;
         }
-        return NULL;
+
+        return false;
 }
 
-/* Find a symbol, return value, (optional) crc and (optional) module
- * which owns it */
-static unsigned long find_symbol(const char *name,
-                                 struct module **owner,
-                                 const unsigned long **crc,
-                                 bool gplok,
-                                 bool warn)
+/* Returns true as soon as fn returns true, otherwise false. */
+static bool each_symbol(bool (*fn)(const struct symsearch *arr,
+                                   struct module *owner,
+                                   unsigned int symnum, void *data),
+                        void *data)
 {
         struct module *mod;
-        const struct kernel_symbol *ks;
         const struct symsearch arr[] = {
                 { __start___ksymtab, __stop___ksymtab, __start___kcrctab,
-                  always_ok },
+                  NOT_GPL_ONLY, false },
                 { __start___ksymtab_gpl, __stop___ksymtab_gpl,
-                  __start___kcrctab_gpl, gpl_only },
+                  __start___kcrctab_gpl,
+                  GPL_ONLY, false },
                 { __start___ksymtab_gpl_future, __stop___ksymtab_gpl_future,
-                  __start___kcrctab_gpl_future, warn_if_not_gpl },
+                  __start___kcrctab_gpl_future,
+                  WILL_BE_GPL_ONLY, false },
+#ifdef CONFIG_UNUSED_SYMBOLS
                 { __start___ksymtab_unused, __stop___ksymtab_unused,
-                  __start___kcrctab_unused, printk_unused_warning },
+                  __start___kcrctab_unused,
+                  NOT_GPL_ONLY, true },
                 { __start___ksymtab_unused_gpl, __stop___ksymtab_unused_gpl,
-                  __start___kcrctab_unused_gpl, gpl_only_unused_warning },
+                  __start___kcrctab_unused_gpl,
+                  GPL_ONLY, true },
+#endif
         };
 
-        /* Core kernel first. */
-        ks = search_symarrays(arr, ARRAY_SIZE(arr), name, gplok, warn, crc);
-        if (ks) {
-                if (owner)
-                        *owner = NULL;
-                return ks->value;
-        }
+        if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
+                return true;
 
-        /* Now try modules. */
         list_for_each_entry(mod, &modules, list) {
                 struct symsearch arr[] = {
                         { mod->syms, mod->syms + mod->num_syms, mod->crcs,
-                          always_ok },
+                          NOT_GPL_ONLY, false },
                         { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms,
-                          mod->gpl_crcs, gpl_only },
+                          mod->gpl_crcs,
+                          GPL_ONLY, false },
                         { mod->gpl_future_syms,
                           mod->gpl_future_syms + mod->num_gpl_future_syms,
-                          mod->gpl_future_crcs, warn_if_not_gpl },
+                          mod->gpl_future_crcs,
+                          WILL_BE_GPL_ONLY, false },
+#ifdef CONFIG_UNUSED_SYMBOLS
                         { mod->unused_syms,
                           mod->unused_syms + mod->num_unused_syms,
-                          mod->unused_crcs, printk_unused_warning },
+                          mod->unused_crcs,
+                          NOT_GPL_ONLY, true },
                         { mod->unused_gpl_syms,
                           mod->unused_gpl_syms + mod->num_unused_gpl_syms,
-                          mod->unused_gpl_crcs, gpl_only_unused_warning },
+                          mod->unused_gpl_crcs,
+                          GPL_ONLY, true },
+#endif
                 };
 
-                ks = search_symarrays(arr, ARRAY_SIZE(arr),
-                                      name, gplok, warn, crc);
-                if (ks) {
-                        if (owner)
-                                *owner = mod;
-                        return ks->value;
+                if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data))
+                        return true;
+        }
+        return false;
+}
+
+struct find_symbol_arg {
+        /* Input */
+        const char *name;
+        bool gplok;
+        bool warn;
+
+        /* Output */
+        struct module *owner;
+        const unsigned long *crc;
+        unsigned long value;
+};
+
+static bool find_symbol_in_section(const struct symsearch *syms,
+                                   struct module *owner,
+                                   unsigned int symnum, void *data)
+{
+        struct find_symbol_arg *fsa = data;
+
+        if (strcmp(syms->start[symnum].name, fsa->name) != 0)
+                return false;
+
+        if (!fsa->gplok) {
+                if (syms->licence == GPL_ONLY)
+                        return false;
+                if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) {
+                        printk(KERN_WARNING "Symbol %s is being used "
+                               "by a non-GPL module, which will not "
+                               "be allowed in the future\n", fsa->name);
+                        printk(KERN_WARNING "Please see the file "
+                               "Documentation/feature-removal-schedule.txt "
+                               "in the kernel source tree for more details.\n");
                 }
         }
 
+#ifdef CONFIG_UNUSED_SYMBOLS
+        if (syms->unused && fsa->warn) {
+                printk(KERN_WARNING "Symbol %s is marked as UNUSED, "
+                       "however this module is using it.\n", fsa->name);
+                printk(KERN_WARNING
+                       "This symbol will go away in the future.\n");
+                printk(KERN_WARNING
+                       "Please evalute if this is the right api to use and if "
+                       "it really is, submit a report the linux kernel "
+                       "mailinglist together with submitting your code for "
+                       "inclusion.\n");
+        }
+#endif
+
+        fsa->owner = owner;
+        fsa->crc = symversion(syms->crcs, symnum);
+        fsa->value = syms->start[symnum].value;
+        return true;
+}
+
+/* Find a symbol, return value, (optional) crc and (optional) module
+ * which owns it */
+static unsigned long find_symbol(const char *name,
+                                 struct module **owner,
+                                 const unsigned long **crc,
+                                 bool gplok,
+                                 bool warn)
+{
+        struct find_symbol_arg fsa;
+
+        fsa.name = name;
+        fsa.gplok = gplok;
+        fsa.warn = warn;
+
+        if (each_symbol(find_symbol_in_section, &fsa)) {
+                if (owner)
+                        *owner = fsa.owner;
+                if (crc)
+                        *crc = fsa.crc;
+                return fsa.value;
+        }
+
         DEBUGP("Failed to find symbol %s\n", name);
         return -ENOENT;
 }
@@ -639,8 +662,8 @@ static int __try_stop_module(void *_sref)
 {
         struct stopref *sref = _sref;
 
-        /* If it's not unused, quit unless we are told to block. */
-        if ((sref->flags & O_NONBLOCK) && module_refcount(sref->mod) != 0) {
+        /* If it's not unused, quit unless we're forcing. */
+        if (module_refcount(sref->mod) != 0) {
                 if (!(*sref->forced = try_force_unload(sref->flags)))
                         return -EWOULDBLOCK;
         }
@@ -652,9 +675,16 @@ static int __try_stop_module(void *_sref)
 
 static int try_stop_module(struct module *mod, int flags, int *forced)
 {
-        struct stopref sref = { mod, flags, forced };
+        if (flags & O_NONBLOCK) {
+                struct stopref sref = { mod, flags, forced };
 
-        return stop_machine_run(__try_stop_module, &sref, NR_CPUS);
+                return stop_machine(__try_stop_module, &sref, NULL);
+        } else {
+                /* We don't need to stop the machine for this. */
+                mod->state = MODULE_STATE_GOING;
+                synchronize_sched();
+                return 0;
+        }
 }
 
 unsigned int module_refcount(struct module *mod)
@@ -1386,7 +1416,7 @@ static int __unlink_module(void *_mod)
 static void free_module(struct module *mod)
 {
         /* Delete from various lists */
-        stop_machine_run(__unlink_module, mod, NR_CPUS);
+        stop_machine(__unlink_module, mod, NULL);
         remove_notes_attrs(mod);
         remove_sect_attrs(mod);
         mod_kobject_remove(mod);
@@ -1445,8 +1475,10 @@ static int verify_export_symbols(struct module *mod)
                 { mod->syms, mod->num_syms },
                 { mod->gpl_syms, mod->num_gpl_syms },
                 { mod->gpl_future_syms, mod->num_gpl_future_syms },
+#ifdef CONFIG_UNUSED_SYMBOLS
                 { mod->unused_syms, mod->num_unused_syms },
                 { mod->unused_gpl_syms, mod->num_unused_gpl_syms },
+#endif
         };
 
         for (i = 0; i < ARRAY_SIZE(arr); i++) {
@@ -1526,7 +1558,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 }
 
 /* Update size with this section: return offset. */
-static long get_offset(unsigned long *size, Elf_Shdr *sechdr)
+static long get_offset(unsigned int *size, Elf_Shdr *sechdr)
 {
         long ret;
 
@@ -1659,6 +1691,19 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
 }
 
 #ifdef CONFIG_KALLSYMS
+
+/* lookup symbol in given range of kernel_symbols */
+static const struct kernel_symbol *lookup_symbol(const char *name,
+        const struct kernel_symbol *start,
+        const struct kernel_symbol *stop)
+{
+        const struct kernel_symbol *ks = start;
+        for (; ks < stop; ks++)
+                if (strcmp(ks->name, name) == 0)
+                        return ks;
+        return NULL;
+}
+
 static int is_exported(const char *name, const struct module *mod)
 {
         if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab))
@@ -1738,9 +1783,23 @@ static inline void add_kallsyms(struct module *mod,
 }
 #endif /* CONFIG_KALLSYMS */
 
+static void *module_alloc_update_bounds(unsigned long size)
+{
+        void *ret = module_alloc(size);
+
+        if (ret) {
+                /* Update module bounds. */
+                if ((unsigned long)ret < module_addr_min)
+                        module_addr_min = (unsigned long)ret;
+                if ((unsigned long)ret + size > module_addr_max)
+                        module_addr_max = (unsigned long)ret + size;
+        }
+        return ret;
+}
+
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
-static struct module *load_module(void __user *umod,
+static noinline struct module *load_module(void __user *umod,
                                   unsigned long len,
                                   const char __user *uargs)
 {
@@ -1764,10 +1823,12 @@ static struct module *load_module(void __user *umod,
         unsigned int gplfutureindex;
         unsigned int gplfuturecrcindex;
         unsigned int unwindex = 0;
+#ifdef CONFIG_UNUSED_SYMBOLS
         unsigned int unusedindex;
         unsigned int unusedcrcindex;
         unsigned int unusedgplindex;
         unsigned int unusedgplcrcindex;
+#endif
         unsigned int markersindex;
         unsigned int markersstringsindex;
         struct module *mod;
@@ -1850,13 +1911,15 @@ static struct module *load_module(void __user *umod,
         exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab");
         gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl");
         gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future");
-        unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused");
-        unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl");
         crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab");
         gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl");
         gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future");
+#ifdef CONFIG_UNUSED_SYMBOLS
+        unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused");
+        unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl");
         unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused");
         unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl");
+#endif
         setupindex = find_sec(hdr, sechdrs, secstrings, "__param");
         exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table");
         obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm");
@@ -1935,7 +1998,7 @@ static struct module *load_module(void __user *umod,
         layout_sections(mod, hdr, sechdrs, secstrings);
 
         /* Do the allocs. */
-        ptr = module_alloc(mod->core_size);
+        ptr = module_alloc_update_bounds(mod->core_size);
         if (!ptr) {
                 err = -ENOMEM;
                 goto free_percpu;
@@ -1943,7 +2006,7 @@ static struct module *load_module(void __user *umod,
         memset(ptr, 0, mod->core_size);
         mod->module_core = ptr;
 
-        ptr = module_alloc(mod->init_size);
+        ptr = module_alloc_update_bounds(mod->init_size);
         if (!ptr && mod->init_size) {
                 err = -ENOMEM;
                 goto free_core;
@@ -2018,14 +2081,15 @@ static struct module *load_module(void __user *umod,
                 mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr;
         mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size /
                                         sizeof(*mod->gpl_future_syms);
-        mod->num_unused_syms = sechdrs[unusedindex].sh_size /
-                                        sizeof(*mod->unused_syms);
-        mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size /
-                                        sizeof(*mod->unused_gpl_syms);
         mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr;
         if (gplfuturecrcindex)
                 mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr;
 
+#ifdef CONFIG_UNUSED_SYMBOLS
+        mod->num_unused_syms = sechdrs[unusedindex].sh_size /
+                                        sizeof(*mod->unused_syms);
+        mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size /
+                                        sizeof(*mod->unused_gpl_syms);
         mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr;
         if (unusedcrcindex)
                 mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr;
@@ -2033,13 +2097,17 @@ static struct module *load_module(void __user *umod,
         if (unusedgplcrcindex)
                 mod->unused_gpl_crcs
                         = (void *)sechdrs[unusedgplcrcindex].sh_addr;
+#endif
 
 #ifdef CONFIG_MODVERSIONS
-        if ((mod->num_syms && !crcindex) ||
-            (mod->num_gpl_syms && !gplcrcindex) ||
-            (mod->num_gpl_future_syms && !gplfuturecrcindex) ||
-            (mod->num_unused_syms && !unusedcrcindex) ||
-            (mod->num_unused_gpl_syms && !unusedgplcrcindex)) {
+        if ((mod->num_syms && !crcindex)
+            || (mod->num_gpl_syms && !gplcrcindex)
+            || (mod->num_gpl_future_syms && !gplfuturecrcindex)
+#ifdef CONFIG_UNUSED_SYMBOLS
+            || (mod->num_unused_syms && !unusedcrcindex)
+            || (mod->num_unused_gpl_syms && !unusedgplcrcindex)
+#endif
+                ) {
                 printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name);
                 err = try_to_force_load(mod, "nocrc");
                 if (err)
@@ -2129,7 +2197,7 @@ static struct module *load_module(void __user *umod,
         /* Now sew it into the lists so we can get lockdep and oops
          * info during argument parsing.  Noone should access us, since
          * strong_try_module_get() will fail. */
-        stop_machine_run(__link_module, mod, NR_CPUS);
+        stop_machine(__link_module, mod, NULL);
 
         /* Size of section 0 is 0, so this works well if no params */
         err = parse_args(mod->name, mod->args,
@@ -2163,7 +2231,7 @@ static struct module *load_module(void __user *umod,
         return mod;
 
  unlink:
-        stop_machine_run(__unlink_module, mod, NR_CPUS);
+        stop_machine(__unlink_module, mod, NULL);
         module_arch_cleanup(mod);
  cleanup:
         kobject_del(&mod->mkobj.kobj);
@@ -2220,7 +2288,7 @@ sys_init_module(void __user *umod,
 
         /* Start the module */
         if (mod->init != NULL)
-                ret = mod->init();
+                ret = do_one_initcall(mod->init);
         if (ret < 0) {
                 /* Init routine failed: abort.  Try to protect us from
                    buggy refcounters. */
@@ -2512,7 +2580,7 @@ static int m_show(struct seq_file *m, void *p)
         struct module *mod = list_entry(p, struct module, list);
         char buf[8];
 
-        seq_printf(m, "%s %lu",
+        seq_printf(m, "%s %u",
                    mod->name, mod->init_size + mod->core_size);
         print_unload_info(m, mod);
 
@@ -2595,6 +2663,9 @@ struct module *__module_text_address(unsigned long addr)
 {
         struct module *mod;
 
+        if (addr < module_addr_min || addr > module_addr_max)
+                return NULL;
+
         list_for_each_entry(mod, &modules, list)
                 if (within(addr, mod->module_init, mod->init_text_size)
                     || within(addr, mod->module_core, mod->core_text_size))
diff --git a/kernel/mutex.c b/kernel/mutex.c
index bcdc9ac8ef60..12c779dc65d4 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -34,6 +34,7 @@
 /***
  * mutex_init - initialize the mutex
  * @lock: the mutex to be initialized
+ * @key: the lock_class_key for the class; used by mutex lock debugging
  *
  * Initialize the mutex to unlocked state.
  *
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 48d7ed6fc3a4..43c2111cd54d 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
+#include <linux/proc_fs.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
 
@@ -24,9 +25,12 @@ static inline struct ns_cgroup *cgroup_to_ns(
                             struct ns_cgroup, css);
 }
 
-int ns_cgroup_clone(struct task_struct *task)
+int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 {
-        return cgroup_clone(task, &ns_subsys);
+        char name[PROC_NUMBUF];
+
+        snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid));
+        return cgroup_clone(task, &ns_subsys, name);
 }
 
 /*
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index adc785146a1c..1d3ef29a2583 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
 #include <linux/mnt_namespace.h>
@@ -157,12 +156,6 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
                 goto out;
         }
 
-        err = ns_cgroup_clone(tsk);
-        if (err) {
-                put_nsproxy(new_ns);
-                goto out;
-        }
-
         tsk->nsproxy = new_ns;
 
 out:
@@ -209,7 +202,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
                 goto out;
         }
 
-        err = ns_cgroup_clone(current);
+        err = ns_cgroup_clone(current, task_pid(current));
         if (err)
                 put_nsproxy(*new_nsp);
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 425567f45b9f..12c5a0a6c89b 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -318,6 +318,28 @@ void warn_on_slowpath(const char *file, int line)
         add_taint(TAINT_WARN);
 }
 EXPORT_SYMBOL(warn_on_slowpath);
+
+
+void warn_slowpath(const char *file, int line, const char *fmt, ...)
+{
+        va_list args;
+        char function[KSYM_SYMBOL_LEN];
+        unsigned long caller = (unsigned long)__builtin_return_address(0);
+        sprint_symbol(function, caller);
+
+        printk(KERN_WARNING "------------[ cut here ]------------\n");
+        printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
+                line, function);
+        va_start(args, fmt);
+        vprintk(fmt, args);
+        va_end(args);
+
+        print_modules();
+        dump_stack();
+        print_oops_end_marker();
+        add_taint(TAINT_WARN);
+}
+EXPORT_SYMBOL(warn_slowpath);
 #endif
 
 #ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/kernel/pid.c b/kernel/pid.c
index 30bd5d4b2ac7..064e76afa507 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -309,12 +309,6 @@ struct pid *find_vpid(int nr)
 }
 EXPORT_SYMBOL_GPL(find_vpid);
 
-struct pid *find_pid(int nr)
-{
-        return find_pid_ns(nr, &init_pid_ns);
-}
-EXPORT_SYMBOL_GPL(find_pid);
-
 /*
  * attach_pid() must be called with the tasklist_lock write-held.
  */
@@ -435,6 +429,7 @@ struct pid *find_get_pid(pid_t nr)
 
         return pid;
 }
+EXPORT_SYMBOL_GPL(find_get_pid);
 
 pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
 {
@@ -482,7 +477,7 @@ EXPORT_SYMBOL(task_session_nr_ns);
 /*
  * Used by proc to find the first pid that is greater then or equal to nr.
  *
- * If there is a pid at nr this function is exactly the same as find_pid.
+ * If there is a pid at nr this function is exactly the same as find_pid_ns.
  */
 struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 {
@@ -497,7 +492,6 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 
         return pid;
 }
-EXPORT_SYMBOL_GPL(find_get_pid);
 
 /*
  * The pid hash table is scaled according to the amount of memory in the
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 98702b4b8851..fab8ea86fac3 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -12,6 +12,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/err.h>
+#include <linux/acct.h>
 
 #define BITS_PER_PAGE           (PAGE_SIZE*8)
 
@@ -71,7 +72,7 @@ static struct pid_namespace *create_pid_namespace(unsigned int level)
         struct pid_namespace *ns;
         int i;
 
-        ns = kmem_cache_alloc(pid_ns_cachep, GFP_KERNEL);
+        ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
         if (ns == NULL)
                 goto out;
 
@@ -84,17 +85,13 @@ static struct pid_namespace *create_pid_namespace(unsigned int level)
                 goto out_free_map;
 
         kref_init(&ns->kref);
-        ns->last_pid = 0;
-        ns->child_reaper = NULL;
         ns->level = level;
 
         set_bit(0, ns->pidmap[0].page);
         atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
 
-        for (i = 1; i < PIDMAP_ENTRIES; i++) {
-                ns->pidmap[i].page = NULL;
+        for (i = 1; i < PIDMAP_ENTRIES; i++)
                 atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
-        }
 
         return ns;
 
@@ -182,9 +179,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
                 rc = sys_wait4(-1, NULL, __WALL, NULL);
         } while (rc != -ECHILD);
 
-
-        /* Child reaper for the pid namespace is going away */
-        pid_ns->child_reaper = NULL;
+        acct_exit_ns(pid_ns);
         return;
 }
 
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 8cb757026386..dfdec524d1b7 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -24,7 +24,7 @@
  * requirement that the application has is cleaned up when closes the file
  * pointer or exits the pm_qos_object will get an opportunity to clean up.
  *
- * mark gross mgross@linux.intel.com
+ * Mark Gross <mgross@linux.intel.com>
  */
 
 #include <linux/pm_qos_params.h>
@@ -43,7 +43,7 @@
 #include <linux/uaccess.h>
 
 /*
- * locking rule: all changes to target_value or requirements or notifiers lists
+ * locking rule: all changes to requirements or notifiers lists
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
@@ -66,7 +66,7 @@ struct pm_qos_object {
         struct miscdevice pm_qos_power_miscdev;
         char *name;
         s32 default_value;
-        s32 target_value;
+        atomic_t target_value;
         s32 (*comparitor)(s32, s32);
 };
 
@@ -77,7 +77,7 @@ static struct pm_qos_object cpu_dma_pm_qos = {
         .notifiers = &cpu_dma_lat_notifier,
         .name = "cpu_dma_latency",
         .default_value = 2000 * USEC_PER_SEC,
-        .target_value = 2000 * USEC_PER_SEC,
+        .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
         .comparitor = min_compare
 };
 
@@ -87,7 +87,7 @@ static struct pm_qos_object network_lat_pm_qos = {
         .notifiers = &network_lat_notifier,
         .name = "network_latency",
         .default_value = 2000 * USEC_PER_SEC,
-        .target_value = 2000 * USEC_PER_SEC,
+        .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
         .comparitor = min_compare
 };
 
@@ -99,7 +99,7 @@ static struct pm_qos_object network_throughput_pm_qos = {
         .notifiers = &network_throughput_notifier,
         .name = "network_throughput",
         .default_value = 0,
-        .target_value = 0,
+        .target_value = ATOMIC_INIT(0),
         .comparitor = max_compare
 };
 
@@ -150,11 +150,11 @@ static void update_target(int target)
                 extreme_value = pm_qos_array[target]->comparitor(
                                 extreme_value, node->value);
         }
-        if (pm_qos_array[target]->target_value != extreme_value) {
+        if (atomic_read(&pm_qos_array[target]->target_value) != extreme_value) {
                 call_notifier = 1;
-                pm_qos_array[target]->target_value = extreme_value;
+                atomic_set(&pm_qos_array[target]->target_value, extreme_value);
                 pr_debug(KERN_ERR "new target for qos %d is %d\n", target,
-                        pm_qos_array[target]->target_value);
+                        atomic_read(&pm_qos_array[target]->target_value));
         }
         spin_unlock_irqrestore(&pm_qos_lock, flags);
 
@@ -193,14 +193,7 @@ static int find_pm_qos_object_by_minor(int minor)
  */
 int pm_qos_requirement(int pm_qos_class)
 {
-        int ret_val;
-        unsigned long flags;
-
-        spin_lock_irqsave(&pm_qos_lock, flags);
-        ret_val = pm_qos_array[pm_qos_class]->target_value;
-        spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-        return ret_val;
+        return atomic_read(&pm_qos_array[pm_qos_class]->target_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_requirement);
 
@@ -211,8 +204,8 @@ EXPORT_SYMBOL_GPL(pm_qos_requirement);
  * @value: defines the qos request
  *
  * This function inserts a new entry in the pm_qos_class list of requested qos
- * performance charactoistics.  It recomputes the agregate QoS expectations for
- * the pm_qos_class of parrameters.
+ * performance characteristics.  It recomputes the aggregate QoS expectations
+ * for the pm_qos_class of parameters.
  */
 int pm_qos_add_requirement(int pm_qos_class, char *name, s32 value)
 {
@@ -250,10 +243,10 @@ EXPORT_SYMBOL_GPL(pm_qos_add_requirement);
  * @name: identifies the request
  * @value: defines the qos request
  *
- * Updates an existing qos requierement for the pm_qos_class of parameters along
+ * Updates an existing qos requirement for the pm_qos_class of parameters along
  * with updating the target pm_qos_class value.
  *
- * If the named request isn't in the lest then no change is made.
+ * If the named request isn't in the list then no change is made.
  */
 int pm_qos_update_requirement(int pm_qos_class, char *name, s32 new_value)
 {
@@ -287,7 +280,7 @@ EXPORT_SYMBOL_GPL(pm_qos_update_requirement);
  * @pm_qos_class: identifies which list of qos request to us
  * @name: identifies the request
  *
- * Will remove named qos request from pm_qos_class list of parrameters and
+ * Will remove named qos request from pm_qos_class list of parameters and
  * recompute the current target value for the pm_qos_class.
  */
 void pm_qos_remove_requirement(int pm_qos_class, char *name)
@@ -319,7 +312,7 @@ EXPORT_SYMBOL_GPL(pm_qos_remove_requirement);
  * @notifier: notifier block managed by caller.
  *
  * will register the notifier into a notification chain that gets called
- * uppon changes to the pm_qos_class target value.
+ * upon changes to the pm_qos_class target value.
  */
  int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
 {
@@ -338,7 +331,7 @@ EXPORT_SYMBOL_GPL(pm_qos_add_notifier);
  * @notifier: notifier block to be removed.
  *
  * will remove the notifier from the notification chain that gets called
- * uppon changes to the pm_qos_class target value.
+ * upon changes to the pm_qos_class target value.
  */
 int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
 {
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index dbd8398ddb0b..e36d5798cbff 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -289,21 +289,29 @@ void do_schedule_next_timer(struct siginfo *info)
                 else
                         schedule_next_timer(timr);
 
-                info->si_overrun = timr->it_overrun_last;
+                info->si_overrun += timr->it_overrun_last;
         }
 
         if (timr)
                 unlock_timer(timr, flags);
 }
 
-int posix_timer_event(struct k_itimer *timr,int si_private)
+int posix_timer_event(struct k_itimer *timr, int si_private)
 {
-        memset(&timr->sigq->info, 0, sizeof(siginfo_t));
+        /*
+         * FIXME: if ->sigq is queued we can race with
+         * dequeue_signal()->do_schedule_next_timer().
+         *
+         * If dequeue_signal() sees the "right" value of
+         * si_sys_private it calls do_schedule_next_timer().
+         * We re-queue ->sigq and drop ->it_lock().
+         * do_schedule_next_timer() locks the timer
+         * and re-schedules it while ->sigq is pending.
+         * Not really bad, but not that we want.
+         */
         timr->sigq->info.si_sys_private = si_private;
-        /* Send signal to the process that owns this timer.*/
 
         timr->sigq->info.si_signo = timr->it_sigev_signo;
-        timr->sigq->info.si_errno = 0;
         timr->sigq->info.si_code = SI_TIMER;
         timr->sigq->info.si_tid = timr->it_id;
         timr->sigq->info.si_value = timr->it_sigev_value;
@@ -435,6 +443,7 @@ static struct k_itimer * alloc_posix_timer(void)
                 kmem_cache_free(posix_timers_cache, tmr);
                 tmr = NULL;
         }
+        memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
         return tmr;
 }
 
@@ -449,9 +458,6 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
                 spin_unlock_irqrestore(&idr_lock, flags);
         }
         sigqueue_free(tmr->sigq);
-        if (unlikely(tmr->it_process) &&
-            tmr->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                put_task_struct(tmr->it_process);
         kmem_cache_free(posix_timers_cache, tmr);
 }
 
@@ -856,11 +862,10 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_process) {
-                if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                        put_task_struct(timer->it_process);
-                timer->it_process = NULL;
-        }
+        if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
+                put_task_struct(timer->it_process);
+        timer->it_process = NULL;
+
         unlock_timer(timer, flags);
         release_posix_timer(timer, IT_ID_SET);
         return 0;
@@ -885,11 +890,10 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_process) {
-                if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                        put_task_struct(timer->it_process);
-                timer->it_process = NULL;
-        }
+        if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
+                put_task_struct(timer->it_process);
+        timer->it_process = NULL;
+
         unlock_timer(timer, flags);
         release_posix_timer(timer, IT_ID_SET);
 }
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index b45da40e8d25..dcd165f92a88 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -82,7 +82,7 @@ config PM_SLEEP_SMP
 
 config PM_SLEEP
         bool
-        depends on SUSPEND || HIBERNATION
+        depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
         default y
 
 config SUSPEND
@@ -94,6 +94,17 @@ config SUSPEND
           powered and thus its contents are preserved, such as the
           suspend-to-RAM state (e.g. the ACPI S3 state).
 
+config PM_TEST_SUSPEND
+        bool "Test suspend/resume and wakealarm during bootup"
+        depends on SUSPEND && PM_DEBUG && RTC_LIB=y
+        ---help---
+        This option will let you suspend your machine during bootup, and
+        make it wake up a few seconds later using an RTC wakeup alarm.
+        Enable this with a kernel parameter like "test_suspend=mem".
+
+        You probably want to have your system's RTC driver statically
+        linked, ensuring that it's available when this test runs.
+
 config SUSPEND_FREEZER
         bool "Enable freezer for suspend to RAM/standby" \
                 if ARCH_WANTS_FREEZER_CONTROL || BROKEN
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index f011e0870b52..bbd85c60f741 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -21,6 +21,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -255,7 +256,7 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
-        int error;
+        int error, ftrace_save;
 
         /* Free memory before shutting down devices. */
         error = swsusp_shrink_memory();
@@ -267,6 +268,7 @@ int hibernation_snapshot(int platform_mode)
                 goto Close;
 
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
         error = device_suspend(PMSG_FREEZE);
         if (error)
                 goto Recover_platform;
@@ -296,6 +298,7 @@ int hibernation_snapshot(int platform_mode)
  Resume_devices:
         device_resume(in_suspend ?
                 (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
  Close:
         platform_end(platform_mode);
@@ -366,10 +369,11 @@ static int resume_target_kernel(void)
 
 int hibernation_restore(int platform_mode)
 {
-        int error;
+        int error, ftrace_save;
 
         pm_prepare_console();
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
         error = device_suspend(PMSG_QUIESCE);
         if (error)
                 goto Finish;
@@ -384,6 +388,7 @@ int hibernation_restore(int platform_mode)
         platform_restore_cleanup(platform_mode);
         device_resume(PMSG_RECOVER);
  Finish:
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
         pm_restore_console();
         return error;
@@ -396,7 +401,7 @@ int hibernation_restore(int platform_mode)
 
 int hibernation_platform_enter(void)
 {
-        int error;
+        int error, ftrace_save;
 
         if (!hibernation_ops)
                 return -ENOSYS;
@@ -411,6 +416,7 @@ int hibernation_platform_enter(void)
                 goto Close;
 
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
         error = device_suspend(PMSG_HIBERNATE);
         if (error) {
                 if (hibernation_ops->recover)
@@ -445,6 +451,7 @@ int hibernation_platform_enter(void)
         hibernation_ops->finish();
  Resume_devices:
         device_resume(PMSG_RESTORE);
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
  Close:
         hibernation_ops->end();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 3398f4651aa1..540b16b68565 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -21,6 +21,7 @@
 #include <linux/freezer.h>
 #include <linux/vmstat.h>
 #include <linux/syscalls.h>
+#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -132,6 +133,61 @@ static inline int suspend_test(int level) { return 0; }
 
 #ifdef CONFIG_SUSPEND
 
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending.  Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS    5
+
+static unsigned long suspend_test_start_time;
+
+static void suspend_test_start(void)
+{
+        /* FIXME Use better timebase than "jiffies", ideally a clocksource.
+         * What we want is a hardware counter that will work correctly even
+         * during the irqs-are-off stages of the suspend/resume cycle...
+         */
+        suspend_test_start_time = jiffies;
+}
+
+static void suspend_test_finish(const char *label)
+{
+        long nj = jiffies - suspend_test_start_time;
+        unsigned msec;
+
+        msec = jiffies_to_msecs(abs(nj));
+        pr_info("PM: %s took %d.%03d seconds\n", label,
+                        msec / 1000, msec % 1000);
+
+        /* Warning on suspend means the RTC alarm period needs to be
+         * larger -- the system was sooo slooowwww to suspend that the
+         * alarm (should have) fired before the system went to sleep!
+         *
+         * Warning on either suspend or resume also means the system
+         * has some performance issues.  The stack dump of a WARN_ON
+         * is more likely to get the right attention than a printk...
+         */
+        WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000));
+}
+
+#else
+
+static void suspend_test_start(void)
+{
+}
+
+static void suspend_test_finish(const char *label)
+{
+}
+
+#endif
+
 /* This is just an arbitrary number */
 #define FREE_PAGE_NUMBER (100)
 
@@ -255,7 +311,7 @@ static int suspend_enter(suspend_state_t state)
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
-        int error;
+        int error, ftrace_save;
 
         if (!suspend_ops)
                 return -ENOSYS;
@@ -266,12 +322,14 @@ int suspend_devices_and_enter(suspend_state_t state)
                         goto Close;
         }
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
+        suspend_test_start();
         error = device_suspend(PMSG_SUSPEND);
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to suspend\n");
                 goto Recover_platform;
         }
-
+        suspend_test_finish("suspend devices");
         if (suspend_test(TEST_DEVICES))
                 goto Recover_platform;
 
@@ -293,7 +351,10 @@ int suspend_devices_and_enter(suspend_state_t state)
         if (suspend_ops->finish)
                 suspend_ops->finish();
  Resume_devices:
+        suspend_test_start();
         device_resume(PMSG_RESUME);
+        suspend_test_finish("resume devices");
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
  Close:
         if (suspend_ops->end)
@@ -521,3 +582,144 @@ static int __init pm_init(void)
 }
 
 core_initcall(pm_init);
+
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+#include <linux/rtc.h>
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system.  RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+        static char err_readtime[] __initdata =
+                KERN_ERR "PM: can't read %s time, err %d\n";
+        static char err_wakealarm [] __initdata =
+                KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+        static char err_suspend[] __initdata =
+                KERN_ERR "PM: suspend test failed, error %d\n";
+        static char info_test[] __initdata =
+                KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+        unsigned long           now;
+        struct rtc_wkalrm       alm;
+        int                     status;
+
+        /* this may fail if the RTC hasn't been initialized */
+        status = rtc_read_time(rtc, &alm.time);
+        if (status < 0) {
+                printk(err_readtime, rtc->dev.bus_id, status);
+                return;
+        }
+        rtc_tm_to_time(&alm.time, &now);
+
+        memset(&alm, 0, sizeof alm);
+        rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+        alm.enabled = true;
+
+        status = rtc_set_alarm(rtc, &alm);
+        if (status < 0) {
+                printk(err_wakealarm, rtc->dev.bus_id, status);
+                return;
+        }
+
+        if (state == PM_SUSPEND_MEM) {
+                printk(info_test, pm_states[state]);
+                status = pm_suspend(state);
+                if (status == -ENODEV)
+                        state = PM_SUSPEND_STANDBY;
+        }
+        if (state == PM_SUSPEND_STANDBY) {
+                printk(info_test, pm_states[state]);
+                status = pm_suspend(state);
+        }
+        if (status < 0)
+                printk(err_suspend, status);
+
+        /* Some platforms can't detect that the alarm triggered the
+         * wakeup, or (accordingly) disable it after it afterwards.
+         * It's supposed to give oneshot behavior; cope.
+         */
+        alm.enabled = false;
+        rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+        struct rtc_device *candidate = to_rtc_device(dev);
+
+        if (!candidate->ops->set_alarm)
+                return 0;
+        if (!device_may_wakeup(candidate->dev.parent))
+                return 0;
+
+        *(char **)name_ptr = dev->bus_id;
+        return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time.  They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+
+static char warn_bad_state[] __initdata =
+        KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+        unsigned i;
+
+        /* "=mem" ==> "mem" */
+        value++;
+        for (i = 0; i < PM_SUSPEND_MAX; i++) {
+                if (!pm_states[i])
+                        continue;
+                if (strcmp(pm_states[i], value) != 0)
+                        continue;
+                test_state = (__force suspend_state_t) i;
+                return 0;
+        }
+        printk(warn_bad_state, value);
+        return 0;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+        static char             warn_no_rtc[] __initdata =
+                KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+        char                    *pony = NULL;
+        struct rtc_device       *rtc = NULL;
+
+        /* PM is initialized by now; is that state testable? */
+        if (test_state == PM_SUSPEND_ON)
+                goto done;
+        if (!valid_state(test_state)) {
+                printk(warn_bad_state, pm_states[test_state]);
+                goto done;
+        }
+
+        /* RTCs have initialized by now too ... can we use one? */
+        class_find_device(rtc_class, NULL, &pony, has_wakealarm);
+        if (pony)
+                rtc = rtc_class_open(pony);
+        if (!rtc) {
+                printk(warn_no_rtc);
+                goto done;
+        }
+
+        /* go for it */
+        test_wakealarm(rtc, test_state);
+        rtc_class_close(rtc);
+done:
+        return 0;
+}
+late_initcall(test_suspend);
+
+#endif /* CONFIG_PM_TEST_SUSPEND */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 700f44ec8406..acc0c101dbd5 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void);
 
 extern int pfn_is_nosave(unsigned long);
 
-extern struct mutex pm_mutex;
-
 #define power_attr(_name) \
 static struct kobj_attribute _name##_attr = {   \
         .attr   = {                             \
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 678ec736076b..72016f051477 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -10,6 +10,7 @@
 #include <linux/pm.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
+#include <linux/cpumask.h>
 
 /*
  * When the user hits Sys-Rq o to power down the machine this is the
@@ -25,7 +26,8 @@ static DECLARE_WORK(poweroff_work, do_poweroff);
 
 static void handle_poweroff(int key, struct tty_struct *tty)
 {
-        schedule_work(&poweroff_work);
+        /* run sysrq poweroff on boot cpu */
+        schedule_work_on(first_cpu(cpu_online_map), &poweroff_work);
 }
 
 static struct sysrq_key_op      sysrq_poweroff_op = {
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5fb87652f214..278946aecaf0 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -149,7 +149,7 @@ static int try_to_freeze_tasks(bool sig_only)
         unsigned long end_time;
         unsigned int todo;
         struct timeval start, end;
-        s64 elapsed_csecs64;
+        u64 elapsed_csecs64;
         unsigned int elapsed_csecs;
 
         do_gettimeofday(&start);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5f91a07c4eac..5d2ab836e998 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -205,8 +205,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *      objects.  The main list's elements are of type struct zone_bitmap
  *      and each of them corresonds to one zone.  For each zone bitmap
  *      object there is a list of objects of type struct bm_block that
- *      represent each blocks of bit chunks in which information is
- *      stored.
+ *      represent each blocks of bitmap in which information is stored.
  *
  *      struct memory_bitmap contains a pointer to the main list of zone
  *      bitmap objects, a struct bm_position used for browsing the bitmap,
@@ -224,26 +223,27 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *      pfns that correspond to the start and end of the represented zone.
  *
  *      struct bm_block contains a pointer to the memory page in which
- *      information is stored (in the form of a block of bit chunks
- *      of type unsigned long each).  It also contains the pfns that
- *      correspond to the start and end of the represented memory area and
- *      the number of bit chunks in the block.
+ *      information is stored (in the form of a block of bitmap)
+ *      It also contains the pfns that correspond to the start and end of
+ *      the represented memory area.
  */
 
 #define BM_END_OF_MAP   (~0UL)
 
-#define BM_CHUNKS_PER_BLOCK     (PAGE_SIZE / sizeof(long))
-#define BM_BITS_PER_CHUNK       (sizeof(long) << 3)
 #define BM_BITS_PER_BLOCK       (PAGE_SIZE << 3)
 
 struct bm_block {
         struct bm_block *next;          /* next element of the list */
         unsigned long start_pfn;        /* pfn represented by the first bit */
         unsigned long end_pfn;  /* pfn represented by the last bit plus 1 */
-        unsigned int size;      /* number of bit chunks */
-        unsigned long *data;    /* chunks of bits representing pages */
+        unsigned long *data;    /* bitmap representing pages */
 };
 
+static inline unsigned long bm_block_bits(struct bm_block *bb)
+{
+        return bb->end_pfn - bb->start_pfn;
+}
+
 struct zone_bitmap {
         struct zone_bitmap *next;       /* next element of the list */
         unsigned long start_pfn;        /* minimal pfn in this zone */
@@ -257,7 +257,6 @@ struct zone_bitmap {
 struct bm_position {
         struct zone_bitmap *zone_bm;
         struct bm_block *block;
-        int chunk;
         int bit;
 };
 
@@ -272,12 +271,6 @@ struct memory_bitmap {
 
 /* Functions that operate on memory bitmaps */
 
-static inline void memory_bm_reset_chunk(struct memory_bitmap *bm)
-{
-        bm->cur.chunk = 0;
-        bm->cur.bit = -1;
-}
-
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
         struct zone_bitmap *zone_bm;
@@ -285,7 +278,7 @@ static void memory_bm_position_reset(struct memory_bitmap *bm)
         zone_bm = bm->zone_bm_list;
         bm->cur.zone_bm = zone_bm;
         bm->cur.block = zone_bm->bm_blocks;
-        memory_bm_reset_chunk(bm);
+        bm->cur.bit = 0;
 }
 
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
@@ -394,12 +387,10 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
                         bb->start_pfn = pfn;
                         if (nr >= BM_BITS_PER_BLOCK) {
                                 pfn += BM_BITS_PER_BLOCK;
-                                bb->size = BM_CHUNKS_PER_BLOCK;
                                 nr -= BM_BITS_PER_BLOCK;
                         } else {
                                 /* This is executed only once in the loop */
                                 pfn += nr;
-                                bb->size = DIV_ROUND_UP(nr, BM_BITS_PER_CHUNK);
                         }
                         bb->end_pfn = pfn;
                         bb = bb->next;
@@ -478,8 +469,8 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
         }
         zone_bm->cur_block = bb;
         pfn -= bb->start_pfn;
-        *bit_nr = pfn % BM_BITS_PER_CHUNK;
-        *addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+        *bit_nr = pfn;
+        *addr = bb->data;
         return 0;
 }
 
@@ -528,36 +519,6 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
         return test_bit(bit, addr);
 }
 
-/* Two auxiliary functions for memory_bm_next_pfn */
-
-/* Find the first set bit in the given chunk, if there is one */
-
-static inline int next_bit_in_chunk(int bit, unsigned long *chunk_p)
-{
-        bit++;
-        while (bit < BM_BITS_PER_CHUNK) {
-                if (test_bit(bit, chunk_p))
-                        return bit;
-
-                bit++;
-        }
-        return -1;
-}
-
-/* Find a chunk containing some bits set in given block of bits */
-
-static inline int next_chunk_in_block(int n, struct bm_block *bb)
-{
-        n++;
-        while (n < bb->size) {
-                if (bb->data[n])
-                        return n;
-
-                n++;
-        }
-        return -1;
-}
-
 /**
  *      memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *      in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -571,40 +532,33 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
         struct zone_bitmap *zone_bm;
         struct bm_block *bb;
-        int chunk;
         int bit;
 
         do {
                 bb = bm->cur.block;
                 do {
-                        chunk = bm->cur.chunk;
                         bit = bm->cur.bit;
-                        do {
-                                bit = next_bit_in_chunk(bit, bb->data + chunk);
-                                if (bit >= 0)
-                                        goto Return_pfn;
-
-                                chunk = next_chunk_in_block(chunk, bb);
-                                bit = -1;
-                        } while (chunk >= 0);
+                        bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+                        if (bit < bm_block_bits(bb))
+                                goto Return_pfn;
+
                         bb = bb->next;
                         bm->cur.block = bb;
-                        memory_bm_reset_chunk(bm);
+                        bm->cur.bit = 0;
                 } while (bb);
                 zone_bm = bm->cur.zone_bm->next;
                 if (zone_bm) {
                         bm->cur.zone_bm = zone_bm;
                         bm->cur.block = zone_bm->bm_blocks;
-                        memory_bm_reset_chunk(bm);
+                        bm->cur.bit = 0;
                 }
         } while (zone_bm);
         memory_bm_position_reset(bm);
         return BM_END_OF_MAP;
 
  Return_pfn:
-        bm->cur.chunk = chunk;
-        bm->cur.bit = bit;
-        return bb->start_pfn + chunk * BM_BITS_PER_CHUNK + bit;
+        bm->cur.bit = bit + 1;
+        return bb->start_pfn + bit;
 }
 
 /**
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a0abf9a463f9..80ccac849e46 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/genhd.h>
diff --git a/kernel/printk.c b/kernel/printk.c
index 07ad9e7f7a66..b51b1567bb55 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -933,7 +933,7 @@ void suspend_console(void)
 {
         if (!console_suspend_enabled)
                 return;
-        printk("Suspending console(s)\n");
+        printk("Suspending console(s) (use no_console_suspend to debug)\n");
         acquire_console_sem();
         console_suspended = 1;
 }
@@ -1308,29 +1308,18 @@ void tty_write_message(struct tty_struct *tty, char *msg)
 }
 
 #if defined CONFIG_PRINTK
+
 /*
  * printk rate limiting, lifted from the networking subsystem.
  *
- * This enforces a rate limit: not more than one kernel message
- * every printk_ratelimit_jiffies to make a denial-of-service
- * attack impossible.
+ * This enforces a rate limit: not more than 10 kernel messages
+ * every 5s to make a denial-of-service attack impossible.
  */
-int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst)
-{
-        return __ratelimit(ratelimit_jiffies, ratelimit_burst);
-}
-EXPORT_SYMBOL(__printk_ratelimit);
-
-/* minimum time in jiffies between messages */
-int printk_ratelimit_jiffies = 5 * HZ;
-
-/* number of messages we send before ratelimiting */
-int printk_ratelimit_burst = 10;
+DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
 
 int printk_ratelimit(void)
 {
-        return __printk_ratelimit(printk_ratelimit_jiffies,
-                                printk_ratelimit_burst);
+        return __ratelimit(&printk_ratelimit_state);
 }
 EXPORT_SYMBOL(printk_ratelimit);
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 58926411eb2a..cd26bed4cc26 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -112,8 +112,6 @@ void __init profile_init(void)
 
 /* Profile event notifications */
 
-#ifdef CONFIG_PROFILING
-
 static BLOCKING_NOTIFIER_HEAD(task_exit_notifier);
 static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
 static BLOCKING_NOTIFIER_HEAD(munmap_notifier);
@@ -203,8 +201,6 @@ void unregister_timer_hook(int (*hook)(struct pt_regs *))
 }
 EXPORT_SYMBOL_GPL(unregister_timer_hook);
 
-#endif /* CONFIG_PROFILING */
-
 
 #ifdef CONFIG_SMP
 /*
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 8392a9da6450..356699a96d56 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -107,7 +107,7 @@ int ptrace_check_attach(struct task_struct *child, int kill)
         read_unlock(&tasklist_lock);
 
         if (!ret && !kill)
-                wait_task_inactive(child);
+                ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
 
         /* All systems go.. */
         return ret;
@@ -140,7 +140,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
         if (!dumpable && !capable(CAP_SYS_PTRACE))
                 return -EPERM;
 
-        return security_ptrace(current, task, mode);
+        return security_ptrace_may_access(task, mode);
 }
 
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)
@@ -499,8 +499,7 @@ repeat:
                         goto repeat;
                 }
 
-                ret = security_ptrace(current->parent, current,
-                                      PTRACE_MODE_ATTACH);
+                ret = security_ptrace_traceme(current->parent);
 
                 /*
                  * Set the ptrace bit in the process ptrace flags.
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 16eeeaa9d618..aad93cdc9f68 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -91,8 +91,8 @@ static void force_quiescent_state(struct rcu_data *rdp,
                  * rdp->cpu is the current cpu.
                  *
                  * cpu_online_map is updated by the _cpu_down()
-                 * using stop_machine_run(). Since we're in irqs disabled
-                 * section, stop_machine_run() is not exectuting, hence
+                 * using __stop_machine(). Since we're in irqs disabled
+                 * section, __stop_machine() is not exectuting, hence
                  * the cpu_online_map is stable.
                  *
                  * However,  a cpu might have been offlined _just_ before
@@ -106,7 +106,7 @@ static void force_quiescent_state(struct rcu_data *rdp,
                  */
                 cpus_and(cpumask, rcp->cpumask, cpu_online_map);
                 cpu_clear(rdp->cpu, cpumask);
-                for_each_cpu_mask(cpu, cpumask)
+                for_each_cpu_mask_nr(cpu, cpumask)
                         smp_send_reschedule(cpu);
         }
 }
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index f14f372cf6f5..467d5940f624 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -77,6 +77,7 @@ void wakeme_after_rcu(struct rcu_head  *head)
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
+void synchronize_rcu(void);     /* Makes kernel-doc tools happy */
 synchronize_rcu_xxx(synchronize_rcu, call_rcu)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 6f62b77d93c4..27827931ca0d 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -756,7 +756,7 @@ rcu_try_flip_idle(void)
 
         /* Now ask each CPU for acknowledgement of the flip. */
 
-        for_each_cpu_mask(cpu, rcu_cpu_online_map) {
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
                 per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
                 dyntick_save_progress_counter(cpu);
         }
@@ -774,7 +774,7 @@ rcu_try_flip_waitack(void)
         int cpu;
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
-        for_each_cpu_mask(cpu, rcu_cpu_online_map)
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
                 if (rcu_try_flip_waitack_needed(cpu) &&
                     per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
                         RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
@@ -806,7 +806,7 @@ rcu_try_flip_waitzero(void)
         /* Check to see if the sum of the "last" counters is zero. */
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
-        for_each_cpu_mask(cpu, rcu_cpu_online_map)
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
                 sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
         if (sum != 0) {
                 RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
@@ -821,7 +821,7 @@ rcu_try_flip_waitzero(void)
         smp_mb();  /*  ^^^^^^^^^^^^ */
 
         /* Call for a memory barrier from each CPU. */
-        for_each_cpu_mask(cpu, rcu_cpu_online_map) {
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
                 per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
                 dyntick_save_progress_counter(cpu);
         }
@@ -841,7 +841,7 @@ rcu_try_flip_waitmb(void)
         int cpu;
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
-        for_each_cpu_mask(cpu, rcu_cpu_online_map)
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
                 if (rcu_try_flip_waitmb_needed(cpu) &&
                     per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
                         RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
diff --git a/kernel/relay.c b/kernel/relay.c
index 7de644cdec43..8d13a7855c08 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -407,6 +407,35 @@ void relay_reset(struct rchan *chan)
 }
 EXPORT_SYMBOL_GPL(relay_reset);
 
+static inline void relay_set_buf_dentry(struct rchan_buf *buf,
+                                        struct dentry *dentry)
+{
+        buf->dentry = dentry;
+        buf->dentry->d_inode->i_size = buf->early_bytes;
+}
+
+static struct dentry *relay_create_buf_file(struct rchan *chan,
+                                            struct rchan_buf *buf,
+                                            unsigned int cpu)
+{
+        struct dentry *dentry;
+        char *tmpname;
+
+        tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
+        if (!tmpname)
+                return NULL;
+        snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
+
+        /* Create file in fs */
+        dentry = chan->cb->create_buf_file(tmpname, chan->parent,
+                                           S_IRUSR, buf,
+                                           &chan->is_global);
+
+        kfree(tmpname);
+
+        return dentry;
+}
+
 /*
  *      relay_open_buf - create a new relay channel buffer
  *
@@ -416,45 +445,34 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 {
         struct rchan_buf *buf = NULL;
         struct dentry *dentry;
-        char *tmpname;
 
         if (chan->is_global)
                 return chan->buf[0];
 
-        tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
-        if (!tmpname)
-                goto end;
-        snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
-
         buf = relay_create_buf(chan);
         if (!buf)
-                goto free_name;
+                return NULL;
+
+        if (chan->has_base_filename) {
+                dentry = relay_create_buf_file(chan, buf, cpu);
+                if (!dentry)
+                        goto free_buf;
+                relay_set_buf_dentry(buf, dentry);
+        }
 
         buf->cpu = cpu;
         __relay_reset(buf, 1);
 
-        /* Create file in fs */
-        dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR,
-                                           buf, &chan->is_global);
-        if (!dentry)
-                goto free_buf;
-
-        buf->dentry = dentry;
-
         if(chan->is_global) {
                 chan->buf[0] = buf;
                 buf->cpu = 0;
         }
 
-        goto free_name;
+        return buf;
 
 free_buf:
         relay_destroy_buf(buf);
-        buf = NULL;
-free_name:
-        kfree(tmpname);
-end:
-        return buf;
+        return NULL;
 }
 
 /**
@@ -537,8 +555,8 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
 
 /**
  *      relay_open - create a new relay channel
- *      @base_filename: base name of files to create
- *      @parent: dentry of parent directory, %NULL for root directory
+ *      @base_filename: base name of files to create, %NULL for buffering only
+ *      @parent: dentry of parent directory, %NULL for root directory or buffer
  *      @subbuf_size: size of sub-buffers
  *      @n_subbufs: number of sub-buffers
  *      @cb: client callback functions
@@ -560,8 +578,6 @@ struct rchan *relay_open(const char *base_filename,
 {
         unsigned int i;
         struct rchan *chan;
-        if (!base_filename)
-                return NULL;
 
         if (!(subbuf_size && n_subbufs))
                 return NULL;
@@ -576,7 +592,10 @@ struct rchan *relay_open(const char *base_filename,
         chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs);
         chan->parent = parent;
         chan->private_data = private_data;
-        strlcpy(chan->base_filename, base_filename, NAME_MAX);
+        if (base_filename) {
+                chan->has_base_filename = 1;
+                strlcpy(chan->base_filename, base_filename, NAME_MAX);
+        }
         setup_callbacks(chan, cb);
         kref_init(&chan->kref);
 
@@ -604,6 +623,94 @@ free_bufs:
 }
 EXPORT_SYMBOL_GPL(relay_open);
 
+struct rchan_percpu_buf_dispatcher {
+        struct rchan_buf *buf;
+        struct dentry *dentry;
+};
+
+/* Called in atomic context. */
+static void __relay_set_buf_dentry(void *info)
+{
+        struct rchan_percpu_buf_dispatcher *p = info;
+
+        relay_set_buf_dentry(p->buf, p->dentry);
+}
+
+/**
+ *      relay_late_setup_files - triggers file creation
+ *      @chan: channel to operate on
+ *      @base_filename: base name of files to create
+ *      @parent: dentry of parent directory, %NULL for root directory
+ *
+ *      Returns 0 if successful, non-zero otherwise.
+ *
+ *      Use to setup files for a previously buffer-only channel.
+ *      Useful to do early tracing in kernel, before VFS is up, for example.
+ */
+int relay_late_setup_files(struct rchan *chan,
+                           const char *base_filename,
+                           struct dentry *parent)
+{
+        int err = 0;
+        unsigned int i, curr_cpu;
+        unsigned long flags;
+        struct dentry *dentry;
+        struct rchan_percpu_buf_dispatcher disp;
+
+        if (!chan || !base_filename)
+                return -EINVAL;
+
+        strlcpy(chan->base_filename, base_filename, NAME_MAX);
+
+        mutex_lock(&relay_channels_mutex);
+        /* Is chan already set up? */
+        if (unlikely(chan->has_base_filename))
+                return -EEXIST;
+        chan->has_base_filename = 1;
+        chan->parent = parent;
+        curr_cpu = get_cpu();
+        /*
+         * The CPU hotplug notifier ran before us and created buffers with
+         * no files associated. So it's safe to call relay_setup_buf_file()
+         * on all currently online CPUs.
+         */
+        for_each_online_cpu(i) {
+                if (unlikely(!chan->buf[i])) {
+                        printk(KERN_ERR "relay_late_setup_files: CPU %u "
+                                        "has no buffer, it must have!\n", i);
+                        BUG();
+                        err = -EINVAL;
+                        break;
+                }
+
+                dentry = relay_create_buf_file(chan, chan->buf[i], i);
+                if (unlikely(!dentry)) {
+                        err = -EINVAL;
+                        break;
+                }
+
+                if (curr_cpu == i) {
+                        local_irq_save(flags);
+                        relay_set_buf_dentry(chan->buf[i], dentry);
+                        local_irq_restore(flags);
+                } else {
+                        disp.buf = chan->buf[i];
+                        disp.dentry = dentry;
+                        smp_mb();
+                        /* relay_channels_mutex must be held, so wait. */
+                        err = smp_call_function_single(i,
+                                                       __relay_set_buf_dentry,
+                                                       &disp, 1);
+                }
+                if (unlikely(err))
+                        break;
+        }
+        put_cpu();
+        mutex_unlock(&relay_channels_mutex);
+
+        return err;
+}
+
 /**
  *      relay_switch_subbuf - switch to a new sub-buffer
  *      @buf: channel buffer
@@ -627,8 +734,13 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
                 old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
                 buf->padding[old_subbuf] = buf->prev_padding;
                 buf->subbufs_produced++;
-                buf->dentry->d_inode->i_size += buf->chan->subbuf_size -
-                        buf->padding[old_subbuf];
+                if (buf->dentry)
+                        buf->dentry->d_inode->i_size +=
+                                buf->chan->subbuf_size -
+                                buf->padding[old_subbuf];
+                else
+                        buf->early_bytes += buf->chan->subbuf_size -
+                                            buf->padding[old_subbuf];
                 smp_mb();
                 if (waitqueue_active(&buf->read_wait))
                         /*
@@ -832,6 +944,10 @@ static void relay_file_read_consume(struct rchan_buf *buf,
         size_t n_subbufs = buf->chan->n_subbufs;
         size_t read_subbuf;
 
+        if (buf->subbufs_produced == buf->subbufs_consumed &&
+            buf->offset == buf->bytes_consumed)
+                return;
+
         if (buf->bytes_consumed + bytes_consumed > subbuf_size) {
                 relay_subbufs_consumed(buf->chan, buf->cpu, 1);
                 buf->bytes_consumed = 0;
@@ -863,6 +979,8 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
 
         relay_file_read_consume(buf, read_pos, 0);
 
+        consumed = buf->subbufs_consumed;
+
         if (unlikely(buf->offset > subbuf_size)) {
                 if (produced == consumed)
                         return 0;
@@ -881,8 +999,12 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
         if (consumed > produced)
                 produced += n_subbufs * subbuf_size;
 
-        if (consumed == produced)
+        if (consumed == produced) {
+                if (buf->offset == subbuf_size &&
+                    buf->subbufs_produced > buf->subbufs_consumed)
+                        return 1;
                 return 0;
+        }
 
         return 1;
 }
@@ -1237,4 +1359,4 @@ static __init int relay_init(void)
         return 0;
 }
 
-module_init(relay_init);
+early_initcall(relay_init);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index d3c61b4ebef2..f275c8eca772 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/res_counter.h>
 #include <linux/uaccess.h>
+#include <linux/mm.h>
 
 void res_counter_init(struct res_counter *counter)
 {
@@ -102,44 +103,37 @@ u64 res_counter_read_u64(struct res_counter *counter, int member)
         return *res_counter_member(counter, member);
 }
 
-ssize_t res_counter_write(struct res_counter *counter, int member,
-                const char __user *userbuf, size_t nbytes, loff_t *pos,
-                int (*write_strategy)(char *st_buf, unsigned long long *val))
+int res_counter_memparse_write_strategy(const char *buf,
+                                        unsigned long long *res)
 {
-        int ret;
-        char *buf, *end;
-        unsigned long flags;
-        unsigned long long tmp, *val;
-
-        buf = kmalloc(nbytes + 1, GFP_KERNEL);
-        ret = -ENOMEM;
-        if (buf == NULL)
-                goto out;
+        char *end;
+        /* FIXME - make memparse() take const char* args */
+        *res = memparse((char *)buf, &end);
+        if (*end != '\0')
+                return -EINVAL;
 
-        buf[nbytes] = '\0';
-        ret = -EFAULT;
-        if (copy_from_user(buf, userbuf, nbytes))
-                goto out_free;
+        *res = PAGE_ALIGN(*res);
+        return 0;
+}
 
-        ret = -EINVAL;
+int res_counter_write(struct res_counter *counter, int member,
+                      const char *buf, write_strategy_fn write_strategy)
+{
+        char *end;
+        unsigned long flags;
+        unsigned long long tmp, *val;
 
-        strstrip(buf);
         if (write_strategy) {
-                if (write_strategy(buf, &tmp)) {
-                        goto out_free;
-                }
+                if (write_strategy(buf, &tmp))
+                        return -EINVAL;
         } else {
                 tmp = simple_strtoull(buf, &end, 10);
                 if (*end != '\0')
-                        goto out_free;
+                        return -EINVAL;
         }
         spin_lock_irqsave(&counter->lock, flags);
         val = res_counter_member(counter, member);
         *val = tmp;
         spin_unlock_irqrestore(&counter->lock, flags);
-        ret = nbytes;
-out_free:
-        kfree(buf);
-out:
-        return ret;
+        return 0;
 }
diff --git a/kernel/resource.c b/kernel/resource.c
index 74af2d7cb5a1..03d796c1b2e9 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -362,35 +362,21 @@ int allocate_resource(struct resource *root, struct resource *new,
 
 EXPORT_SYMBOL(allocate_resource);
 
-/**
- * insert_resource - Inserts a resource in the resource tree
- * @parent: parent of the new resource
- * @new: new resource to insert
- *
- * Returns 0 on success, -EBUSY if the resource can't be inserted.
- *
- * This function is equivalent to request_resource when no conflict
- * happens. If a conflict happens, and the conflicting resources
- * entirely fit within the range of the new resource, then the new
- * resource is inserted and the conflicting resources become children of
- * the new resource.
+/*
+ * Insert a resource into the resource tree. If successful, return NULL,
+ * otherwise return the conflicting resource (compare to __request_resource())
  */
-int insert_resource(struct resource *parent, struct resource *new)
+static struct resource * __insert_resource(struct resource *parent, struct resource *new)
 {
-        int result;
         struct resource *first, *next;
 
-        write_lock(&resource_lock);
-
         for (;; parent = first) {
-                result = 0;
                 first = __request_resource(parent, new);
                 if (!first)
-                        goto out;
+                        return first;
 
-                result = -EBUSY;
                 if (first == parent)
-                        goto out;
+                        return first;
 
                 if ((first->start > new->start) || (first->end < new->end))
                         break;
@@ -401,15 +387,13 @@ int insert_resource(struct resource *parent, struct resource *new)
         for (next = first; ; next = next->sibling) {
                 /* Partial overlap? Bad, and unfixable */
                 if (next->start < new->start || next->end > new->end)
-                        goto out;
+                        return next;
                 if (!next->sibling)
                         break;
                 if (next->sibling->start > new->end)
                         break;
         }
 
-        result = 0;
-
         new->parent = parent;
         new->sibling = next->sibling;
         new->child = first;
@@ -426,10 +410,64 @@ int insert_resource(struct resource *parent, struct resource *new)
                         next = next->sibling;
                 next->sibling = new;
         }
+        return NULL;
+}
 
- out:
+/**
+ * insert_resource - Inserts a resource in the resource tree
+ * @parent: parent of the new resource
+ * @new: new resource to insert
+ *
+ * Returns 0 on success, -EBUSY if the resource can't be inserted.
+ *
+ * This function is equivalent to request_resource when no conflict
+ * happens. If a conflict happens, and the conflicting resources
+ * entirely fit within the range of the new resource, then the new
+ * resource is inserted and the conflicting resources become children of
+ * the new resource.
+ */
+int insert_resource(struct resource *parent, struct resource *new)
+{
+        struct resource *conflict;
+
+        write_lock(&resource_lock);
+        conflict = __insert_resource(parent, new);
+        write_unlock(&resource_lock);
+        return conflict ? -EBUSY : 0;
+}
+
+/**
+ * insert_resource_expand_to_fit - Insert a resource into the resource tree
+ * @root: root resource descriptor
+ * @new: new resource to insert
+ *
+ * Insert a resource into the resource tree, possibly expanding it in order
+ * to make it encompass any conflicting resources.
+ */
+void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
+{
+        if (new->parent)
+                return;
+
+        write_lock(&resource_lock);
+        for (;;) {
+                struct resource *conflict;
+
+                conflict = __insert_resource(root, new);
+                if (!conflict)
+                        break;
+                if (conflict == root)
+                        break;
+
+                /* Ok, expand resource to cover the conflict, then try again .. */
+                if (conflict->start < new->start)
+                        new->start = conflict->start;
+                if (conflict->end > new->end)
+                        new->end = conflict->end;
+
+                printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
+        }
         write_unlock(&resource_lock);
-        return result;
 }
 
 /**
@@ -490,7 +528,7 @@ resource_size_t resource_alignment(struct resource *res)
 {
         switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) {
         case IORESOURCE_SIZEALIGN:
-                return res->end - res->start + 1;
+                return resource_size(res);
         case IORESOURCE_STARTALIGN:
                 return res->start;
         default:
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 092e4c620af9..a56f629b057a 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -297,8 +297,8 @@ static int test_func(void *data)
  *
  * opcode:data
  */
-static ssize_t sysfs_test_command(struct sys_device *dev, const char *buf,
-                                  size_t count)
+static ssize_t sysfs_test_command(struct sys_device *dev, struct sysdev_attribute *attr,
+                                  const char *buf, size_t count)
 {
         struct sched_param schedpar;
         struct test_thread_data *td;
@@ -360,7 +360,8 @@ static ssize_t sysfs_test_command(struct sys_device *dev, const char *buf,
  * @dev:        thread to query
  * @buf:        char buffer to be filled with thread status info
  */
-static ssize_t sysfs_test_status(struct sys_device *dev, char *buf)
+static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute *attr,
+                                 char *buf)
 {
         struct test_thread_data *td;
         struct task_struct *tsk;
diff --git a/kernel/sched.c b/kernel/sched.c
index 99e6d850ecab..13dd2db9fb2d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -571,8 +571,10 @@ struct rq {
 #endif
 
 #ifdef CONFIG_SCHED_HRTICK
-        unsigned long hrtick_flags;
-        ktime_t hrtick_expire;
+#ifdef CONFIG_SMP
+        int hrtick_csd_pending;
+        struct call_single_data hrtick_csd;
+#endif
         struct hrtimer hrtick_timer;
 #endif
 
@@ -598,7 +600,6 @@ struct rq {
         /* BKL stats */
         unsigned int bkl_count;
 #endif
-        struct lock_class_key rq_lock_key;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -807,9 +808,9 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
 /*
  * ratelimit for updating the group shares.
- * default: 0.5ms
+ * default: 0.25ms
  */
-const_debug unsigned int sysctl_sched_shares_ratelimit = 500000;
+unsigned int sysctl_sched_shares_ratelimit = 250000;
 
 /*
  * period over which we measure -rt task cpu usage in us.
@@ -832,7 +833,7 @@ static inline u64 global_rt_period(void)
 
 static inline u64 global_rt_runtime(void)
 {
-        if (sysctl_sched_rt_period < 0)
+        if (sysctl_sched_rt_runtime < 0)
                 return RUNTIME_INF;
 
         return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
@@ -983,13 +984,6 @@ static struct rq *this_rq_lock(void)
         return rq;
 }
 
-static void __resched_task(struct task_struct *p, int tif_bit);
-
-static inline void resched_task(struct task_struct *p)
-{
-        __resched_task(p, TIF_NEED_RESCHED);
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
@@ -1001,25 +995,6 @@ static inline void resched_task(struct task_struct *p)
  * When we get rescheduled we reprogram the hrtick_timer outside of the
  * rq->lock.
  */
-static inline void resched_hrt(struct task_struct *p)
-{
-        __resched_task(p, TIF_HRTICK_RESCHED);
-}
-
-static inline void resched_rq(struct rq *rq)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&rq->lock, flags);
-        resched_task(rq->curr);
-        spin_unlock_irqrestore(&rq->lock, flags);
-}
-
-enum {
-        HRTICK_SET,             /* re-programm hrtick_timer */
-        HRTICK_RESET,           /* not a new slice */
-        HRTICK_BLOCK,           /* stop hrtick operations */
-};
 
 /*
  * Use hrtick when:
@@ -1030,40 +1005,11 @@ static inline int hrtick_enabled(struct rq *rq)
 {
         if (!sched_feat(HRTICK))
                 return 0;
-        if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags)))
+        if (!cpu_active(cpu_of(rq)))
                 return 0;
         return hrtimer_is_hres_active(&rq->hrtick_timer);
 }
 
-/*
- * Called to set the hrtick timer state.
- *
- * called with rq->lock held and irqs disabled
- */
-static void hrtick_start(struct rq *rq, u64 delay, int reset)
-{
-        assert_spin_locked(&rq->lock);
-
-        /*
-         * preempt at: now + delay
-         */
-        rq->hrtick_expire =
-                ktime_add_ns(rq->hrtick_timer.base->get_time(), delay);
-        /*
-         * indicate we need to program the timer
-         */
-        __set_bit(HRTICK_SET, &rq->hrtick_flags);
-        if (reset)
-                __set_bit(HRTICK_RESET, &rq->hrtick_flags);
-
-        /*
-         * New slices are called from the schedule path and don't need a
-         * forced reschedule.
-         */
-        if (reset)
-                resched_hrt(rq->curr);
-}
-
 static void hrtick_clear(struct rq *rq)
 {
         if (hrtimer_active(&rq->hrtick_timer))
@@ -1071,32 +1017,6 @@ static void hrtick_clear(struct rq *rq)
 }
 
 /*
- * Update the timer from the possible pending state.
- */
-static void hrtick_set(struct rq *rq)
-{
-        ktime_t time;
-        int set, reset;
-        unsigned long flags;
-
-        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-
-        spin_lock_irqsave(&rq->lock, flags);
-        set = __test_and_clear_bit(HRTICK_SET, &rq->hrtick_flags);
-        reset = __test_and_clear_bit(HRTICK_RESET, &rq->hrtick_flags);
-        time = rq->hrtick_expire;
-        clear_thread_flag(TIF_HRTICK_RESCHED);
-        spin_unlock_irqrestore(&rq->lock, flags);
-
-        if (set) {
-                hrtimer_start(&rq->hrtick_timer, time, HRTIMER_MODE_ABS);
-                if (reset && !hrtimer_active(&rq->hrtick_timer))
-                        resched_rq(rq);
-        } else
-                hrtick_clear(rq);
-}
-
-/*
  * High-resolution timer tick.
  * Runs from hardirq context with interrupts disabled.
  */
@@ -1115,27 +1035,37 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 }
 
 #ifdef CONFIG_SMP
-static void hotplug_hrtick_disable(int cpu)
+/*
+ * called from hardirq (IPI) context
+ */
+static void __hrtick_start(void *arg)
 {
-        struct rq *rq = cpu_rq(cpu);
-        unsigned long flags;
+        struct rq *rq = arg;
 
-        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);
+        spin_lock(&rq->lock);
+        hrtimer_restart(&rq->hrtick_timer);
+        rq->hrtick_csd_pending = 0;
+        spin_unlock(&rq->lock);
 }
 
-static void hotplug_hrtick_enable(int cpu)
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay)
 {
-        struct rq *rq = cpu_rq(cpu);
-        unsigned long flags;
+        struct hrtimer *timer = &rq->hrtick_timer;
+        ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
 
-        spin_lock_irqsave(&rq->lock, flags);
-        __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags);
-        spin_unlock_irqrestore(&rq->lock, flags);
+        timer->expires = time;
+
+        if (rq == this_rq()) {
+                hrtimer_restart(timer);
+        } else if (!rq->hrtick_csd_pending) {
+                __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+                rq->hrtick_csd_pending = 1;
+        }
 }
 
 static int
@@ -1150,66 +1080,56 @@ hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
         case CPU_DOWN_PREPARE_FROZEN:
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                hotplug_hrtick_disable(cpu);
-                return NOTIFY_OK;
-
-        case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
-        case CPU_DOWN_FAILED:
-        case CPU_DOWN_FAILED_FROZEN:
-        case CPU_ONLINE:
-        case CPU_ONLINE_FROZEN:
-                hotplug_hrtick_enable(cpu);
+                hrtick_clear(cpu_rq(cpu));
                 return NOTIFY_OK;
         }
 
         return NOTIFY_DONE;
 }
 
-static void init_hrtick(void)
+static __init void init_hrtick(void)
 {
         hotcpu_notifier(hotplug_hrtick, 0);
 }
-#endif /* CONFIG_SMP */
+#else
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay)
+{
+        hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+}
 
-static void init_rq_hrtick(struct rq *rq)
+static void init_hrtick(void)
 {
-        rq->hrtick_flags = 0;
-        hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-        rq->hrtick_timer.function = hrtick;
-        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
 }
+#endif /* CONFIG_SMP */
 
-void hrtick_resched(void)
+static void init_rq_hrtick(struct rq *rq)
 {
-        struct rq *rq;
-        unsigned long flags;
+#ifdef CONFIG_SMP
+        rq->hrtick_csd_pending = 0;
 
-        if (!test_thread_flag(TIF_HRTICK_RESCHED))
-                return;
+        rq->hrtick_csd.flags = 0;
+        rq->hrtick_csd.func = __hrtick_start;
+        rq->hrtick_csd.info = rq;
+#endif
 
-        local_irq_save(flags);
-        rq = cpu_rq(smp_processor_id());
-        hrtick_set(rq);
-        local_irq_restore(flags);
+        hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+        rq->hrtick_timer.function = hrtick;
+        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
 }
 #else
 static inline void hrtick_clear(struct rq *rq)
 {
 }
 
-static inline void hrtick_set(struct rq *rq)
-{
-}
-
 static inline void init_rq_hrtick(struct rq *rq)
 {
 }
 
-void hrtick_resched(void)
-{
-}
-
 static inline void init_hrtick(void)
 {
 }
@@ -1228,16 +1148,16 @@ static inline void init_hrtick(void)
 #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
 #endif
 
-static void __resched_task(struct task_struct *p, int tif_bit)
+static void resched_task(struct task_struct *p)
 {
         int cpu;
 
         assert_spin_locked(&task_rq(p)->lock);
 
-        if (unlikely(test_tsk_thread_flag(p, tif_bit)))
+        if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
                 return;
 
-        set_tsk_thread_flag(p, tif_bit);
+        set_tsk_thread_flag(p, TIF_NEED_RESCHED);
 
         cpu = task_cpu(p);
         if (cpu == smp_processor_id())
@@ -1303,10 +1223,10 @@ void wake_up_idle_cpu(int cpu)
 #endif /* CONFIG_NO_HZ */
 
 #else /* !CONFIG_SMP */
-static void __resched_task(struct task_struct *p, int tif_bit)
+static void resched_task(struct task_struct *p)
 {
         assert_spin_locked(&task_rq(p)->lock);
-        set_tsk_thread_flag(p, tif_bit);
+        set_tsk_need_resched(p);
 }
 #endif /* CONFIG_SMP */
 
@@ -1946,16 +1866,24 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
+ * If @match_state is nonzero, it's the @p->state value just checked and
+ * not expected to change.  If it changes, i.e. @p might have woken up,
+ * then return zero.  When we succeed in waiting for @p to be off its CPU,
+ * we return a positive number (its total switch count).  If a second call
+ * a short while later returns the same number, the caller can be sure that
+ * @p has remained unscheduled the whole time.
+ *
  * The caller must ensure that the task *will* unschedule sometime soon,
  * else this function might spin for a *long* time. This function can't
  * be called with interrupts off, or it may introduce deadlock with
  * smp_call_function() if an IPI is sent by the same process we are
  * waiting to become inactive.
  */
-void wait_task_inactive(struct task_struct *p)
+unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
         unsigned long flags;
         int running, on_rq;
+        unsigned long ncsw;
         struct rq *rq;
 
         for (;;) {
@@ -1978,8 +1906,11 @@ void wait_task_inactive(struct task_struct *p)
                  * return false if the runqueue has changed and p
                  * is actually now running somewhere else!
                  */
-                while (task_running(rq, p))
+                while (task_running(rq, p)) {
+                        if (match_state && unlikely(p->state != match_state))
+                                return 0;
                         cpu_relax();
+                }
 
                 /*
                  * Ok, time to look more closely! We need the rq
@@ -1989,9 +1920,21 @@ void wait_task_inactive(struct task_struct *p)
                 rq = task_rq_lock(p, &flags);
                 running = task_running(rq, p);
                 on_rq = p->se.on_rq;
+                ncsw = 0;
+                if (!match_state || p->state == match_state) {
+                        ncsw = p->nivcsw + p->nvcsw;
+                        if (unlikely(!ncsw))
+                                ncsw = 1;
+                }
                 task_rq_unlock(rq, &flags);
 
                 /*
+                 * If it changed from the expected state, bail out now.
+                 */
+                if (unlikely(!ncsw))
+                        break;
+
+                /*
                  * Was it really running after all now that we
                  * checked with the proper locks actually held?
                  *
@@ -2023,6 +1966,8 @@ void wait_task_inactive(struct task_struct *p)
                  */
                 break;
         }
+
+        return ncsw;
 }
 
 /***
@@ -2108,7 +2053,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
                 /* Tally up the load of all CPUs in the group */
                 avg_load = 0;
 
-                for_each_cpu_mask(i, group->cpumask) {
+                for_each_cpu_mask_nr(i, group->cpumask) {
                         /* Bias balancing toward cpus of our domain */
                         if (local_group)
                                 load = source_load(i, load_idx);
@@ -2150,7 +2095,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu,
         /* Traverse only the allowed CPUs */
         cpus_and(*tmp, group->cpumask, p->cpus_allowed);
 
-        for_each_cpu_mask(i, *tmp) {
+        for_each_cpu_mask_nr(i, *tmp) {
                 load = weighted_cpuload(i);
 
                 if (load < min_load || (load == min_load && i == this_cpu)) {
@@ -2813,10 +2758,10 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
         } else {
                 if (rq1 < rq2) {
                         spin_lock(&rq1->lock);
-                        spin_lock(&rq2->lock);
+                        spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
                 } else {
                         spin_lock(&rq2->lock);
-                        spin_lock(&rq1->lock);
+                        spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                 }
         }
         update_rq_clock(rq1);
@@ -2859,14 +2804,21 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
                 if (busiest < this_rq) {
                         spin_unlock(&this_rq->lock);
                         spin_lock(&busiest->lock);
-                        spin_lock(&this_rq->lock);
+                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
                         ret = 1;
                 } else
-                        spin_lock(&busiest->lock);
+                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
         }
         return ret;
 }
 
+static void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+        __releases(busiest->lock)
+{
+        spin_unlock(&busiest->lock);
+        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
+
 /*
  * If dest_cpu is allowed for this process, migrate the task to it.
  * This is accomplished by forcing the cpu_allowed mask to only
@@ -2881,7 +2833,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 
         rq = task_rq_lock(p, &flags);
         if (!cpu_isset(dest_cpu, p->cpus_allowed)
-            || unlikely(cpu_is_offline(dest_cpu)))
+            || unlikely(!cpu_active(dest_cpu)))
                 goto out;
 
         /* force the process onto the specified CPU */
@@ -3168,7 +3120,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
                 max_cpu_load = 0;
                 min_cpu_load = ~0UL;
 
-                for_each_cpu_mask(i, group->cpumask) {
+                for_each_cpu_mask_nr(i, group->cpumask) {
                         struct rq *rq;
 
                         if (!cpu_isset(i, *cpus))
@@ -3447,7 +3399,7 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
         unsigned long max_load = 0;
         int i;
 
-        for_each_cpu_mask(i, group->cpumask) {
+        for_each_cpu_mask_nr(i, group->cpumask) {
                 unsigned long wl;
 
                 if (!cpu_isset(i, *cpus))
@@ -3691,7 +3643,7 @@ redo:
                 ld_moved = move_tasks(this_rq, this_cpu, busiest,
                                         imbalance, sd, CPU_NEWLY_IDLE,
                                         &all_pinned);
-                spin_unlock(&busiest->lock);
+                double_unlock_balance(this_rq, busiest);
 
                 if (unlikely(all_pinned)) {
                         cpu_clear(cpu_of(busiest), *cpus);
@@ -3806,7 +3758,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
                 else
                         schedstat_inc(sd, alb_failed);
         }
-        spin_unlock(&target_rq->lock);
+        double_unlock_balance(busiest_rq, target_rq);
 }
 
 #ifdef CONFIG_NO_HZ
@@ -3849,7 +3801,7 @@ int select_nohz_load_balancer(int stop_tick)
                 /*
                  * If we are going offline and still the leader, give up!
                  */
-                if (cpu_is_offline(cpu) &&
+                if (!cpu_active(cpu) &&
                     atomic_read(&nohz.load_balancer) == cpu) {
                         if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
                                 BUG();
@@ -3989,7 +3941,7 @@ static void run_rebalance_domains(struct softirq_action *h)
                 int balance_cpu;
 
                 cpu_clear(this_cpu, cpus);
-                for_each_cpu_mask(balance_cpu, cpus) {
+                for_each_cpu_mask_nr(balance_cpu, cpus) {
                         /*
                          * If this cpu gets work to do, stop the load balancing
                          * work being done for other cpus. Next load
@@ -4125,6 +4077,8 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
                 cpustat->nice = cputime64_add(cpustat->nice, tmp);
         else
                 cpustat->user = cputime64_add(cpustat->user, tmp);
+        /* Account for user time used */
+        acct_update_integrals(p);
 }
 
 /*
@@ -4225,6 +4179,65 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 }
 
 /*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+cputime_t task_utime(struct task_struct *p)
+{
+        return p->utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+        return p->stime;
+}
+#else
+cputime_t task_utime(struct task_struct *p)
+{
+        clock_t utime = cputime_to_clock_t(p->utime),
+                total = utime + cputime_to_clock_t(p->stime);
+        u64 temp;
+
+        /*
+         * Use CFS's precise accounting:
+         */
+        temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+
+        if (total) {
+                temp *= utime;
+                do_div(temp, total);
+        }
+        utime = (clock_t)temp;
+
+        p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
+        return p->prev_utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+        clock_t stime;
+
+        /*
+         * Use CFS's precise accounting. (we subtract utime from
+         * the total, to make sure the total observed by userspace
+         * grows monotonically - apps rely on that):
+         */
+        stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
+                        cputime_to_clock_t(task_utime(p));
+
+        if (stime >= 0)
+                p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+
+        return p->prev_stime;
+}
+#endif
+
+inline cputime_t task_gtime(struct task_struct *p)
+{
+        return p->gtime;
+}
+
+/*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
  *
@@ -4395,7 +4408,7 @@ asmlinkage void __sched schedule(void)
         struct task_struct *prev, *next;
         unsigned long *switch_count;
         struct rq *rq;
-        int cpu, hrtick = sched_feat(HRTICK);
+        int cpu;
 
 need_resched:
         preempt_disable();
@@ -4410,7 +4423,7 @@ need_resched_nonpreemptible:
 
         schedule_debug(prev);
 
-        if (hrtick)
+        if (sched_feat(HRTICK))
                 hrtick_clear(rq);
 
         /*
@@ -4457,9 +4470,6 @@ need_resched_nonpreemptible:
         } else
                 spin_unlock_irq(&rq->lock);
 
-        if (hrtick)
-                hrtick_set(rq);
-
         if (unlikely(reacquire_kernel_lock(current) < 0))
                 goto need_resched_nonpreemptible;
 
@@ -4718,6 +4728,52 @@ int __sched wait_for_completion_killable(struct completion *x)
 }
 EXPORT_SYMBOL(wait_for_completion_killable);
 
+/**
+ *      try_wait_for_completion - try to decrement a completion without blocking
+ *      @x:     completion structure
+ *
+ *      Returns: 0 if a decrement cannot be done without blocking
+ *               1 if a decrement succeeded.
+ *
+ *      If a completion is being used as a counting completion,
+ *      attempt to decrement the counter without blocking. This
+ *      enables us to avoid waiting if the resource the completion
+ *      is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+        int ret = 1;
+
+        spin_lock_irq(&x->wait.lock);
+        if (!x->done)
+                ret = 0;
+        else
+                x->done--;
+        spin_unlock_irq(&x->wait.lock);
+        return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *      completion_done - Test to see if a completion has any waiters
+ *      @x:     completion structure
+ *
+ *      Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *               1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+        int ret = 1;
+
+        spin_lock_irq(&x->wait.lock);
+        if (!x->done)
+                ret = 0;
+        spin_unlock_irq(&x->wait.lock);
+        return ret;
+}
+EXPORT_SYMBOL(completion_done);
+
 static long __sched
 sleep_on_common(wait_queue_head_t *q, int state, long timeout)
 {
@@ -5059,19 +5115,21 @@ recheck:
                         return -EPERM;
         }
 
+        if (user) {
 #ifdef CONFIG_RT_GROUP_SCHED
-        /*
-         * Do not allow realtime tasks into groups that have no runtime
-         * assigned.
-         */
-        if (user
-            && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
-                return -EPERM;
+                /*
+                 * Do not allow realtime tasks into groups that have no runtime
+                 * assigned.
+                 */
+                if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+                        return -EPERM;
 #endif
 
-        retval = security_task_setscheduler(p, policy, param);
-        if (retval)
-                return retval;
+                retval = security_task_setscheduler(p, policy, param);
+                if (retval)
+                        return retval;
+        }
+
         /*
          * make sure no PI-waiters arrive (or leave) while we are
          * changing the priority of the task:
@@ -5787,6 +5845,8 @@ static inline void sched_init_granularity(void)
                 sysctl_sched_latency = limit;
 
         sysctl_sched_wakeup_granularity *= factor;
+
+        sysctl_sched_shares_ratelimit *= factor;
 }
 
 #ifdef CONFIG_SMP
@@ -5876,7 +5936,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
         struct rq *rq_dest, *rq_src;
         int ret = 0, on_rq;
 
-        if (unlikely(cpu_is_offline(dest_cpu)))
+        if (unlikely(!cpu_active(dest_cpu)))
                 return ret;
 
         rq_src = cpu_rq(src_cpu);
@@ -6469,7 +6529,7 @@ static struct notifier_block __cpuinitdata migration_notifier = {
         .priority = 10
 };
 
-void __init migration_init(void)
+static int __init migration_init(void)
 {
         void *cpu = (void *)(long)smp_processor_id();
         int err;
@@ -6479,7 +6539,10 @@ void __init migration_init(void)
         BUG_ON(err == NOTIFY_BAD);
         migration_call(&migration_notifier, CPU_ONLINE, cpu);
         register_cpu_notifier(&migration_notifier);
+
+        return err;
 }
+early_initcall(migration_init);
 #endif
 
 #ifdef CONFIG_SMP
@@ -6768,7 +6831,8 @@ static cpumask_t cpu_isolated_map = CPU_MASK_NONE;
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
-        int ints[NR_CPUS], i;
+        static int __initdata ints[NR_CPUS];
+        int i;
 
         str = get_options(str, ARRAY_SIZE(ints), ints);
         cpus_clear(cpu_isolated_map);
@@ -6802,7 +6866,7 @@ init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
 
         cpus_clear(*covered);
 
-        for_each_cpu_mask(i, *span) {
+        for_each_cpu_mask_nr(i, *span) {
                 struct sched_group *sg;
                 int group = group_fn(i, cpu_map, &sg, tmpmask);
                 int j;
@@ -6813,7 +6877,7 @@ init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
                 cpus_clear(sg->cpumask);
                 sg->__cpu_power = 0;
 
-                for_each_cpu_mask(j, *span) {
+                for_each_cpu_mask_nr(j, *span) {
                         if (group_fn(j, cpu_map, NULL, tmpmask) != group)
                                 continue;
 
@@ -7013,7 +7077,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
         if (!sg)
                 return;
         do {
-                for_each_cpu_mask(j, sg->cpumask) {
+                for_each_cpu_mask_nr(j, sg->cpumask) {
                         struct sched_domain *sd;
 
                         sd = &per_cpu(phys_domains, j);
@@ -7038,7 +7102,7 @@ static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
 {
         int cpu, i;
 
-        for_each_cpu_mask(cpu, *cpu_map) {
+        for_each_cpu_mask_nr(cpu, *cpu_map) {
                 struct sched_group **sched_group_nodes
                         = sched_group_nodes_bycpu[cpu];
 
@@ -7277,7 +7341,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
         /*
          * Set up domains for cpus specified by the cpu_map.
          */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = NULL, *p;
                 SCHED_CPUMASK_VAR(nodemask, allmasks);
 
@@ -7344,7 +7408,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_SMT
         /* Set up CPU (sibling) groups */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 SCHED_CPUMASK_VAR(this_sibling_map, allmasks);
                 SCHED_CPUMASK_VAR(send_covered, allmasks);
 
@@ -7361,7 +7425,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_MC
         /* Set up multi-core groups */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 SCHED_CPUMASK_VAR(this_core_map, allmasks);
                 SCHED_CPUMASK_VAR(send_covered, allmasks);
 
@@ -7428,7 +7492,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                         goto error;
                 }
                 sched_group_nodes[i] = sg;
-                for_each_cpu_mask(j, *nodemask) {
+                for_each_cpu_mask_nr(j, *nodemask) {
                         struct sched_domain *sd;
 
                         sd = &per_cpu(node_domains, j);
@@ -7474,21 +7538,21 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
         /* Calculate CPU power for physical packages and nodes */
 #ifdef CONFIG_SCHED_SMT
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = &per_cpu(cpu_domains, i);
 
                 init_sched_groups_power(i, sd);
         }
 #endif
 #ifdef CONFIG_SCHED_MC
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = &per_cpu(core_domains, i);
 
                 init_sched_groups_power(i, sd);
         }
 #endif
 
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = &per_cpu(phys_domains, i);
 
                 init_sched_groups_power(i, sd);
@@ -7508,7 +7572,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 #endif
 
         /* Attach the domains */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd;
 #ifdef CONFIG_SCHED_SMT
                 sd = &per_cpu(cpu_domains, i);
@@ -7553,18 +7617,6 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
 }
 
 /*
- * Free current domain masks.
- * Called after all cpus are attached to NULL domain.
- */
-static void free_sched_domains(void)
-{
-        ndoms_cur = 0;
-        if (doms_cur != &fallback_doms)
-                kfree(doms_cur);
-        doms_cur = &fallback_doms;
-}
-
-/*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
@@ -7603,7 +7655,7 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
 
         unregister_sched_domain_sysctl();
 
-        for_each_cpu_mask(i, *cpu_map)
+        for_each_cpu_mask_nr(i, *cpu_map)
                 cpu_attach_domain(NULL, &def_root_domain, i);
         synchronize_sched();
         arch_destroy_sched_domains(cpu_map, &tmpmask);
@@ -7642,30 +7694,29 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * ownership of it and will kfree it when done with it. If the caller
  * failed the kmalloc call, then it can pass in doms_new == NULL,
  * and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms'.
+ * 'fallback_doms', it also forces the domains to be rebuilt.
+ *
+ * If doms_new==NULL it will be replaced with cpu_online_map.
+ * ndoms_new==0 is a special case for destroying existing domains.
+ * It will not create the default domain.
  *
  * Call with hotplug lock held
  */
 void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
                              struct sched_domain_attr *dattr_new)
 {
-        int i, j;
+        int i, j, n;
 
         mutex_lock(&sched_domains_mutex);
 
         /* always unregister in case we don't destroy any domains */
         unregister_sched_domain_sysctl();
 
-        if (doms_new == NULL) {
-                ndoms_new = 1;
-                doms_new = &fallback_doms;
-                cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
-                dattr_new = NULL;
-        }
+        n = doms_new ? ndoms_new : 0;
 
         /* Destroy deleted domains */
         for (i = 0; i < ndoms_cur; i++) {
-                for (j = 0; j < ndoms_new; j++) {
+                for (j = 0; j < n; j++) {
                         if (cpus_equal(doms_cur[i], doms_new[j])
                             && dattrs_equal(dattr_cur, i, dattr_new, j))
                                 goto match1;
@@ -7676,6 +7727,13 @@ match1:
                 ;
         }
 
+        if (doms_new == NULL) {
+                ndoms_cur = 0;
+                doms_new = &fallback_doms;
+                cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+                dattr_new = NULL;
+        }
+
         /* Build new domains */
         for (i = 0; i < ndoms_new; i++) {
                 for (j = 0; j < ndoms_cur; j++) {
@@ -7706,17 +7764,15 @@ match2:
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
 int arch_reinit_sched_domains(void)
 {
-        int err;
-
         get_online_cpus();
-        mutex_lock(&sched_domains_mutex);
-        detach_destroy_domains(&cpu_online_map);
-        free_sched_domains();
-        err = arch_init_sched_domains(&cpu_online_map);
-        mutex_unlock(&sched_domains_mutex);
+
+        /* Destroy domains first to force the rebuild */
+        partition_sched_domains(0, NULL, NULL);
+
+        rebuild_sched_domains();
         put_online_cpus();
 
-        return err;
+        return 0;
 }
 
 static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
@@ -7737,30 +7793,34 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 }
 
 #ifdef CONFIG_SCHED_MC
-static ssize_t sched_mc_power_savings_show(struct sys_device *dev, char *page)
+static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
+                                           char *page)
 {
         return sprintf(page, "%u\n", sched_mc_power_savings);
 }
-static ssize_t sched_mc_power_savings_store(struct sys_device *dev,
+static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
                                             const char *buf, size_t count)
 {
         return sched_power_savings_store(buf, count, 0);
 }
-static SYSDEV_ATTR(sched_mc_power_savings, 0644, sched_mc_power_savings_show,
-                   sched_mc_power_savings_store);
+static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
+                         sched_mc_power_savings_show,
+                         sched_mc_power_savings_store);
 #endif
 
 #ifdef CONFIG_SCHED_SMT
-static ssize_t sched_smt_power_savings_show(struct sys_device *dev, char *page)
+static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
+                                            char *page)
 {
         return sprintf(page, "%u\n", sched_smt_power_savings);
 }
-static ssize_t sched_smt_power_savings_store(struct sys_device *dev,
+static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
                                              const char *buf, size_t count)
 {
         return sched_power_savings_store(buf, count, 1);
 }
-static SYSDEV_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_show,
+static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
+                   sched_smt_power_savings_show,
                    sched_smt_power_savings_store);
 #endif
 
@@ -7782,59 +7842,49 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
+#ifndef CONFIG_CPUSETS
 /*
- * Force a reinitialization of the sched domains hierarchy. The domains
- * and groups cannot be updated in place without racing with the balancing
- * code, so we temporarily attach all running cpus to the NULL domain
- * which will prevent rebalancing while the sched domains are recalculated.
+ * Add online and remove offline CPUs from the scheduler domains.
+ * When cpusets are enabled they take over this function.
  */
 static int update_sched_domains(struct notifier_block *nfb,
                                 unsigned long action, void *hcpu)
 {
+        switch (action) {
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                partition_sched_domains(1, NULL, NULL);
+                return NOTIFY_OK;
+
+        default:
+                return NOTIFY_DONE;
+        }
+}
+#endif
+
+static int update_runtime(struct notifier_block *nfb,
+                                unsigned long action, void *hcpu)
+{
         int cpu = (int)(long)hcpu;
 
         switch (action) {
         case CPU_DOWN_PREPARE:
         case CPU_DOWN_PREPARE_FROZEN:
                 disable_runtime(cpu_rq(cpu));
-                /* fall-through */
-        case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
-                detach_destroy_domains(&cpu_online_map);
-                free_sched_domains();
                 return NOTIFY_OK;
 
-
         case CPU_DOWN_FAILED:
         case CPU_DOWN_FAILED_FROZEN:
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 enable_runtime(cpu_rq(cpu));
-                /* fall-through */
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
-                /*
-                 * Fall through and re-initialise the domains.
-                 */
-                break;
+                return NOTIFY_OK;
+
         default:
                 return NOTIFY_DONE;
         }
-
-#ifndef CONFIG_CPUSETS
-        /*
-         * Create default domain partitioning if cpusets are disabled.
-         * Otherwise we let cpusets rebuild the domains based on the
-         * current setup.
-         */
-
-        /* The hotplug lock is already held by cpu_up/cpu_down */
-        arch_init_sched_domains(&cpu_online_map);
-#endif
-
-        return NOTIFY_OK;
 }
 
 void __init sched_init_smp(void)
@@ -7854,8 +7904,15 @@ void __init sched_init_smp(void)
                 cpu_set(smp_processor_id(), non_isolated_cpus);
         mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
+
+#ifndef CONFIG_CPUSETS
         /* XXX: Theoretical race here - CPU may be hotplugged now */
         hotcpu_notifier(update_sched_domains, 0);
+#endif
+
+        /* RT runtime code needs to handle some hotplug events */
+        hotcpu_notifier(update_runtime, 0);
+
         init_hrtick();
 
         /* Move init over to a non-isolated CPU */
@@ -8063,7 +8120,6 @@ void __init sched_init(void)
 
                 rq = cpu_rq(i);
                 spin_lock_init(&rq->lock);
-                lockdep_set_class(&rq->lock, &rq->rq_lock_key);
                 rq->nr_running = 0;
                 init_cfs_rq(&rq->cfs, rq);
                 init_rt_rq(&rq->rt, rq);
@@ -8520,8 +8576,8 @@ struct task_group *sched_create_group(struct task_group *parent)
         WARN_ON(!parent); /* root should already exist */
 
         tg->parent = parent;
-        list_add_rcu(&tg->siblings, &parent->children);
         INIT_LIST_HEAD(&tg->children);
+        list_add_rcu(&tg->siblings, &parent->children);
         spin_unlock_irqrestore(&task_group_lock, flags);
 
         return tg;
@@ -8853,6 +8909,9 @@ static int sched_rt_global_constraints(void)
         u64 rt_runtime, rt_period;
         int ret = 0;
 
+        if (sysctl_sched_rt_period <= 0)
+                return -EINVAL;
+
         rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
         rt_runtime = tg->rt_bandwidth.rt_runtime;
 
@@ -8869,6 +8928,9 @@ static int sched_rt_global_constraints(void)
         unsigned long flags;
         int i;
 
+        if (sysctl_sched_rt_period <= 0)
+                return -EINVAL;
+
         spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
         for_each_possible_cpu(i) {
                 struct rt_rq *rt_rq = &cpu_rq(i)->rt;
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 22ed55d1167f..e8ab096ddfe3 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -12,19 +12,17 @@
  *
  * Create a semi stable clock from a mixture of other events, including:
  *  - gtod
- *  - jiffies
  *  - sched_clock()
  *  - explicit idle events
  *
  * We use gtod as base and the unstable clock deltas. The deltas are filtered,
- * making it monotonic and keeping it within an expected window.  This window
- * is set up using jiffies.
+ * making it monotonic and keeping it within an expected window.
  *
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
  * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
- * consistent between cpus (never more than 1 jiffies difference).
+ * consistent between cpus (never more than 2 jiffies difference).
  */
 #include <linux/sched.h>
 #include <linux/percpu.h>
@@ -32,13 +30,19 @@
 #include <linux/ktime.h>
 #include <linux/module.h>
 
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
 
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static __read_mostly int sched_clock_running;
 
-#define MULTI_SHIFT 15
-/* Max is double, Min is 1/2 */
-#define MAX_MULTI (2LL << MULTI_SHIFT)
-#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 
 struct sched_clock_data {
         /*
@@ -48,15 +52,9 @@ struct sched_clock_data {
          */
         raw_spinlock_t          lock;
 
-        unsigned long           tick_jiffies;
-        u64                     prev_raw;
         u64                     tick_raw;
         u64                     tick_gtod;
         u64                     clock;
-        s64                     multi;
-#ifdef CONFIG_NO_HZ
-        int                     check_max;
-#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -71,121 +69,69 @@ static inline struct sched_clock_data *cpu_sdc(int cpu)
         return &per_cpu(sched_clock_data, cpu);
 }
 
-static __read_mostly int sched_clock_running;
-
 void sched_clock_init(void)
 {
         u64 ktime_now = ktime_to_ns(ktime_get());
-        unsigned long now_jiffies = jiffies;
         int cpu;
 
         for_each_possible_cpu(cpu) {
                 struct sched_clock_data *scd = cpu_sdc(cpu);
 
                 scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-                scd->tick_jiffies = now_jiffies;
-                scd->prev_raw = 0;
                 scd->tick_raw = 0;
                 scd->tick_gtod = ktime_now;
                 scd->clock = ktime_now;
-                scd->multi = 1 << MULTI_SHIFT;
-#ifdef CONFIG_NO_HZ
-                scd->check_max = 1;
-#endif
         }
 
         sched_clock_running = 1;
 }
 
-#ifdef CONFIG_NO_HZ
 /*
- * The dynamic ticks makes the delta jiffies inaccurate. This
- * prevents us from checking the maximum time update.
- * Disable the maximum check during stopped ticks.
+ * min,max except they take wrapping into account
  */
-void sched_clock_tick_stop(int cpu)
-{
-        struct sched_clock_data *scd = cpu_sdc(cpu);
-
-        scd->check_max = 0;
-}
 
-void sched_clock_tick_start(int cpu)
+static inline u64 wrap_min(u64 x, u64 y)
 {
-        struct sched_clock_data *scd = cpu_sdc(cpu);
-
-        scd->check_max = 1;
+        return (s64)(x - y) < 0 ? x : y;
 }
 
-static int check_max(struct sched_clock_data *scd)
+static inline u64 wrap_max(u64 x, u64 y)
 {
-        return scd->check_max;
+        return (s64)(x - y) > 0 ? x : y;
 }
-#else
-static int check_max(struct sched_clock_data *scd)
-{
-        return 1;
-}
-#endif /* CONFIG_NO_HZ */
 
 /*
  * update the percpu scd from the raw @now value
  *
  *  - filter out backward motion
- *  - use jiffies to generate a min,max window to clip the raw values
+ *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
+static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 {
-        unsigned long now_jiffies = jiffies;
-        long delta_jiffies = now_jiffies - scd->tick_jiffies;
-        u64 clock = scd->clock;
-        u64 min_clock, max_clock;
-        s64 delta = now - scd->prev_raw;
+        s64 delta = now - scd->tick_raw;
+        u64 clock, min_clock, max_clock;
 
         WARN_ON_ONCE(!irqs_disabled());
 
-        /*
-         * At schedule tick the clock can be just under the gtod. We don't
-         * want to push it too prematurely.
-         */
-        min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
-        if (min_clock > TICK_NSEC)
-                min_clock -= TICK_NSEC / 2;
-
-        if (unlikely(delta < 0)) {
-                clock++;
-                goto out;
-        }
+        if (unlikely(delta < 0))
+                delta = 0;
 
         /*
-         * The clock must stay within a jiffie of the gtod.
-         * But since we may be at the start of a jiffy or the end of one
-         * we add another jiffy buffer.
+         * scd->clock = clamp(scd->tick_gtod + delta,
+         *                    max(scd->tick_gtod, scd->clock),
+         *                    scd->tick_gtod + TICK_NSEC);
          */
-        max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
 
-        delta *= scd->multi;
-        delta >>= MULTI_SHIFT;
+        clock = scd->tick_gtod + delta;
+        min_clock = wrap_max(scd->tick_gtod, scd->clock);
+        max_clock = scd->tick_gtod + TICK_NSEC;
 
-        if (unlikely(clock + delta > max_clock) && check_max(scd)) {
-                if (clock < max_clock)
-                        clock = max_clock;
-                else
-                        clock++;
-        } else {
-                clock += delta;
-        }
+        clock = wrap_max(clock, min_clock);
+        clock = wrap_min(clock, max_clock);
 
- out:
-        if (unlikely(clock < min_clock))
-                clock = min_clock;
+        scd->clock = clock;
 
-        if (time)
-                *time = clock;
-        else {
-                scd->prev_raw = now;
-                scd->clock = clock;
-        }
+        return scd->clock;
 }
 
 static void lock_double_clock(struct sched_clock_data *data1,
@@ -203,7 +149,7 @@ static void lock_double_clock(struct sched_clock_data *data1,
 u64 sched_clock_cpu(int cpu)
 {
         struct sched_clock_data *scd = cpu_sdc(cpu);
-        u64 now, clock;
+        u64 now, clock, this_clock, remote_clock;
 
         if (unlikely(!sched_clock_running))
                 return 0ull;
@@ -212,43 +158,44 @@ u64 sched_clock_cpu(int cpu)
         now = sched_clock();
 
         if (cpu != raw_smp_processor_id()) {
-                /*
-                 * in order to update a remote cpu's clock based on our
-                 * unstable raw time rebase it against:
-                 *   tick_raw           (offset between raw counters)
-                 *   tick_gotd          (tick offset between cpus)
-                 */
                 struct sched_clock_data *my_scd = this_scd();
 
                 lock_double_clock(scd, my_scd);
 
-                now -= my_scd->tick_raw;
-                now += scd->tick_raw;
+                this_clock = __update_sched_clock(my_scd, now);
+                remote_clock = scd->clock;
 
-                now += my_scd->tick_gtod;
-                now -= scd->tick_gtod;
+                /*
+                 * Use the opportunity that we have both locks
+                 * taken to couple the two clocks: we take the
+                 * larger time as the latest time for both
+                 * runqueues. (this creates monotonic movement)
+                 */
+                if (likely((s64)(remote_clock - this_clock) < 0)) {
+                        clock = this_clock;
+                        scd->clock = clock;
+                } else {
+                        /*
+                         * Should be rare, but possible:
+                         */
+                        clock = remote_clock;
+                        my_scd->clock = remote_clock;
+                }
 
                 __raw_spin_unlock(&my_scd->lock);
-
-                __update_sched_clock(scd, now, &clock);
-
-                __raw_spin_unlock(&scd->lock);
-
         } else {
                 __raw_spin_lock(&scd->lock);
-                __update_sched_clock(scd, now, NULL);
-                clock = scd->clock;
-                __raw_spin_unlock(&scd->lock);
+                clock = __update_sched_clock(scd, now);
         }
 
+        __raw_spin_unlock(&scd->lock);
+
         return clock;
 }
 
 void sched_clock_tick(void)
 {
         struct sched_clock_data *scd = this_scd();
-        unsigned long now_jiffies = jiffies;
-        s64 mult, delta_gtod, delta_raw;
         u64 now, now_gtod;
 
         if (unlikely(!sched_clock_running))
@@ -260,29 +207,9 @@ void sched_clock_tick(void)
         now = sched_clock();
 
         __raw_spin_lock(&scd->lock);
-        __update_sched_clock(scd, now, NULL);
-        /*
-         * update tick_gtod after __update_sched_clock() because that will
-         * already observe 1 new jiffy; adding a new tick_gtod to that would
-         * increase the clock 2 jiffies.
-         */
-        delta_gtod = now_gtod - scd->tick_gtod;
-        delta_raw = now - scd->tick_raw;
-
-        if ((long)delta_raw > 0) {
-                mult = delta_gtod << MULTI_SHIFT;
-                do_div(mult, delta_raw);
-                scd->multi = mult;
-                if (scd->multi > MAX_MULTI)
-                        scd->multi = MAX_MULTI;
-                else if (scd->multi < MIN_MULTI)
-                        scd->multi = MIN_MULTI;
-        } else
-                scd->multi = 1 << MULTI_SHIFT;
-
         scd->tick_raw = now;
         scd->tick_gtod = now_gtod;
-        scd->tick_jiffies = now_jiffies;
+        __update_sched_clock(scd, now);
         __raw_spin_unlock(&scd->lock);
 }
 
@@ -300,37 +227,28 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
  */
 void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
-        struct sched_clock_data *scd = this_scd();
-        u64 now = sched_clock();
-
-        /*
-         * Override the previous timestamp and ignore all
-         * sched_clock() deltas that occured while we idled,
-         * and use the PM-provided delta_ns to advance the
-         * rq clock:
-         */
-        __raw_spin_lock(&scd->lock);
-        scd->prev_raw = now;
-        scd->clock += delta_ns;
-        scd->multi = 1 << MULTI_SHIFT;
-        __raw_spin_unlock(&scd->lock);
-
+        sched_clock_tick();
         touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
-#endif
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-/*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
+void sched_clock_init(void)
 {
-        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+        sched_clock_running = 1;
 }
 
+u64 sched_clock_cpu(int cpu)
+{
+        if (unlikely(!sched_clock_running))
+                return 0;
+
+        return sched_clock();
+}
+
+#endif
+
 unsigned long long cpu_clock(int cpu)
 {
         unsigned long long clock;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f2aa987027d6..fb8994c6d4bb 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -878,7 +878,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 #ifdef CONFIG_SCHED_HRTICK
 static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
-        int requeue = rq->curr == p;
         struct sched_entity *se = &p->se;
         struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
@@ -899,10 +898,10 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
                  * Don't schedule slices shorter than 10000ns, that just
                  * doesn't make sense. Rely on vruntime for fairness.
                  */
-                if (!requeue)
-                        delta = max(10000LL, delta);
+                if (rq->curr != p)
+                        delta = max_t(s64, 10000LL, delta);
 
-                hrtick_start(rq, delta, requeue);
+                hrtick_start(rq, delta);
         }
 }
 #else /* !CONFIG_SCHED_HRTICK */
@@ -1004,6 +1003,8 @@ static void yield_task_fair(struct rq *rq)
  * not idle and an idle cpu is available.  The span of cpus to
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
  *
  * Returns the CPU we should wake onto.
  */
@@ -1031,7 +1032,8 @@ static int wake_idle(int cpu, struct task_struct *p)
                     || ((sd->flags & SD_WAKE_IDLE_FAR)
                         && !task_hot(p, task_rq(p)->clock, sd))) {
                         cpus_and(tmp, sd->span, p->cpus_allowed);
-                        for_each_cpu_mask(i, tmp) {
+                        cpus_and(tmp, tmp, cpu_active_map);
+                        for_each_cpu_mask_nr(i, tmp) {
                                 if (idle_cpu(i)) {
                                         if (i != task_cpu(p)) {
                                                 schedstat_inc(p,
@@ -1440,18 +1442,23 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
         struct task_struct *p = NULL;
         struct sched_entity *se;
 
-        while (next != &cfs_rq->tasks) {
+        if (next == &cfs_rq->tasks)
+                return NULL;
+
+        /* Skip over entities that are not tasks */
+        do {
                 se = list_entry(next, struct sched_entity, group_node);
                 next = next->next;
+        } while (next != &cfs_rq->tasks && !entity_is_task(se));
 
-                /* Skip over entities that are not tasks */
-                if (entity_is_task(se)) {
-                        p = task_of(se);
-                        break;
-                }
-        }
+        if (next == &cfs_rq->tasks)
+                return NULL;
 
         cfs_rq->balance_iterator = next;
+
+        if (entity_is_task(se))
+                p = task_of(se);
+
         return p;
 }
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 862b06bd560a..9353ca78154e 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -8,6 +8,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1)
 SCHED_FEAT(HRTICK, 1)
 SCHED_FEAT(DOUBLE_TICK, 0)
 SCHED_FEAT(ASYM_GRAN, 1)
-SCHED_FEAT(LB_BIAS, 0)
+SCHED_FEAT(LB_BIAS, 1)
 SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 47ceac9e8552..1113157b2058 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -199,6 +199,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 
 static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+        if (rt_rq->rt_nr_running)
+                resched_task(rq_of_rt_rq(rt_rq)->curr);
 }
 
 static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
@@ -240,7 +242,7 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 
         spin_lock(&rt_b->rt_runtime_lock);
         rt_period = ktime_to_ns(rt_b->rt_period);
-        for_each_cpu_mask(i, rd->span) {
+        for_each_cpu_mask_nr(i, rd->span) {
                 struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
                 s64 diff;
 
@@ -253,7 +255,7 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 
                 diff = iter->rt_runtime - iter->rt_time;
                 if (diff > 0) {
-                        do_div(diff, weight);
+                        diff = div_u64((u64)diff, weight);
                         if (rt_rq->rt_runtime + diff > rt_period)
                                 diff = rt_period - rt_rq->rt_runtime;
                         iter->rt_runtime -= diff;
@@ -298,7 +300,7 @@ static void __disable_runtime(struct rq *rq)
                         struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
                         s64 diff;
 
-                        if (iter == rt_rq)
+                        if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
                                 continue;
 
                         spin_lock(&iter->rt_runtime_lock);
@@ -348,6 +350,7 @@ static void __enable_runtime(struct rq *rq)
                 spin_lock(&rt_rq->rt_runtime_lock);
                 rt_rq->rt_runtime = rt_b->rt_runtime;
                 rt_rq->rt_time = 0;
+                rt_rq->rt_throttled = 0;
                 spin_unlock(&rt_rq->rt_runtime_lock);
                 spin_unlock(&rt_b->rt_runtime_lock);
         }
@@ -438,9 +441,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 {
         u64 runtime = sched_rt_runtime(rt_rq);
 
-        if (runtime == RUNTIME_INF)
-                return 0;
-
         if (rt_rq->rt_throttled)
                 return rt_rq_throttled(rt_rq);
 
@@ -491,9 +491,11 @@ static void update_curr_rt(struct rq *rq)
                 rt_rq = rt_rq_of_se(rt_se);
 
                 spin_lock(&rt_rq->rt_runtime_lock);
-                rt_rq->rt_time += delta_exec;
-                if (sched_rt_runtime_exceeded(rt_rq))
-                        resched_task(curr);
+                if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
+                        rt_rq->rt_time += delta_exec;
+                        if (sched_rt_runtime_exceeded(rt_rq))
+                                resched_task(curr);
+                }
                 spin_unlock(&rt_rq->rt_runtime_lock);
         }
 }
@@ -505,7 +507,9 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
         rt_rq->rt_nr_running++;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
         if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+#ifdef CONFIG_SMP
                 struct rq *rq = rq_of_rt_rq(rt_rq);
+#endif
 
                 rt_rq->highest_prio = rt_se_prio(rt_se);
 #ifdef CONFIG_SMP
@@ -599,11 +603,7 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
         if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
                 return;
 
-        if (rt_se->nr_cpus_allowed == 1)
-                list_add(&rt_se->run_list, queue);
-        else
-                list_add_tail(&rt_se->run_list, queue);
-
+        list_add_tail(&rt_se->run_list, queue);
         __set_bit(rt_se_prio(rt_se), array->bitmap);
 
         inc_rt_tasks(rt_se, rt_rq);
@@ -688,32 +688,34 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
  * Put task to the end of the run list without the overhead of dequeue
  * followed by enqueue.
  */
-static
-void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+static void
+requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
 {
-        struct rt_prio_array *array = &rt_rq->active;
-
         if (on_rt_rq(rt_se)) {
-                list_del_init(&rt_se->run_list);
-                list_add_tail(&rt_se->run_list,
-                              array->queue + rt_se_prio(rt_se));
+                struct rt_prio_array *array = &rt_rq->active;
+                struct list_head *queue = array->queue + rt_se_prio(rt_se);
+
+                if (head)
+                        list_move(&rt_se->run_list, queue);
+                else
+                        list_move_tail(&rt_se->run_list, queue);
         }
 }
 
-static void requeue_task_rt(struct rq *rq, struct task_struct *p)
+static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
 {
         struct sched_rt_entity *rt_se = &p->rt;
         struct rt_rq *rt_rq;
 
         for_each_sched_rt_entity(rt_se) {
                 rt_rq = rt_rq_of_se(rt_se);
-                requeue_rt_entity(rt_rq, rt_se);
+                requeue_rt_entity(rt_rq, rt_se, head);
         }
 }
 
 static void yield_task_rt(struct rq *rq)
 {
-        requeue_task_rt(rq, rq->curr);
+        requeue_task_rt(rq, rq->curr, 0);
 }
 
 #ifdef CONFIG_SMP
@@ -753,6 +755,30 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
          */
         return task_cpu(p);
 }
+
+static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
+{
+        cpumask_t mask;
+
+        if (rq->curr->rt.nr_cpus_allowed == 1)
+                return;
+
+        if (p->rt.nr_cpus_allowed != 1
+            && cpupri_find(&rq->rd->cpupri, p, &mask))
+                return;
+
+        if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+                return;
+
+        /*
+         * There appears to be other cpus that can accept
+         * current and none to run 'p', so lets reschedule
+         * to try and push current away:
+         */
+        requeue_task_rt(rq, p, 1);
+        resched_task(rq->curr);
+}
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -778,18 +804,8 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
          * to move current somewhere else, making room for our non-migratable
          * task.
          */
-        if((p->prio == rq->curr->prio)
-           && p->rt.nr_cpus_allowed == 1
-           && rq->curr->rt.nr_cpus_allowed != 1) {
-                cpumask_t mask;
-
-                if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
-                        /*
-                         * There appears to be other cpus that can accept
-                         * current, so lets reschedule to try and push it away
-                         */
-                        resched_task(rq->curr);
-        }
+        if (p->prio == rq->curr->prio && !need_resched())
+                check_preempt_equal_prio(rq, p);
 #endif
 }
 
@@ -847,6 +863,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 #define RT_MAX_TRIES 3
 
 static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
+static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);
+
 static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
@@ -922,6 +940,13 @@ static int find_lowest_rq(struct task_struct *task)
                 return -1; /* No targets found */
 
         /*
+         * Only consider CPUs that are usable for migration.
+         * I guess we might want to change cpupri_find() to ignore those
+         * in the first place.
+         */
+        cpus_and(*lowest_mask, *lowest_mask, cpu_active_map);
+
+        /*
          * At this point we have built a mask of cpus representing the
          * lowest priority tasks in the system.  Now we want to elect
          * the best one based on our affinity and topology.
@@ -1001,7 +1026,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
                         break;
 
                 /* try again */
-                spin_unlock(&lowest_rq->lock);
+                double_unlock_balance(rq, lowest_rq);
                 lowest_rq = NULL;
         }
 
@@ -1070,7 +1095,7 @@ static int push_rt_task(struct rq *rq)
 
         resched_task(lowest_rq->curr);
 
-        spin_unlock(&lowest_rq->lock);
+        double_unlock_balance(rq, lowest_rq);
 
         ret = 1;
 out:
@@ -1107,7 +1132,7 @@ static int pull_rt_task(struct rq *this_rq)
 
         next = pick_next_task_rt(this_rq);
 
-        for_each_cpu_mask(cpu, this_rq->rd->rto_mask) {
+        for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) {
                 if (this_cpu == cpu)
                         continue;
 
@@ -1176,7 +1201,7 @@ static int pull_rt_task(struct rq *this_rq)
 
                 }
  skip:
-                spin_unlock(&src_rq->lock);
+                double_unlock_balance(this_rq, src_rq);
         }
 
         return ret;
@@ -1415,7 +1440,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
          * on the queue:
          */
         if (p->rt.run_list.prev != p->rt.run_list.next) {
-                requeue_task_rt(rq, p);
+                requeue_task_rt(rq, p, 0);
                 set_tsk_need_resched(p);
         }
 }
diff --git a/kernel/semaphore.c b/kernel/semaphore.c
index aaaeae8244e7..94a62c0d4ade 100644
--- a/kernel/semaphore.c
+++ b/kernel/semaphore.c
@@ -212,9 +212,7 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
         waiter.up = 0;
 
         for (;;) {
-                if (state == TASK_INTERRUPTIBLE && signal_pending(task))
-                        goto interrupted;
-                if (state == TASK_KILLABLE && fatal_signal_pending(task))
+                if (signal_pending_state(state, task))
                         goto interrupted;
                 if (timeout <= 0)
                         goto timed_out;
diff --git a/kernel/signal.c b/kernel/signal.c
index 6c0958e52ea7..e661b01d340f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,6 +22,7 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/signalfd.h>
+#include <linux/tracehook.h>
 #include <linux/capability.h>
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
@@ -39,24 +40,21 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
-static int __sig_ignored(struct task_struct *t, int sig)
+static void __user *sig_handler(struct task_struct *t, int sig)
 {
-        void __user *handler;
+        return t->sighand->action[sig - 1].sa.sa_handler;
+}
 
+static int sig_handler_ignored(void __user *handler, int sig)
+{
         /* Is it explicitly or implicitly ignored? */
-
-        handler = t->sighand->action[sig - 1].sa.sa_handler;
         return handler == SIG_IGN ||
                 (handler == SIG_DFL && sig_kernel_ignore(sig));
 }
 
 static int sig_ignored(struct task_struct *t, int sig)
 {
-        /*
-         * Tracers always want to know about signals..
-         */
-        if (t->ptrace & PT_PTRACED)
-                return 0;
+        void __user *handler;
 
         /*
          * Blocked signals are never ignored, since the
@@ -66,7 +64,14 @@ static int sig_ignored(struct task_struct *t, int sig)
         if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
                 return 0;
 
-        return __sig_ignored(t, sig);
+        handler = sig_handler(t, sig);
+        if (!sig_handler_ignored(handler, sig))
+                return 0;
+
+        /*
+         * Tracers may want to know about even ignored signals.
+         */
+        return !tracehook_consider_ignored_signal(t, sig, handler);
 }
 
 /*
@@ -129,7 +134,9 @@ void recalc_sigpending_and_wake(struct task_struct *t)
 
 void recalc_sigpending(void)
 {
-        if (!recalc_sigpending_tsk(current) && !freezing(current))
+        if (unlikely(tracehook_force_sigpending()))
+                set_thread_flag(TIF_SIGPENDING);
+        else if (!recalc_sigpending_tsk(current) && !freezing(current))
                 clear_thread_flag(TIF_SIGPENDING);
 
 }
@@ -295,12 +302,12 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 
 int unhandled_signal(struct task_struct *tsk, int sig)
 {
+        void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler;
         if (is_global_init(tsk))
                 return 1;
-        if (tsk->ptrace & PT_PTRACED)
+        if (handler != SIG_IGN && handler != SIG_DFL)
                 return 0;
-        return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) ||
-                (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL);
+        return !tracehook_consider_fatal_signal(tsk, sig, handler);
 }
 
 
@@ -338,13 +345,9 @@ unblock_all_signals(void)
         spin_unlock_irqrestore(&current->sighand->siglock, flags);
 }
 
-static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
+static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
 {
         struct sigqueue *q, *first = NULL;
-        int still_pending = 0;
-
-        if (unlikely(!sigismember(&list->signal, sig)))
-                return 0;
 
         /*
          * Collect the siginfo appropriate to this signal.  Check if
@@ -352,33 +355,30 @@ static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
         */
         list_for_each_entry(q, &list->list, list) {
                 if (q->info.si_signo == sig) {
-                        if (first) {
-                                still_pending = 1;
-                                break;
-                        }
+                        if (first)
+                                goto still_pending;
                         first = q;
                 }
         }
+
+        sigdelset(&list->signal, sig);
+
         if (first) {
+still_pending:
                 list_del_init(&first->list);
                 copy_siginfo(info, &first->info);
                 __sigqueue_free(first);
-                if (!still_pending)
-                        sigdelset(&list->signal, sig);
         } else {
-
                 /* Ok, it wasn't in the queue.  This must be
                    a fast-pathed signal or we must have been
                    out of queue space.  So zero out the info.
                  */
-                sigdelset(&list->signal, sig);
                 info->si_signo = sig;
                 info->si_errno = 0;
                 info->si_code = 0;
                 info->si_pid = 0;
                 info->si_uid = 0;
         }
-        return 1;
 }
 
 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
@@ -396,8 +396,7 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
                         }
                 }
 
-                if (!collect_signal(sig, pending, info))
-                        sig = 0;
+                collect_signal(sig, pending, info);
         }
 
         return sig;
@@ -462,8 +461,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
                  * is to alert stop-signal processing code when another
                  * processor has come along and cleared the flag.
                  */
-                if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
-                        tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
+                tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
         }
         if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
                 /*
@@ -600,9 +598,6 @@ static int check_kill_permission(int sig, struct siginfo *info,
         return security_task_kill(t, info, sig, 0);
 }
 
-/* forward decl */
-static void do_notify_parent_cldstop(struct task_struct *tsk, int why);
-
 /*
  * Handle magic process-wide effects of stop/continue signals. Unlike
  * the signal actions, these happen immediately at signal-generation
@@ -765,7 +760,8 @@ static void complete_signal(int sig, struct task_struct *p, int group)
         if (sig_fatal(p, sig) &&
             !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
             !sigismember(&t->real_blocked, sig) &&
-            (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) {
+            (sig == SIGKILL ||
+             !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) {
                 /*
                  * This signal will be fatal to the whole group.
                  */
@@ -1125,7 +1121,7 @@ EXPORT_SYMBOL_GPL(kill_pid_info_as_uid);
  * is probably wrong.  Should make it like BSD or SYSV.
  */
 
-static int kill_something_info(int sig, struct siginfo *info, int pid)
+static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
 {
         int ret;
 
@@ -1237,17 +1233,6 @@ int kill_pid(struct pid *pid, int sig, int priv)
 }
 EXPORT_SYMBOL(kill_pid);
 
-int
-kill_proc(pid_t pid, int sig, int priv)
-{
-        int ret;
-
-        rcu_read_lock();
-        ret = kill_pid_info(sig, __si_special(priv), find_pid(pid));
-        rcu_read_unlock();
-        return ret;
-}
-
 /*
  * These functions support sending signals using preallocated sigqueue
  * structures.  This is needed "because realtime applications cannot
@@ -1319,6 +1304,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
                 q->info.si_overrun++;
                 goto out;
         }
+        q->info.si_overrun = 0;
 
         signalfd_notify(t, sig);
         pending = group ? &t->signal->shared_pending : &t->pending;
@@ -1343,13 +1329,16 @@ static inline void __wake_up_parent(struct task_struct *p,
 /*
  * Let a parent know about the death of a child.
  * For a stopped/continued status change, use do_notify_parent_cldstop instead.
+ *
+ * Returns -1 if our parent ignored us and so we've switched to
+ * self-reaping, or else @sig.
  */
-
-void do_notify_parent(struct task_struct *tsk, int sig)
+int do_notify_parent(struct task_struct *tsk, int sig)
 {
         struct siginfo info;
         unsigned long flags;
         struct sighand_struct *psig;
+        int ret = sig;
 
         BUG_ON(sig == -1);
 
@@ -1379,10 +1368,9 @@ void do_notify_parent(struct task_struct *tsk, int sig)
 
         info.si_uid = tsk->uid;
 
-        /* FIXME: find out whether or not this is supposed to be c*time. */
-        info.si_utime = cputime_to_jiffies(cputime_add(tsk->utime,
+        info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
                                                        tsk->signal->utime));
-        info.si_stime = cputime_to_jiffies(cputime_add(tsk->stime,
+        info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
                                                        tsk->signal->stime));
 
         info.si_status = tsk->exit_code & 0x7f;
@@ -1415,14 +1403,16 @@ void do_notify_parent(struct task_struct *tsk, int sig)
                  * is implementation-defined: we do (if you don't want
                  * it, just use SIG_IGN instead).
                  */
-                tsk->exit_signal = -1;
+                ret = tsk->exit_signal = -1;
                 if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
-                        sig = 0;
+                        sig = -1;
         }
         if (valid_signal(sig) && sig > 0)
                 __group_send_sig_info(sig, &info, tsk->parent);
         __wake_up_parent(tsk, tsk->parent);
         spin_unlock_irqrestore(&psig->siglock, flags);
+
+        return ret;
 }
 
 static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
@@ -1450,9 +1440,8 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
 
         info.si_uid = tsk->uid;
 
-        /* FIXME: find out whether or not this is supposed to be c*time. */
-        info.si_utime = cputime_to_jiffies(tsk->utime);
-        info.si_stime = cputime_to_jiffies(tsk->stime);
+        info.si_utime = cputime_to_clock_t(tsk->utime);
+        info.si_stime = cputime_to_clock_t(tsk->stime);
 
         info.si_code = why;
         switch (why) {
@@ -1491,10 +1480,10 @@ static inline int may_ptrace_stop(void)
          * is a deadlock situation, and pointless because our tracer
          * is dead so don't allow us to stop.
          * If SIGKILL was already sent before the caller unlocked
-         * ->siglock we must see ->core_waiters != 0. Otherwise it
+         * ->siglock we must see ->core_state != NULL. Otherwise it
          * is safe to enter schedule().
          */
-        if (unlikely(current->mm->core_waiters) &&
+        if (unlikely(current->mm->core_state) &&
             unlikely(current->mm == current->parent->mm))
                 return 0;
 
@@ -1507,9 +1496,8 @@ static inline int may_ptrace_stop(void)
  */
 static int sigkill_pending(struct task_struct *tsk)
 {
-        return ((sigismember(&tsk->pending.signal, SIGKILL) ||
-                 sigismember(&tsk->signal->shared_pending.signal, SIGKILL)) &&
-                !unlikely(sigismember(&tsk->blocked, SIGKILL)));
+        return  sigismember(&tsk->pending.signal, SIGKILL) ||
+                sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
 }
 
 /*
@@ -1525,8 +1513,6 @@ static int sigkill_pending(struct task_struct *tsk)
  */
 static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
 {
-        int killed = 0;
-
         if (arch_ptrace_stop_needed(exit_code, info)) {
                 /*
                  * The arch code has something special to do before a
@@ -1542,7 +1528,8 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
                 spin_unlock_irq(&current->sighand->siglock);
                 arch_ptrace_stop(exit_code, info);
                 spin_lock_irq(&current->sighand->siglock);
-                killed = sigkill_pending(current);
+                if (sigkill_pending(current))
+                        return;
         }
 
         /*
@@ -1559,7 +1546,7 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
         __set_current_state(TASK_TRACED);
         spin_unlock_irq(&current->sighand->siglock);
         read_lock(&tasklist_lock);
-        if (!unlikely(killed) && may_ptrace_stop()) {
+        if (may_ptrace_stop()) {
                 do_notify_parent_cldstop(current, CLD_TRAPPED);
                 read_unlock(&tasklist_lock);
                 schedule();
@@ -1623,7 +1610,7 @@ finish_stop(int stop_count)
          * a group stop in progress and we are the last to stop,
          * report to the parent.  When ptraced, every thread reports itself.
          */
-        if (stop_count == 0 || (current->ptrace & PT_PTRACED)) {
+        if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
                 read_lock(&tasklist_lock);
                 do_notify_parent_cldstop(current, CLD_STOPPED);
                 read_unlock(&tasklist_lock);
@@ -1658,8 +1645,7 @@ static int do_signal_stop(int signr)
         } else {
                 struct task_struct *t;
 
-                if (unlikely((sig->flags & (SIGNAL_STOP_DEQUEUED | SIGNAL_UNKILLABLE))
-                                         != SIGNAL_STOP_DEQUEUED) ||
+                if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
                     unlikely(signal_group_exit(sig)))
                         return 0;
                 /*
@@ -1760,6 +1746,9 @@ relock:
                 signal->flags &= ~SIGNAL_CLD_MASK;
                 spin_unlock_irq(&sighand->siglock);
 
+                if (unlikely(!tracehook_notify_jctl(1, why)))
+                        goto relock;
+
                 read_lock(&tasklist_lock);
                 do_notify_parent_cldstop(current->group_leader, why);
                 read_unlock(&tasklist_lock);
@@ -1773,17 +1762,33 @@ relock:
                     do_signal_stop(0))
                         goto relock;
 
-                signr = dequeue_signal(current, &current->blocked, info);
-                if (!signr)
-                        break; /* will return 0 */
+                /*
+                 * Tracing can induce an artifical signal and choose sigaction.
+                 * The return value in @signr determines the default action,
+                 * but @info->si_signo is the signal number we will report.
+                 */
+                signr = tracehook_get_signal(current, regs, info, return_ka);
+                if (unlikely(signr < 0))
+                        goto relock;
+                if (unlikely(signr != 0))
+                        ka = return_ka;
+                else {
+                        signr = dequeue_signal(current, &current->blocked,
+                                               info);
 
-                if (signr != SIGKILL) {
-                        signr = ptrace_signal(signr, info, regs, cookie);
                         if (!signr)
-                                continue;
+                                break; /* will return 0 */
+
+                        if (signr != SIGKILL) {
+                                signr = ptrace_signal(signr, info,
+                                                      regs, cookie);
+                                if (!signr)
+                                        continue;
+                        }
+
+                        ka = &sighand->action[signr-1];
                 }
 
-                ka = &sighand->action[signr-1];
                 if (ka->sa.sa_handler == SIG_IGN) /* Do nothing.  */
                         continue;
                 if (ka->sa.sa_handler != SIG_DFL) {
@@ -1831,7 +1836,7 @@ relock:
                                 spin_lock_irq(&sighand->siglock);
                         }
 
-                        if (likely(do_signal_stop(signr))) {
+                        if (likely(do_signal_stop(info->si_signo))) {
                                 /* It released the siglock.  */
                                 goto relock;
                         }
@@ -1852,7 +1857,7 @@ relock:
 
                 if (sig_kernel_coredump(signr)) {
                         if (print_fatal_signals)
-                                print_fatal_signal(regs, signr);
+                                print_fatal_signal(regs, info->si_signo);
                         /*
                          * If it was able to dump core, this kills all
                          * other threads in the group and synchronizes with
@@ -1861,13 +1866,13 @@ relock:
                          * first and our do_group_exit call below will use
                          * that value and ignore the one we pass it.
                          */
-                        do_coredump((long)signr, signr, regs);
+                        do_coredump(info->si_signo, info->si_signo, regs);
                 }
 
                 /*
                  * Death signals, no core dump.
                  */
-                do_group_exit(signr);
+                do_group_exit(info->si_signo);
                 /* NOTREACHED */
         }
         spin_unlock_irq(&sighand->siglock);
@@ -1909,7 +1914,7 @@ void exit_signals(struct task_struct *tsk)
 out:
         spin_unlock_irq(&tsk->sighand->siglock);
 
-        if (unlikely(group_stop)) {
+        if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
                 read_lock(&tasklist_lock);
                 do_notify_parent_cldstop(tsk, CLD_STOPPED);
                 read_unlock(&tasklist_lock);
@@ -1920,8 +1925,6 @@ EXPORT_SYMBOL(recalc_sigpending);
 EXPORT_SYMBOL_GPL(dequeue_signal);
 EXPORT_SYMBOL(flush_signals);
 EXPORT_SYMBOL(force_sig);
-EXPORT_SYMBOL(kill_proc);
-EXPORT_SYMBOL(ptrace_notify);
 EXPORT_SYMBOL(send_sig);
 EXPORT_SYMBOL(send_sig_info);
 EXPORT_SYMBOL(sigprocmask);
@@ -2196,7 +2199,7 @@ sys_rt_sigtimedwait(const sigset_t __user *uthese,
 }
 
 asmlinkage long
-sys_kill(int pid, int sig)
+sys_kill(pid_t pid, int sig)
 {
         struct siginfo info;
 
@@ -2209,7 +2212,7 @@ sys_kill(int pid, int sig)
         return kill_something_info(sig, &info, pid);
 }
 
-static int do_tkill(int tgid, int pid, int sig)
+static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
         int error;
         struct siginfo info;
@@ -2255,7 +2258,7 @@ static int do_tkill(int tgid, int pid, int sig)
  *  exists but it's not belonging to the target process anymore. This
  *  method solves the problem of threads exiting and PIDs getting reused.
  */
-asmlinkage long sys_tgkill(int tgid, int pid, int sig)
+asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig)
 {
         /* This is only valid for single tasks */
         if (pid <= 0 || tgid <= 0)
@@ -2268,7 +2271,7 @@ asmlinkage long sys_tgkill(int tgid, int pid, int sig)
  *  Send a signal to only one task, even if it's a CLONE_THREAD task.
  */
 asmlinkage long
-sys_tkill(int pid, int sig)
+sys_tkill(pid_t pid, int sig)
 {
         /* This is only valid for single tasks */
         if (pid <= 0)
@@ -2278,7 +2281,7 @@ sys_tkill(int pid, int sig)
 }
 
 asmlinkage long
-sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo)
+sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo)
 {
         siginfo_t info;
 
@@ -2325,7 +2328,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
                  *   (for example, SIGCHLD), shall cause the pending signal to
                  *   be discarded, whether or not it is blocked"
                  */
-                if (__sig_ignored(t, sig)) {
+                if (sig_handler_ignored(sig_handler(t, sig), sig)) {
                         sigemptyset(&mask);
                         sigaddset(&mask, sig);
                         rm_from_queue_full(&mask, &t->signal->shared_pending);
diff --git a/kernel/smp.c b/kernel/smp.c
index 462c785ca1ee..f362a8553777 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -33,7 +33,7 @@ struct call_single_queue {
         spinlock_t lock;
 };
 
-void __cpuinit init_call_single_data(void)
+static int __cpuinit init_call_single_data(void)
 {
         int i;
 
@@ -43,7 +43,9 @@ void __cpuinit init_call_single_data(void)
                 spin_lock_init(&q->lock);
                 INIT_LIST_HEAD(&q->list);
         }
+        return 0;
 }
+early_initcall(init_call_single_data);
 
 static void csd_flag_wait(struct call_single_data *data)
 {
@@ -133,7 +135,8 @@ void generic_smp_call_function_interrupt(void)
                          */
                         smp_wmb();
                         data->csd.flags &= ~CSD_FLAG_WAIT;
-                } else
+                }
+                if (data->csd.flags & CSD_FLAG_ALLOC)
                         call_rcu(&data->rcu_head, rcu_free_call_data);
         }
         rcu_read_unlock();
@@ -207,8 +210,10 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 {
         struct call_single_data d;
         unsigned long flags;
-        /* prevent preemption and reschedule on another processor */
+        /* prevent preemption and reschedule on another processor,
+           as well as CPU removal */
         int me = get_cpu();
+        int err = 0;
 
         /* Can deadlock when called with interrupts disabled */
         WARN_ON(irqs_disabled());
@@ -217,7 +222,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 local_irq_save(flags);
                 func(info);
                 local_irq_restore(flags);
-        } else {
+        } else if ((unsigned)cpu < NR_CPUS && cpu_online(cpu)) {
                 struct call_single_data *data = NULL;
 
                 if (!wait) {
@@ -233,10 +238,12 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 data->func = func;
                 data->info = info;
                 generic_exec_single(cpu, data);
+        } else {
+                err = -ENXIO;   /* CPU not online */
         }
 
         put_cpu();
-        return 0;
+        return err;
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
@@ -258,6 +265,42 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
         generic_exec_single(cpu, data);
 }
 
+/* Dummy function */
+static void quiesce_dummy(void *unused)
+{
+}
+
+/*
+ * Ensure stack based data used in call function mask is safe to free.
+ *
+ * This is needed by smp_call_function_mask when using on-stack data, because
+ * a single call function queue is shared by all CPUs, and any CPU may pick up
+ * the data item on the queue at any time before it is deleted. So we need to
+ * ensure that all CPUs have transitioned through a quiescent state after
+ * this call.
+ *
+ * This is a very slow function, implemented by sending synchronous IPIs to
+ * all possible CPUs. For this reason, we have to alloc data rather than use
+ * stack based data even in the case of synchronous calls. The stack based
+ * data is then just used for deadlock/oom fallback which will be very rare.
+ *
+ * If a faster scheme can be made, we could go back to preferring stack based
+ * data -- the data allocation/free is non-zero cost.
+ */
+static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
+{
+        struct call_single_data data;
+        int cpu;
+
+        data.func = quiesce_dummy;
+        data.info = NULL;
+
+        for_each_cpu_mask(cpu, mask) {
+                data.flags = CSD_FLAG_WAIT;
+                generic_exec_single(cpu, &data);
+        }
+}
+
 /**
  * smp_call_function_mask(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on.
@@ -283,6 +326,7 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         cpumask_t allbutself;
         unsigned long flags;
         int cpu, num_cpus;
+        int slowpath = 0;
 
         /* Can deadlock when called with interrupts disabled */
         WARN_ON(irqs_disabled());
@@ -304,15 +348,16 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
                 return smp_call_function_single(cpu, func, info, wait);
         }
 
-        if (!wait) {
-                data = kmalloc(sizeof(*data), GFP_ATOMIC);
-                if (data)
-                        data->csd.flags = CSD_FLAG_ALLOC;
-        }
-        if (!data) {
+        data = kmalloc(sizeof(*data), GFP_ATOMIC);
+        if (data) {
+                data->csd.flags = CSD_FLAG_ALLOC;
+                if (wait)
+                        data->csd.flags |= CSD_FLAG_WAIT;
+        } else {
                 data = &d;
                 data->csd.flags = CSD_FLAG_WAIT;
                 wait = 1;
+                slowpath = 1;
         }
 
         spin_lock_init(&data->lock);
@@ -329,8 +374,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         arch_send_call_function_ipi(mask);
 
         /* optionally wait for the CPUs to complete */
-        if (wait)
+        if (wait) {
                 csd_flag_wait(&data->csd);
+                if (unlikely(slowpath))
+                        smp_call_function_mask_quiesce_stack(mask);
+        }
 
         return 0;
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 81e2fe0f983a..c506f266a6b9 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -286,7 +286,7 @@ void irq_exit(void)
 #ifdef CONFIG_NO_HZ
         /* Make sure that timer wheel updates are propagated */
         if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
-                tick_nohz_stop_sched_tick();
+                tick_nohz_stop_sched_tick(0);
         rcu_irq_exit();
 #endif
         preempt_enable_no_resched();
@@ -630,7 +630,7 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
         .notifier_call = cpu_callback
 };
 
-__init int spawn_ksoftirqd(void)
+static __init int spawn_ksoftirqd(void)
 {
         void *cpu = (void *)(long)smp_processor_id();
         int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
@@ -640,6 +640,7 @@ __init int spawn_ksoftirqd(void)
         register_cpu_notifier(&cpu_nfb);
         return 0;
 }
+early_initcall(spawn_ksoftirqd);
 
 #ifdef CONFIG_SMP
 /*
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index a272d78185eb..cb838ee93a82 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
+#include <linux/lockdep.h>
 #include <linux/notifier.h>
 #include <linux/module.h>
 
@@ -25,7 +26,22 @@ static DEFINE_PER_CPU(unsigned long, print_timestamp);
 static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
 
 static int __read_mostly did_panic;
-unsigned long __read_mostly softlockup_thresh = 60;
+int __read_mostly softlockup_thresh = 60;
+
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * soft-lockup occurs:
+ */
+unsigned int __read_mostly softlockup_panic =
+                                CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
+
+static int __init softlockup_panic_setup(char *str)
+{
+        softlockup_panic = simple_strtoul(str, NULL, 0);
+
+        return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
 
 static int
 softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
@@ -84,6 +100,14 @@ void softlockup_tick(void)
         struct pt_regs *regs = get_irq_regs();
         unsigned long now;
 
+        /* Is detection switched off? */
+        if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) {
+                /* Be sure we don't false trigger if switched back on */
+                if (touch_timestamp)
+                        per_cpu(touch_timestamp, this_cpu) = 0;
+                return;
+        }
+
         if (touch_timestamp == 0) {
                 __touch_softlockup_watchdog();
                 return;
@@ -92,11 +116,8 @@ void softlockup_tick(void)
         print_timestamp = per_cpu(print_timestamp, this_cpu);
 
         /* report at most once a second */
-        if ((print_timestamp >= touch_timestamp &&
-                        print_timestamp < (touch_timestamp + 1)) ||
-                        did_panic || !per_cpu(watchdog_task, this_cpu)) {
+        if (print_timestamp == touch_timestamp || did_panic)
                 return;
-        }
 
         /* do not print during early bootup: */
         if (unlikely(system_state != SYSTEM_RUNNING)) {
@@ -106,8 +127,11 @@ void softlockup_tick(void)
 
         now = get_timestamp(this_cpu);
 
-        /* Wake up the high-prio watchdog task every second: */
-        if (now > (touch_timestamp + 1))
+        /*
+         * Wake up the high-prio watchdog task twice per
+         * threshold timespan.
+         */
+        if (now > touch_timestamp + softlockup_thresh/2)
                 wake_up_process(per_cpu(watchdog_task, this_cpu));
 
         /* Warn about unreasonable delays: */
@@ -121,11 +145,15 @@ void softlockup_tick(void)
                         this_cpu, now - touch_timestamp,
                         current->comm, task_pid_nr(current));
         print_modules();
+        print_irqtrace_events(current);
         if (regs)
                 show_regs(regs);
         else
                 dump_stack();
         spin_unlock(&print_lock);
+
+        if (softlockup_panic)
+                panic("softlockup: hung tasks");
 }
 
 /*
@@ -178,6 +206,9 @@ static void check_hung_task(struct task_struct *t, unsigned long now)
 
         t->last_switch_timestamp = now;
         touch_nmi_watchdog();
+
+        if (softlockup_panic)
+                panic("softlockup: blocked tasks");
 }
 
 /*
@@ -202,7 +233,8 @@ static void check_hung_uninterruptible_tasks(int this_cpu)
         do_each_thread(g, t) {
                 if (!--max_count)
                         goto unlock;
-                if (t->state & TASK_UNINTERRUPTIBLE)
+                /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
+                if (t->state == TASK_UNINTERRUPTIBLE)
                         check_hung_task(t, now);
         } while_each_thread(g, t);
  unlock:
@@ -307,14 +339,33 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
         .notifier_call = cpu_callback
 };
 
-__init void spawn_softlockup_task(void)
+static int __initdata nosoftlockup;
+
+static int __init nosoftlockup_setup(char *str)
+{
+        nosoftlockup = 1;
+        return 1;
+}
+__setup("nosoftlockup", nosoftlockup_setup);
+
+static int __init spawn_softlockup_task(void)
 {
         void *cpu = (void *)(long)smp_processor_id();
-        int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+        int err;
+
+        if (nosoftlockup)
+                return 0;
 
-        BUG_ON(err == NOTIFY_BAD);
+        err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+        if (err == NOTIFY_BAD) {
+                BUG();
+                return 1;
+        }
         cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
         register_cpu_notifier(&cpu_nfb);
 
         atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+        return 0;
 }
+early_initcall(spawn_softlockup_task);
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index a1fb54c93cdd..29ab20749dd3 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -290,8 +290,8 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
         spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
         LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 }
-
 EXPORT_SYMBOL(_spin_lock_nested);
+
 unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
 {
         unsigned long flags;
@@ -311,9 +311,17 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas
 #endif
         return flags;
 }
-
 EXPORT_SYMBOL(_spin_lock_irqsave_nested);
 
+void __lockfunc _spin_lock_nest_lock(spinlock_t *lock,
+                                     struct lockdep_map *nest_lock)
+{
+        preempt_disable();
+        spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+        LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+EXPORT_SYMBOL(_spin_lock_nest_lock);
+
 #endif
 
 void __lockfunc _spin_unlock(spinlock_t *lock)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index ba9b2054ecbd..af3c7cea258b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,4 +1,4 @@
-/* Copyright 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
+/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
  * GPL v2 and any later version.
  */
 #include <linux/cpu.h>
@@ -13,203 +13,177 @@
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
 
-/* Since we effect priority and affinity (both of which are visible
- * to, and settable by outside processes) we do indirection via a
- * kthread. */
-
-/* Thread to stop each CPU in user context. */
+/* This controls the threads on each CPU. */
 enum stopmachine_state {
-        STOPMACHINE_WAIT,
+        /* Dummy starting state for thread. */
+        STOPMACHINE_NONE,
+        /* Awaiting everyone to be scheduled. */
         STOPMACHINE_PREPARE,
+        /* Disable interrupts. */
         STOPMACHINE_DISABLE_IRQ,
+        /* Run the function */
+        STOPMACHINE_RUN,
+        /* Exit */
         STOPMACHINE_EXIT,
 };
+static enum stopmachine_state state;
 
-static enum stopmachine_state stopmachine_state;
-static unsigned int stopmachine_num_threads;
-static atomic_t stopmachine_thread_ack;
-
-static int stopmachine(void *cpu)
-{
-        int irqs_disabled = 0;
-        int prepared = 0;
-
-        set_cpus_allowed_ptr(current, &cpumask_of_cpu((int)(long)cpu));
-
-        /* Ack: we are alive */
-        smp_mb(); /* Theoretically the ack = 0 might not be on this CPU yet. */
-        atomic_inc(&stopmachine_thread_ack);
-
-        /* Simple state machine */
-        while (stopmachine_state != STOPMACHINE_EXIT) {
-                if (stopmachine_state == STOPMACHINE_DISABLE_IRQ 
-                    && !irqs_disabled) {
-                        local_irq_disable();
-                        hard_irq_disable();
-                        irqs_disabled = 1;
-                        /* Ack: irqs disabled. */
-                        smp_mb(); /* Must read state first. */
-                        atomic_inc(&stopmachine_thread_ack);
-                } else if (stopmachine_state == STOPMACHINE_PREPARE
-                           && !prepared) {
-                        /* Everyone is in place, hold CPU. */
-                        preempt_disable();
-                        prepared = 1;
-                        smp_mb(); /* Must read state first. */
-                        atomic_inc(&stopmachine_thread_ack);
-                }
-                /* Yield in first stage: migration threads need to
-                 * help our sisters onto their CPUs. */
-                if (!prepared && !irqs_disabled)
-                        yield();
-                cpu_relax();
-        }
-
-        /* Ack: we are exiting. */
-        smp_mb(); /* Must read state first. */
-        atomic_inc(&stopmachine_thread_ack);
-
-        if (irqs_disabled)
-                local_irq_enable();
-        if (prepared)
-                preempt_enable();
+struct stop_machine_data {
+        int (*fn)(void *);
+        void *data;
+        int fnret;
+};
 
-        return 0;
-}
+/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+static unsigned int num_threads;
+static atomic_t thread_ack;
+static struct completion finished;
+static DEFINE_MUTEX(lock);
 
-/* Change the thread state */
-static void stopmachine_set_state(enum stopmachine_state state)
+static void set_state(enum stopmachine_state newstate)
 {
-        atomic_set(&stopmachine_thread_ack, 0);
+        /* Reset ack counter. */
+        atomic_set(&thread_ack, num_threads);
         smp_wmb();
-        stopmachine_state = state;
-        while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads)
-                cpu_relax();
+        state = newstate;
 }
 
-static int stop_machine(void)
+/* Last one to ack a state moves to the next state. */
+static void ack_state(void)
 {
-        int i, ret = 0;
-
-        atomic_set(&stopmachine_thread_ack, 0);
-        stopmachine_num_threads = 0;
-        stopmachine_state = STOPMACHINE_WAIT;
-
-        for_each_online_cpu(i) {
-                if (i == raw_smp_processor_id())
-                        continue;
-                ret = kernel_thread(stopmachine, (void *)(long)i,CLONE_KERNEL);
-                if (ret < 0)
-                        break;
-                stopmachine_num_threads++;
-        }
-
-        /* Wait for them all to come to life. */
-        while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads) {
-                yield();
-                cpu_relax();
+        if (atomic_dec_and_test(&thread_ack)) {
+                /* If we're the last one to ack the EXIT, we're finished. */
+                if (state == STOPMACHINE_EXIT)
+                        complete(&finished);
+                else
+                        set_state(state + 1);
         }
+}
 
-        /* If some failed, kill them all. */
-        if (ret < 0) {
-                stopmachine_set_state(STOPMACHINE_EXIT);
-                return ret;
-        }
+/* This is the actual thread which stops the CPU.  It exits by itself rather
+ * than waiting for kthread_stop(), because it's easier for hotplug CPU. */
+static int stop_cpu(struct stop_machine_data *smdata)
+{
+        enum stopmachine_state curstate = STOPMACHINE_NONE;
 
-        /* Now they are all started, make them hold the CPUs, ready. */
-        preempt_disable();
-        stopmachine_set_state(STOPMACHINE_PREPARE);
+        /* Simple state machine */
+        do {
+                /* Chill out and ensure we re-read stopmachine_state. */
+                cpu_relax();
+                if (state != curstate) {
+                        curstate = state;
+                        switch (curstate) {
+                        case STOPMACHINE_DISABLE_IRQ:
+                                local_irq_disable();
+                                hard_irq_disable();
+                                break;
+                        case STOPMACHINE_RUN:
+                                /* |= allows error detection if functions on
+                                 * multiple CPUs. */
+                                smdata->fnret |= smdata->fn(smdata->data);
+                                break;
+                        default:
+                                break;
+                        }
+                        ack_state();
+                }
+        } while (curstate != STOPMACHINE_EXIT);
 
-        /* Make them disable irqs. */
-        local_irq_disable();
-        hard_irq_disable();
-        stopmachine_set_state(STOPMACHINE_DISABLE_IRQ);
+        local_irq_enable();
+        do_exit(0);
+}
 
+/* Callback for CPUs which aren't supposed to do anything. */
+static int chill(void *unused)
+{
         return 0;
 }
 
-static void restart_machine(void)
+int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
 {
-        stopmachine_set_state(STOPMACHINE_EXIT);
-        local_irq_enable();
-        preempt_enable_no_resched();
-}
+        int i, err;
+        struct stop_machine_data active, idle;
+        struct task_struct **threads;
+
+        active.fn = fn;
+        active.data = data;
+        active.fnret = 0;
+        idle.fn = chill;
+        idle.data = NULL;
+
+        /* This could be too big for stack on large machines. */
+        threads = kcalloc(NR_CPUS, sizeof(threads[0]), GFP_KERNEL);
+        if (!threads)
+                return -ENOMEM;
+
+        /* Set up initial state. */
+        mutex_lock(&lock);
+        init_completion(&finished);
+        num_threads = num_online_cpus();
+        set_state(STOPMACHINE_PREPARE);
 
-struct stop_machine_data {
-        int (*fn)(void *);
-        void *data;
-        struct completion done;
-};
+        for_each_online_cpu(i) {
+                struct stop_machine_data *smdata = &idle;
+                struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 
-static int do_stop(void *_smdata)
-{
-        struct stop_machine_data *smdata = _smdata;
-        int ret;
+                if (!cpus) {
+                        if (i == first_cpu(cpu_online_map))
+                                smdata = &active;
+                } else {
+                        if (cpu_isset(i, *cpus))
+                                smdata = &active;
+                }
 
-        ret = stop_machine();
-        if (ret == 0) {
-                ret = smdata->fn(smdata->data);
-                restart_machine();
-        }
+                threads[i] = kthread_create((void *)stop_cpu, smdata, "kstop%u",
+                                            i);
+                if (IS_ERR(threads[i])) {
+                        err = PTR_ERR(threads[i]);
+                        threads[i] = NULL;
+                        goto kill_threads;
+                }
 
-        /* We're done: you can kthread_stop us now */
-        complete(&smdata->done);
+                /* Place it onto correct cpu. */
+                kthread_bind(threads[i], i);
 
-        /* Wait for kthread_stop */
-        set_current_state(TASK_INTERRUPTIBLE);
-        while (!kthread_should_stop()) {
-                schedule();
-                set_current_state(TASK_INTERRUPTIBLE);
+                /* Make it highest prio. */
+                if (sched_setscheduler_nocheck(threads[i], SCHED_FIFO, &param))
+                        BUG();
         }
-        __set_current_state(TASK_RUNNING);
-        return ret;
-}
 
-struct task_struct *__stop_machine_run(int (*fn)(void *), void *data,
-                                       unsigned int cpu)
-{
-        static DEFINE_MUTEX(stopmachine_mutex);
-        struct stop_machine_data smdata;
-        struct task_struct *p;
+        /* We've created all the threads.  Wake them all: hold this CPU so one
+         * doesn't hit this CPU until we're ready. */
+        get_cpu();
+        for_each_online_cpu(i)
+                wake_up_process(threads[i]);
 
-        smdata.fn = fn;
-        smdata.data = data;
-        init_completion(&smdata.done);
+        /* This will release the thread on our CPU. */
+        put_cpu();
+        wait_for_completion(&finished);
+        mutex_unlock(&lock);
 
-        mutex_lock(&stopmachine_mutex);
+        kfree(threads);
 
-        /* If they don't care which CPU fn runs on, bind to any online one. */
-        if (cpu == NR_CPUS)
-                cpu = raw_smp_processor_id();
+        return active.fnret;
 
-        p = kthread_create(do_stop, &smdata, "kstopmachine");
-        if (!IS_ERR(p)) {
-                struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+kill_threads:
+        for_each_online_cpu(i)
+                if (threads[i])
+                        kthread_stop(threads[i]);
+        mutex_unlock(&lock);
 
-                /* One high-prio thread per cpu.  We'll do this one. */
-                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
-                kthread_bind(p, cpu);
-                wake_up_process(p);
-                wait_for_completion(&smdata.done);
-        }
-        mutex_unlock(&stopmachine_mutex);
-        return p;
+        kfree(threads);
+        return err;
 }
 
-int stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu)
+int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
 {
-        struct task_struct *p;
         int ret;
 
         /* No CPUs can come up or down during this. */
         get_online_cpus();
-        p = __stop_machine_run(fn, data, cpu);
-        if (!IS_ERR(p))
-                ret = kthread_stop(p);
-        else
-                ret = PTR_ERR(p);
+        ret = __stop_machine(fn, data, cpus);
         put_online_cpus();
 
         return ret;
 }
-EXPORT_SYMBOL_GPL(stop_machine_run);
+EXPORT_SYMBOL_GPL(stop_machine);
diff --git a/kernel/sys.c b/kernel/sys.c
index 14e97282eb6c..038a7bc0901d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -169,9 +169,9 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
                                 pgrp = find_vpid(who);
                         else
                                 pgrp = task_pgrp(current);
-                        do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+                        do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
                                 error = set_one_prio(p, niceval, error);
-                        } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+                        } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
                         break;
                 case PRIO_USER:
                         user = current->user;
@@ -229,11 +229,11 @@ asmlinkage long sys_getpriority(int which, int who)
                                 pgrp = find_vpid(who);
                         else
                                 pgrp = task_pgrp(current);
-                        do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+                        do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
                                 niceval = 20 - task_nice(p);
                                 if (niceval > retval)
                                         retval = niceval;
-                        } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+                        } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
                         break;
                 case PRIO_USER:
                         user = current->user;
@@ -274,7 +274,7 @@ void emergency_restart(void)
 }
 EXPORT_SYMBOL_GPL(emergency_restart);
 
-static void kernel_restart_prepare(char *cmd)
+void kernel_restart_prepare(char *cmd)
 {
         blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
         system_state = SYSTEM_RESTART;
@@ -301,26 +301,6 @@ void kernel_restart(char *cmd)
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
 
-/**
- *      kernel_kexec - reboot the system
- *
- *      Move into place and start executing a preloaded standalone
- *      executable.  If nothing was preloaded return an error.
- */
-static void kernel_kexec(void)
-{
-#ifdef CONFIG_KEXEC
-        struct kimage *image;
-        image = xchg(&kexec_image, NULL);
-        if (!image)
-                return;
-        kernel_restart_prepare(NULL);
-        printk(KERN_EMERG "Starting new kernel\n");
-        machine_shutdown();
-        machine_kexec(image);
-#endif
-}
-
 static void kernel_shutdown_prepare(enum system_states state)
 {
         blocking_notifier_call_chain(&reboot_notifier_list,
@@ -425,10 +405,15 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
                 kernel_restart(buffer);
                 break;
 
+#ifdef CONFIG_KEXEC
         case LINUX_REBOOT_CMD_KEXEC:
-                kernel_kexec();
-                unlock_kernel();
-                return -EINVAL;
+                {
+                        int ret;
+                        ret = kernel_kexec();
+                        unlock_kernel();
+                        return ret;
+                }
+#endif
 
 #ifdef CONFIG_HIBERNATION
         case LINUX_REBOOT_CMD_SW_SUSPEND:
@@ -1343,8 +1328,6 @@ EXPORT_SYMBOL(in_egroup_p);
 
 DECLARE_RWSEM(uts_sem);
 
-EXPORT_SYMBOL(uts_sem);
-
 asmlinkage long sys_newuname(struct new_utsname __user * name)
 {
         int errno = 0;
@@ -1795,7 +1778,7 @@ int orderly_poweroff(bool force)
                 goto out;
         }
 
-        info = call_usermodehelper_setup(argv[0], argv, envp);
+        info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
         if (info == NULL) {
                 argv_free(argv);
                 goto out;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 5b9b467de070..08d6e1bb99ac 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -31,6 +31,7 @@ cond_syscall(sys_socketpair);
 cond_syscall(sys_bind);
 cond_syscall(sys_listen);
 cond_syscall(sys_accept);
+cond_syscall(sys_paccept);
 cond_syscall(sys_connect);
 cond_syscall(sys_getsockname);
 cond_syscall(sys_getpeername);
@@ -56,9 +57,11 @@ cond_syscall(compat_sys_set_robust_list);
 cond_syscall(sys_get_robust_list);
 cond_syscall(compat_sys_get_robust_list);
 cond_syscall(sys_epoll_create);
+cond_syscall(sys_epoll_create1);
 cond_syscall(sys_epoll_ctl);
 cond_syscall(sys_epoll_wait);
 cond_syscall(sys_epoll_pwait);
+cond_syscall(compat_sys_epoll_pwait);
 cond_syscall(sys_semget);
 cond_syscall(sys_semop);
 cond_syscall(sys_semtimedop);
@@ -94,6 +97,7 @@ cond_syscall(sys_keyctl);
 cond_syscall(compat_sys_keyctl);
 cond_syscall(compat_sys_socketcall);
 cond_syscall(sys_inotify_init);
+cond_syscall(sys_inotify_init1);
 cond_syscall(sys_inotify_add_watch);
 cond_syscall(sys_inotify_rm_watch);
 cond_syscall(sys_migrate_pages);
@@ -154,10 +158,13 @@ cond_syscall(sys_ioprio_get);
 
 /* New file descriptors */
 cond_syscall(sys_signalfd);
+cond_syscall(sys_signalfd4);
 cond_syscall(compat_sys_signalfd);
+cond_syscall(compat_sys_signalfd4);
 cond_syscall(sys_timerfd_create);
 cond_syscall(sys_timerfd_settime);
 cond_syscall(sys_timerfd_gettime);
 cond_syscall(compat_sys_timerfd_settime);
 cond_syscall(compat_sys_timerfd_gettime);
 cond_syscall(sys_eventfd);
+cond_syscall(sys_eventfd2);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6b16e16428d8..50ec0886fa3d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -43,6 +43,7 @@
 #include <linux/limits.h>
 #include <linux/dcache.h>
 #include <linux/syscalls.h>
+#include <linux/vmstat.h>
 #include <linux/nfs_fs.h>
 #include <linux/acpi.h>
 #include <linux/reboot.h>
@@ -80,7 +81,6 @@ extern int sysctl_drop_caches;
 extern int percpu_pagelist_fraction;
 extern int compat_log;
 extern int maps_protect;
-extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifdef CONFIG_RCU_TORTURE_TEST
@@ -88,12 +88,13 @@ extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
-#if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
+#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP)
 static int one = 1;
 #endif
 
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 static int sixty = 60;
+static int neg_one = -1;
 #endif
 
 #ifdef CONFIG_MMU
@@ -110,7 +111,7 @@ static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
 extern char modprobe_path[];
 #endif
 #ifdef CONFIG_CHR_DEV_SG
@@ -158,13 +159,15 @@ static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
+        .count = 1,
         .ctl_table = root_table,
-        .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.header_list),
+        .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
         .root = &sysctl_table_root,
+        .set = &sysctl_table_root.default_set,
 };
 static struct ctl_table_root sysctl_table_root = {
         .root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
-        .header_list = LIST_HEAD_INIT(root_table_header.ctl_entry),
+        .default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry),
 };
 
 static struct ctl_table kern_table[];
@@ -475,7 +478,7 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &ftrace_enable_sysctl,
         },
 #endif
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
         {
                 .ctl_name       = KERN_MODPROBE,
                 .procname       = "modprobe",
@@ -623,7 +626,7 @@ static struct ctl_table kern_table[] = {
         {
                 .ctl_name       = KERN_PRINTK_RATELIMIT,
                 .procname       = "printk_ratelimit",
-                .data           = &printk_ratelimit_jiffies,
+                .data           = &printk_ratelimit_state.interval,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec_jiffies,
@@ -632,7 +635,7 @@ static struct ctl_table kern_table[] = {
         {
                 .ctl_name       = KERN_PRINTK_RATELIMIT_BURST,
                 .procname       = "printk_ratelimit_burst",
-                .data           = &printk_ratelimit_burst,
+                .data           = &printk_ratelimit_state.burst,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
@@ -739,13 +742,24 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_DETECT_SOFTLOCKUP
         {
                 .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "softlockup_panic",
+                .data           = &softlockup_panic,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "softlockup_thresh",
                 .data           = &softlockup_thresh,
-                .maxlen         = sizeof(unsigned long),
+                .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
+                .proc_handler   = &proc_dointvec_minmax,
                 .strategy       = &sysctl_intvec,
-                .extra1         = &one,
+                .extra1         = &neg_one,
                 .extra2         = &sixty,
         },
         {
@@ -947,7 +961,7 @@ static struct ctl_table vm_table[] = {
 #ifdef CONFIG_HUGETLB_PAGE
          {
                 .procname       = "nr_hugepages",
-                .data           = &max_huge_pages,
+                .data           = NULL,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
                 .proc_handler   = &hugetlb_sysctl_handler,
@@ -973,10 +987,12 @@ static struct ctl_table vm_table[] = {
         {
                 .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nr_overcommit_hugepages",
-                .data           = &sysctl_overcommit_huge_pages,
-                .maxlen         = sizeof(sysctl_overcommit_huge_pages),
+                .data           = NULL,
+                .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
                 .proc_handler   = &hugetlb_overcommit_handler,
+                .extra1         = (void *)&hugetlb_zero,
+                .extra2         = (void *)&hugetlb_infinity,
         },
 #endif
         {
@@ -1372,6 +1388,9 @@ static void start_unregistering(struct ctl_table_header *p)
                 spin_unlock(&sysctl_lock);
                 wait_for_completion(&wait);
                 spin_lock(&sysctl_lock);
+        } else {
+                /* anything non-NULL; we'll never dereference it */
+                p->unregistering = ERR_PTR(-EINVAL);
         }
         /*
          * do not remove from the list until nobody holds it; walking the
@@ -1380,6 +1399,32 @@ static void start_unregistering(struct ctl_table_header *p)
         list_del_init(&p->ctl_entry);
 }
 
+void sysctl_head_get(struct ctl_table_header *head)
+{
+        spin_lock(&sysctl_lock);
+        head->count++;
+        spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+        spin_lock(&sysctl_lock);
+        if (!--head->count)
+                kfree(head);
+        spin_unlock(&sysctl_lock);
+}
+
+struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+        if (!head)
+                BUG();
+        spin_lock(&sysctl_lock);
+        if (!use_table(head))
+                head = ERR_PTR(-ENOENT);
+        spin_unlock(&sysctl_lock);
+        return head;
+}
+
 void sysctl_head_finish(struct ctl_table_header *head)
 {
         if (!head)
@@ -1389,14 +1434,20 @@ void sysctl_head_finish(struct ctl_table_header *head)
         spin_unlock(&sysctl_lock);
 }
 
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+        struct ctl_table_set *set = &root->default_set;
+        if (root->lookup)
+                set = root->lookup(root, namespaces);
+        return set;
+}
+
 static struct list_head *
 lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
 {
-        struct list_head *header_list;
-        header_list = &root->header_list;
-        if (root->lookup)
-                header_list = root->lookup(root, namespaces);
-        return header_list;
+        struct ctl_table_set *set = lookup_header_set(root, namespaces);
+        return &set->list;
 }
 
 struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
@@ -1466,9 +1517,9 @@ static int do_sysctl_strategy(struct ctl_table_root *root,
         int op = 0, rc;
 
         if (oldval)
-                op |= 004;
+                op |= MAY_READ;
         if (newval)
-                op |= 002;
+                op |= MAY_WRITE;
         if (sysctl_perm(root, table, op))
                 return -EPERM;
 
@@ -1510,7 +1561,7 @@ repeat:
                 if (n == table->ctl_name) {
                         int error;
                         if (table->child) {
-                                if (sysctl_perm(root, table, 001))
+                                if (sysctl_perm(root, table, MAY_EXEC))
                                         return -EPERM;
                                 name++;
                                 nlen--;
@@ -1585,7 +1636,7 @@ static int test_perm(int mode, int op)
                 mode >>= 6;
         else if (in_egroup_p(0))
                 mode >>= 3;
-        if ((mode & op & 0007) == op)
+        if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
                 return 0;
         return -EACCES;
 }
@@ -1595,7 +1646,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
         int error;
         int mode;
 
-        error = security_sysctl(table, op);
+        error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
         if (error)
                 return error;
 
@@ -1630,6 +1681,54 @@ static __init int sysctl_init(void)
 
 core_initcall(sysctl_init);
 
+static struct ctl_table *is_branch_in(struct ctl_table *branch,
+                                      struct ctl_table *table)
+{
+        struct ctl_table *p;
+        const char *s = branch->procname;
+
+        /* branch should have named subdirectory as its first element */
+        if (!s || !branch->child)
+                return NULL;
+
+        /* ... and nothing else */
+        if (branch[1].procname || branch[1].ctl_name)
+                return NULL;
+
+        /* table should contain subdirectory with the same name */
+        for (p = table; p->procname || p->ctl_name; p++) {
+                if (!p->child)
+                        continue;
+                if (p->procname && strcmp(p->procname, s) == 0)
+                        return p;
+        }
+        return NULL;
+}
+
+/* see if attaching q to p would be an improvement */
+static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
+{
+        struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
+        struct ctl_table *next;
+        int is_better = 0;
+        int not_in_parent = !p->attached_by;
+
+        while ((next = is_branch_in(by, to)) != NULL) {
+                if (by == q->attached_by)
+                        is_better = 1;
+                if (to == p->attached_by)
+                        not_in_parent = 1;
+                by = by->child;
+                to = next->child;
+        }
+
+        if (is_better && not_in_parent) {
+                q->attached_by = by;
+                q->attached_to = to;
+                q->parent = p;
+        }
+}
+
 /**
  * __register_sysctl_paths - register a sysctl hierarchy
  * @root: List of sysctl headers to register on
@@ -1706,10 +1805,10 @@ struct ctl_table_header *__register_sysctl_paths(
         struct nsproxy *namespaces,
         const struct ctl_path *path, struct ctl_table *table)
 {
-        struct list_head *header_list;
         struct ctl_table_header *header;
         struct ctl_table *new, **prevp;
         unsigned int n, npath;
+        struct ctl_table_set *set;
 
         /* Count the path components */
         for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath)
@@ -1751,6 +1850,7 @@ struct ctl_table_header *__register_sysctl_paths(
         header->unregistering = NULL;
         header->root = root;
         sysctl_set_parent(NULL, header->ctl_table);
+        header->count = 1;
 #ifdef CONFIG_SYSCTL_SYSCALL_CHECK
         if (sysctl_check_table(namespaces, header->ctl_table)) {
                 kfree(header);
@@ -1758,8 +1858,20 @@ struct ctl_table_header *__register_sysctl_paths(
         }
 #endif
         spin_lock(&sysctl_lock);
-        header_list = lookup_header_list(root, namespaces);
-        list_add_tail(&header->ctl_entry, header_list);
+        header->set = lookup_header_set(root, namespaces);
+        header->attached_by = header->ctl_table;
+        header->attached_to = root_table;
+        header->parent = &root_table_header;
+        for (set = header->set; set; set = set->parent) {
+                struct ctl_table_header *p;
+                list_for_each_entry(p, &set->list, ctl_entry) {
+                        if (p->unregistering)
+                                continue;
+                        try_attach(p, header);
+                }
+        }
+        header->parent->count++;
+        list_add_tail(&header->ctl_entry, &header->set->list);
         spin_unlock(&sysctl_lock);
 
         return header;
@@ -1814,8 +1926,37 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 
         spin_lock(&sysctl_lock);
         start_unregistering(header);
+        if (!--header->parent->count) {
+                WARN_ON(1);
+                kfree(header->parent);
+        }
+        if (!--header->count)
+                kfree(header);
+        spin_unlock(&sysctl_lock);
+}
+
+int sysctl_is_seen(struct ctl_table_header *p)
+{
+        struct ctl_table_set *set = p->set;
+        int res;
+        spin_lock(&sysctl_lock);
+        if (p->unregistering)
+                res = 0;
+        else if (!set->is_seen)
+                res = 1;
+        else
+                res = set->is_seen(set);
         spin_unlock(&sysctl_lock);
-        kfree(header);
+        return res;
+}
+
+void setup_sysctl_set(struct ctl_table_set *p,
+        struct ctl_table_set *parent,
+        int (*is_seen)(struct ctl_table_set *))
+{
+        INIT_LIST_HEAD(&p->list);
+        p->parent = parent ? parent : &sysctl_table_root.default_set;
+        p->is_seen = is_seen;
 }
 
 #else /* !CONFIG_SYSCTL */
@@ -1834,6 +1975,16 @@ void unregister_sysctl_table(struct ctl_table_header * table)
 {
 }
 
+void setup_sysctl_set(struct ctl_table_set *p,
+        struct ctl_table_set *parent,
+        int (*is_seen)(struct ctl_table_set *))
+{
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+}
+
 #endif /* CONFIG_SYSCTL */
 
 /*
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index c09350d564f2..c35da23ab8fb 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -1532,6 +1532,8 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
                         sysctl_check_leaf(namespaces, table, &fail);
                 }
                 sysctl_check_bin_path(table, &fail);
+                if (table->mode > 0777)
+                        set_fail(&fail, table, "bogus .mode");
                 if (fail) {
                         set_fail(&fail, table, NULL);
                         error = -EINVAL;
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 4a23517169a6..bd6be76303cf 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -35,7 +35,7 @@
  */
 #define TASKSTATS_CPUMASK_MAXLEN        (100+6*NR_CPUS)
 
-static DEFINE_PER_CPU(__u32, taskstats_seqnum) = { 0 };
+static DEFINE_PER_CPU(__u32, taskstats_seqnum);
 static int family_registered;
 struct kmem_cache *taskstats_cache;
 
@@ -301,7 +301,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
                 return -EINVAL;
 
         if (isadd == REGISTER) {
-                for_each_cpu_mask(cpu, mask) {
+                for_each_cpu_mask_nr(cpu, mask) {
                         s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
                                          cpu_to_node(cpu));
                         if (!s)
@@ -320,7 +320,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
 
         /* Deregister or cleanup */
 cleanup:
-        for_each_cpu_mask(cpu, mask) {
+        for_each_cpu_mask_nr(cpu, mask) {
                 listeners = &per_cpu(listener_array, cpu);
                 down_write(&listeners->sem);
                 list_for_each_entry_safe(s, tmp, &listeners->list, list) {
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 3d1e3e1a1971..f8d968063cea 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -72,6 +72,16 @@ void clockevents_set_mode(struct clock_event_device *dev,
 }
 
 /**
+ * clockevents_shutdown - shutdown the device and clear next_event
+ * @dev:        device to shutdown
+ */
+void clockevents_shutdown(struct clock_event_device *dev)
+{
+        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+        dev->next_event.tv64 = KTIME_MAX;
+}
+
+/**
  * clockevents_program_event - Reprogram the clock event device.
  * @expires:    absolute expiry time (monotonic clock)
  *
@@ -177,7 +187,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 /*
  * Noop handler when we shut down an event device
  */
-static void clockevents_handle_noop(struct clock_event_device *dev)
+void clockevents_handle_noop(struct clock_event_device *dev)
 {
 }
 
@@ -199,7 +209,6 @@ void clockevents_exchange_device(struct clock_event_device *old,
          * released list and do a notify add later.
          */
         if (old) {
-                old->event_handler = clockevents_handle_noop;
                 clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
                 list_del(&old->list);
                 list_add(&old->list, &clockevents_released);
@@ -207,7 +216,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 
         if (new) {
                 BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
-                clockevents_set_mode(new, CLOCK_EVT_MODE_SHUTDOWN);
+                clockevents_shutdown(new);
         }
         local_irq_restore(flags);
 }
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index dadde5361f32..093d4acf993b 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -145,9 +145,9 @@ static void clocksource_watchdog(unsigned long data)
                  * Cycle through CPUs to check if the CPUs stay
                  * synchronized to each other.
                  */
-                int next_cpu = next_cpu(raw_smp_processor_id(), cpu_online_map);
+                int next_cpu = next_cpu_nr(raw_smp_processor_id(), cpu_online_map);
 
-                if (next_cpu >= NR_CPUS)
+                if (next_cpu >= nr_cpu_ids)
                         next_cpu = first_cpu(cpu_online_map);
                 watchdog_timer.expires += WATCHDOG_INTERVAL;
                 add_timer_on(&watchdog_timer, next_cpu);
@@ -376,7 +376,8 @@ void clocksource_unregister(struct clocksource *cs)
  * Provides sysfs interface for listing current clocksource.
  */
 static ssize_t
-sysfs_show_current_clocksources(struct sys_device *dev, char *buf)
+sysfs_show_current_clocksources(struct sys_device *dev,
+                                struct sysdev_attribute *attr, char *buf)
 {
         ssize_t count = 0;
 
@@ -397,6 +398,7 @@ sysfs_show_current_clocksources(struct sys_device *dev, char *buf)
  * clocksource selction.
  */
 static ssize_t sysfs_override_clocksource(struct sys_device *dev,
+                                          struct sysdev_attribute *attr,
                                           const char *buf, size_t count)
 {
         struct clocksource *ovr = NULL;
@@ -449,7 +451,9 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
  * Provides sysfs interface for listing registered clocksources
  */
 static ssize_t
-sysfs_show_available_clocksources(struct sys_device *dev, char *buf)
+sysfs_show_available_clocksources(struct sys_device *dev,
+                                  struct sysdev_attribute *attr,
+                                  char *buf)
 {
         struct clocksource *src;
         ssize_t count = 0;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5125ddd8196b..1ad46f3df6e7 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -245,7 +245,7 @@ static void sync_cmos_clock(unsigned long dummy)
         if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
                 fail = update_persistent_clock(now);
 
-        next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec;
+        next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
         if (next.tv_nsec <= 0)
                 next.tv_nsec += NSEC_PER_SEC;
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f48d0f09d32f..bd7034542399 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -175,6 +175,8 @@ static void tick_do_periodic_broadcast(void)
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
+        ktime_t next;
+
         tick_do_periodic_broadcast();
 
         /*
@@ -185,10 +187,13 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 
         /*
          * Setup the next period for devices, which do not have
-         * periodic mode:
+         * periodic mode. We read dev->next_event first and add to it
+         * when the event alrady expired. clockevents_program_event()
+         * sets dev->next_event only when the event is really
+         * programmed to the device.
          */
-        for (;;) {
-                ktime_t next = ktime_add(dev->next_event, tick_period);
+        for (next = dev->next_event; ;) {
+                next = ktime_add(next, tick_period);
 
                 if (!clockevents_program_event(dev, next, ktime_get()))
                         return;
@@ -205,7 +210,7 @@ static void tick_do_broadcast_on_off(void *why)
         struct clock_event_device *bc, *dev;
         struct tick_device *td;
         unsigned long flags, *reason = why;
-        int cpu;
+        int cpu, bc_stopped;
 
         spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -223,14 +228,15 @@ static void tick_do_broadcast_on_off(void *why)
         if (!tick_device_is_functional(dev))
                 goto out;
 
+        bc_stopped = cpus_empty(tick_broadcast_mask);
+
         switch (*reason) {
         case CLOCK_EVT_NOTIFY_BROADCAST_ON:
         case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
                 if (!cpu_isset(cpu, tick_broadcast_mask)) {
                         cpu_set(cpu, tick_broadcast_mask);
-                        if (td->mode == TICKDEV_MODE_PERIODIC)
-                                clockevents_set_mode(dev,
-                                                     CLOCK_EVT_MODE_SHUTDOWN);
+                        if (bc->mode == TICKDEV_MODE_PERIODIC)
+                                clockevents_shutdown(dev);
                 }
                 if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
                         tick_broadcast_force = 1;
@@ -239,15 +245,16 @@ static void tick_do_broadcast_on_off(void *why)
                 if (!tick_broadcast_force &&
                     cpu_isset(cpu, tick_broadcast_mask)) {
                         cpu_clear(cpu, tick_broadcast_mask);
-                        if (td->mode == TICKDEV_MODE_PERIODIC)
+                        if (bc->mode == TICKDEV_MODE_PERIODIC)
                                 tick_setup_periodic(dev, 0);
                 }
                 break;
         }
 
-        if (cpus_empty(tick_broadcast_mask))
-                clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
-        else {
+        if (cpus_empty(tick_broadcast_mask)) {
+                if (!bc_stopped)
+                        clockevents_shutdown(bc);
+        } else if (bc_stopped) {
                 if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
                         tick_broadcast_start_periodic(bc);
                 else
@@ -298,7 +305,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
         if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
                 if (bc && cpus_empty(tick_broadcast_mask))
-                        clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+                        clockevents_shutdown(bc);
         }
 
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
@@ -313,7 +320,7 @@ void tick_suspend_broadcast(void)
 
         bc = tick_broadcast_device.evtdev;
         if (bc)
-                clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+                clockevents_shutdown(bc);
 
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
@@ -364,16 +371,8 @@ cpumask_t *tick_get_broadcast_oneshot_mask(void)
 static int tick_broadcast_set_event(ktime_t expires, int force)
 {
         struct clock_event_device *bc = tick_broadcast_device.evtdev;
-        ktime_t now = ktime_get();
-        int res;
-
-        for(;;) {
-                res = clockevents_program_event(bc, expires, now);
-                if (!res || !force)
-                        return res;
-                now = ktime_get();
-                expires = ktime_add(now, ktime_set(0, bc->min_delta_ns));
-        }
+
+        return tick_dev_program_event(bc, expires, force);
 }
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -399,8 +398,7 @@ again:
         mask = CPU_MASK_NONE;
         now = ktime_get();
         /* Find all expired events */
-        for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
-             cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+        for_each_cpu_mask_nr(cpu, tick_broadcast_oneshot_mask) {
                 td = &per_cpu(tick_cpu_device, cpu);
                 if (td->evtdev->next_event.tv64 <= now.tv64)
                         cpu_set(cpu, mask);
@@ -492,14 +490,52 @@ static void tick_broadcast_clear_oneshot(int cpu)
         cpu_clear(cpu, tick_broadcast_oneshot_mask);
 }
 
+static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+{
+        struct tick_device *td;
+        int cpu;
+
+        for_each_cpu_mask_nr(cpu, *mask) {
+                td = &per_cpu(tick_cpu_device, cpu);
+                if (td->evtdev)
+                        td->evtdev->next_event = expires;
+        }
+}
+
 /**
  * tick_broadcast_setup_oneshot - setup the broadcast device
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
-        bc->event_handler = tick_handle_oneshot_broadcast;
-        clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-        bc->next_event.tv64 = KTIME_MAX;
+        /* Set it up only once ! */
+        if (bc->event_handler != tick_handle_oneshot_broadcast) {
+                int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+                int cpu = smp_processor_id();
+                cpumask_t mask;
+
+                bc->event_handler = tick_handle_oneshot_broadcast;
+                clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
+                /* Take the do_timer update */
+                tick_do_timer_cpu = cpu;
+
+                /*
+                 * We must be careful here. There might be other CPUs
+                 * waiting for periodic broadcast. We need to set the
+                 * oneshot_mask bits for those and program the
+                 * broadcast device to fire.
+                 */
+                mask = tick_broadcast_mask;
+                cpu_clear(cpu, mask);
+                cpus_or(tick_broadcast_oneshot_mask,
+                        tick_broadcast_oneshot_mask, mask);
+
+                if (was_periodic && !cpus_empty(mask)) {
+                        tick_broadcast_init_next_event(&mask, tick_next_period);
+                        tick_broadcast_set_event(tick_next_period, 1);
+                } else
+                        bc->next_event.tv64 = KTIME_MAX;
+        }
 }
 
 /*
@@ -539,4 +575,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+/*
+ * Check, whether the broadcast device is in one shot mode
+ */
+int tick_broadcast_oneshot_active(void)
+{
+        return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
+}
+
 #endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 4f3886562b8c..df12434b43ca 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
  */
 ktime_t tick_next_period;
 ktime_t tick_period;
-int tick_do_timer_cpu __read_mostly = -1;
+int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
 DEFINE_SPINLOCK(tick_device_lock);
 
 /*
@@ -109,7 +109,8 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
         if (!tick_device_is_functional(dev))
                 return;
 
-        if (dev->features & CLOCK_EVT_FEAT_PERIODIC) {
+        if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+            !tick_broadcast_oneshot_active()) {
                 clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
         } else {
                 unsigned long seq;
@@ -135,7 +136,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
  */
 static void tick_setup_device(struct tick_device *td,
                               struct clock_event_device *newdev, int cpu,
-                              cpumask_t cpumask)
+                              const cpumask_t *cpumask)
 {
         ktime_t next_event;
         void (*handler)(struct clock_event_device *) = NULL;
@@ -148,7 +149,7 @@ static void tick_setup_device(struct tick_device *td,
                  * If no cpu took the do_timer update, assign it to
                  * this cpu:
                  */
-                if (tick_do_timer_cpu == -1) {
+                if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
                         tick_do_timer_cpu = cpu;
                         tick_next_period = ktime_get();
                         tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
@@ -161,6 +162,7 @@ static void tick_setup_device(struct tick_device *td,
         } else {
                 handler = td->evtdev->event_handler;
                 next_event = td->evtdev->next_event;
+                td->evtdev->event_handler = clockevents_handle_noop;
         }
 
         td->evtdev = newdev;
@@ -169,8 +171,8 @@ static void tick_setup_device(struct tick_device *td,
          * When the device is not per cpu, pin the interrupt to the
          * current cpu:
          */
-        if (!cpus_equal(newdev->cpumask, cpumask))
-                irq_set_affinity(newdev->irq, cpumask);
+        if (!cpus_equal(newdev->cpumask, *cpumask))
+                irq_set_affinity(newdev->irq, *cpumask);
 
         /*
          * When global broadcasting is active, check if the current
@@ -196,7 +198,6 @@ static int tick_check_new_device(struct clock_event_device *newdev)
         struct tick_device *td;
         int cpu, ret = NOTIFY_OK;
         unsigned long flags;
-        cpumask_t cpumask;
 
         spin_lock_irqsave(&tick_device_lock, flags);
 
@@ -206,10 +207,9 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 
         td = &per_cpu(tick_cpu_device, cpu);
         curdev = td->evtdev;
-        cpumask = cpumask_of_cpu(cpu);
 
         /* cpu local device ? */
-        if (!cpus_equal(newdev->cpumask, cpumask)) {
+        if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) {
 
                 /*
                  * If the cpu affinity of the device interrupt can not
@@ -222,7 +222,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
                  * If we have a cpu local device already, do not replace it
                  * by a non cpu local device
                  */
-                if (curdev && cpus_equal(curdev->cpumask, cpumask))
+                if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu)))
                         goto out_bc;
         }
 
@@ -250,11 +250,11 @@ static int tick_check_new_device(struct clock_event_device *newdev)
          * not give it back to the clockevents layer !
          */
         if (tick_is_broadcast_device(curdev)) {
-                clockevents_set_mode(curdev, CLOCK_EVT_MODE_SHUTDOWN);
+                clockevents_shutdown(curdev);
                 curdev = NULL;
         }
         clockevents_exchange_device(curdev, newdev);
-        tick_setup_device(td, newdev, cpu, cpumask);
+        tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu));
         if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
                 tick_oneshot_notify();
 
@@ -301,7 +301,8 @@ static void tick_shutdown(unsigned int *cpup)
         if (*cpup == tick_do_timer_cpu) {
                 int cpu = first_cpu(cpu_online_map);
 
-                tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : -1;
+                tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu :
+                        TICK_DO_TIMER_NONE;
         }
         spin_unlock_irqrestore(&tick_device_lock, flags);
 }
@@ -312,7 +313,7 @@ static void tick_suspend(void)
         unsigned long flags;
 
         spin_lock_irqsave(&tick_device_lock, flags);
-        clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+        clockevents_shutdown(td->evtdev);
         spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f13f2b7f4fd4..469248782c23 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,10 @@
 /*
  * tick internal variable and functions used by low/high res code
  */
+
+#define TICK_DO_TIMER_NONE      -1
+#define TICK_DO_TIMER_BOOT      -2
+
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 extern spinlock_t tick_device_lock;
 extern ktime_t tick_next_period;
@@ -10,6 +14,8 @@ extern int tick_do_timer_cpu __read_mostly;
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
 
+extern void clockevents_shutdown(struct clock_event_device *dev);
+
 /*
  * NO_HZ / high resolution timer shared code
  */
@@ -17,6 +23,8 @@ extern void tick_handle_periodic(struct clock_event_device *dev);
 extern void tick_setup_oneshot(struct clock_event_device *newdev,
                                void (*handler)(struct clock_event_device *),
                                ktime_t nextevt);
+extern int tick_dev_program_event(struct clock_event_device *dev,
+                                  ktime_t expires, int force);
 extern int tick_program_event(ktime_t expires, int force);
 extern void tick_oneshot_notify(void);
 extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
@@ -27,6 +35,7 @@ extern void tick_broadcast_oneshot_control(unsigned long reason);
 extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+extern int tick_broadcast_oneshot_active(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -35,6 +44,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */
@@ -64,6 +74,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
         return 0;
 }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
 #endif /* !TICK_ONESHOT */
 
 /*
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 450c04935b66..2e8de678e767 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -23,24 +23,56 @@
 #include "tick-internal.h"
 
 /**
- * tick_program_event
+ * tick_program_event internal worker function
  */
-int tick_program_event(ktime_t expires, int force)
+int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
+                           int force)
 {
-        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
         ktime_t now = ktime_get();
+        int i;
 
-        while (1) {
+        for (i = 0;;) {
                 int ret = clockevents_program_event(dev, expires, now);
 
                 if (!ret || !force)
                         return ret;
+
+                /*
+                 * We tried 2 times to program the device with the given
+                 * min_delta_ns. If that's not working then we double it
+                 * and emit a warning.
+                 */
+                if (++i > 2) {
+                        /* Increase the min. delta and try again */
+                        if (!dev->min_delta_ns)
+                                dev->min_delta_ns = 5000;
+                        else
+                                dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+                        printk(KERN_WARNING
+                               "CE: %s increasing min_delta_ns to %lu nsec\n",
+                               dev->name ? dev->name : "?",
+                               dev->min_delta_ns << 1);
+
+                        i = 0;
+                }
+
                 now = ktime_get();
-                expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+                expires = ktime_add_ns(now, dev->min_delta_ns);
         }
 }
 
 /**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+        return tick_dev_program_event(dev, expires, force);
+}
+
+/**
  * tick_resume_onshot - resume oneshot mode
  */
 void tick_resume_oneshot(void)
@@ -61,7 +93,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 {
         newdev->event_handler = handler;
         clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
-        clockevents_program_event(newdev, next_event, ktime_get());
+        tick_dev_program_event(newdev, next_event, 1);
 }
 
 /**
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index beef7ccdf842..39019b3f7621 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -75,6 +75,9 @@ static void tick_do_update_jiffies64(ktime_t now)
                                                            incr * ticks);
                 }
                 do_timer(++ticks);
+
+                /* Keep the tick_next_period variable up to date */
+                tick_next_period = ktime_add(last_jiffies_update, tick_period);
         }
         write_sequnlock(&xtime_lock);
 }
@@ -140,8 +143,6 @@ void tick_nohz_update_jiffies(void)
         if (!ts->tick_stopped)
                 return;
 
-        touch_softlockup_watchdog();
-
         cpu_clear(cpu, nohz_cpu_mask);
         now = ktime_get();
         ts->idle_waketime = now;
@@ -149,6 +150,8 @@ void tick_nohz_update_jiffies(void)
         local_irq_save(flags);
         tick_do_update_jiffies64(now);
         local_irq_restore(flags);
+
+        touch_softlockup_watchdog();
 }
 
 void tick_nohz_stop_idle(int cpu)
@@ -162,6 +165,8 @@ void tick_nohz_stop_idle(int cpu)
                 ts->idle_lastupdate = now;
                 ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
                 ts->idle_active = 0;
+
+                sched_clock_idle_wakeup_event(0);
         }
 }
 
@@ -177,6 +182,7 @@ static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
         }
         ts->idle_entrytime = now;
         ts->idle_active = 1;
+        sched_clock_idle_sleep_event();
         return now;
 }
 
@@ -195,7 +201,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
  * Called either from the idle loop or from irq_exit() when an idle period was
  * just interrupted by an interrupt which did not cause a reschedule.
  */
-void tick_nohz_stop_sched_tick(void)
+void tick_nohz_stop_sched_tick(int inidle)
 {
         unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
         struct tick_sched *ts;
@@ -218,12 +224,17 @@ void tick_nohz_stop_sched_tick(void)
          */
         if (unlikely(!cpu_online(cpu))) {
                 if (cpu == tick_do_timer_cpu)
-                        tick_do_timer_cpu = -1;
+                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
         }
 
         if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
                 goto end;
 
+        if (!inidle && !ts->inidle)
+                goto end;
+
+        ts->inidle = 1;
+
         if (need_resched())
                 goto end;
 
@@ -284,7 +295,6 @@ void tick_nohz_stop_sched_tick(void)
                         ts->tick_stopped = 1;
                         ts->idle_jiffies = last_jiffies;
                         rcu_enter_nohz();
-                        sched_clock_tick_stop(cpu);
                 }
 
                 /*
@@ -296,7 +306,7 @@ void tick_nohz_stop_sched_tick(void)
                  * invoked.
                  */
                 if (cpu == tick_do_timer_cpu)
-                        tick_do_timer_cpu = -1;
+                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
 
                 ts->idle_sleeps++;
 
@@ -373,18 +383,20 @@ void tick_nohz_restart_sched_tick(void)
         local_irq_disable();
         tick_nohz_stop_idle(cpu);
 
-        if (!ts->tick_stopped) {
+        if (!ts->inidle || !ts->tick_stopped) {
+                ts->inidle = 0;
                 local_irq_enable();
                 return;
         }
 
+        ts->inidle = 0;
+
         rcu_exit_nohz();
 
         /* Update jiffies first */
         select_nohz_load_balancer(0);
         now = ktime_get();
         tick_do_update_jiffies64(now);
-        sched_clock_tick_start(cpu);
         cpu_clear(cpu, nohz_cpu_mask);
 
         /*
@@ -459,7 +471,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
          * this duty, then the jiffies update is still serialized by
          * xtime_lock.
          */
-        if (unlikely(tick_do_timer_cpu == -1))
+        if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
                 tick_do_timer_cpu = cpu;
 
         /* Check, if the jiffies need an update */
@@ -561,7 +573,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
          * this duty, then the jiffies update is still serialized by
          * xtime_lock.
          */
-        if (unlikely(tick_do_timer_cpu == -1))
+        if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
                 tick_do_timer_cpu = cpu;
 #endif
 
@@ -637,17 +649,21 @@ void tick_setup_sched_timer(void)
                 ts->nohz_mode = NOHZ_MODE_HIGHRES;
 #endif
 }
+#endif /* HIGH_RES_TIMERS */
 
+#if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS
 void tick_cancel_sched_timer(int cpu)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
+# ifdef CONFIG_HIGH_RES_TIMERS
         if (ts->sched_timer.base)
                 hrtimer_cancel(&ts->sched_timer);
+# endif
 
         ts->nohz_mode = NOHZ_MODE_INACTIVE;
 }
-#endif /* HIGH_RES_TIMERS */
+#endif
 
 /**
  * Async notification about clocksource changes
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4231a3dc224a..f6e3af31b403 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -587,7 +587,7 @@ static int __ftrace_modify_code(void *data)
 
 static void ftrace_run_update_code(int command)
 {
-        stop_machine_run(__ftrace_modify_code, &command, NR_CPUS);
+        stop_machine(__ftrace_modify_code, &command, NULL);
 }
 
 void ftrace_disable_daemon(void)
@@ -787,7 +787,7 @@ static int ftrace_update_code(void)
             !ftrace_enabled || !ftraced_trigger)
                 return 0;
 
-        stop_machine_run(__ftrace_update_code, NULL, NR_CPUS);
+        stop_machine(__ftrace_update_code, NULL, NULL);
 
         return 1;
 }
@@ -1564,7 +1564,7 @@ static int __init ftrace_dynamic_init(void)
 
         addr = (unsigned long)ftrace_record_ip;
 
-        stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS);
+        stop_machine(ftrace_dyn_arch_init, &addr, NULL);
 
         /* ftrace_dyn_arch_init places the return code in addr */
         if (addr) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 868e121c8e38..8f3fb3db61c3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1183,7 +1183,6 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 {
         struct trace_iterator *iter = m->private;
-        void *last_ent = iter->ent;
         int i = (int)*pos;
         void *ent;
 
@@ -1203,9 +1202,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
         iter->pos = *pos;
 
-        if (last_ent && !ent)
-                seq_puts(m, "\n\nvim:ft=help\n");
-
         return ent;
 }
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 421d6fe3650e..ece6cfb649fa 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -253,12 +253,14 @@ void start_critical_timings(void)
         if (preempt_trace() || irq_trace())
                 start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
+EXPORT_SYMBOL_GPL(start_critical_timings);
 
 void stop_critical_timings(void)
 {
         if (preempt_trace() || irq_trace())
                 stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
+EXPORT_SYMBOL_GPL(stop_critical_timings);
 
 #ifdef CONFIG_IRQSOFF_TRACER
 #ifdef CONFIG_PROVE_LOCKING
@@ -337,12 +339,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller);
 #ifdef CONFIG_PREEMPT_TRACER
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-        stop_critical_timing(a0, a1);
+        if (preempt_trace())
+                stop_critical_timing(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-        start_critical_timing(a0, a1);
+        if (preempt_trace())
+                start_critical_timing(a0, a1);
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3c8d61df4474..e303ccb62cdf 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -26,7 +26,8 @@ static struct task_struct	*wakeup_task;
 static int                      wakeup_cpu;
 static unsigned                 wakeup_prio = -1;
 
-static DEFINE_SPINLOCK(wakeup_lock);
+static raw_spinlock_t wakeup_lock =
+        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 
 static void __wakeup_reset(struct trace_array *tr);
 
@@ -56,7 +57,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
         if (unlikely(disabled != 1))
                 goto out;
 
-        spin_lock_irqsave(&wakeup_lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&wakeup_lock);
 
         if (unlikely(!wakeup_task))
                 goto unlock;
@@ -71,7 +73,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
         trace_function(tr, data, ip, parent_ip, flags);
 
  unlock:
-        spin_unlock_irqrestore(&wakeup_lock, flags);
+        __raw_spin_unlock(&wakeup_lock);
+        local_irq_restore(flags);
 
  out:
         atomic_dec(&data->disabled);
@@ -145,7 +148,8 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
         if (likely(disabled != 1))
                 goto out;
 
-        spin_lock_irqsave(&wakeup_lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&wakeup_lock);
 
         /* We could race with grabbing wakeup_lock */
         if (unlikely(!tracer_enabled || next != wakeup_task))
@@ -174,7 +178,8 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
 
 out_unlock:
         __wakeup_reset(tr);
-        spin_unlock_irqrestore(&wakeup_lock, flags);
+        __raw_spin_unlock(&wakeup_lock);
+        local_irq_restore(flags);
 out:
         atomic_dec(&tr->data[cpu]->disabled);
 }
@@ -209,8 +214,6 @@ static void __wakeup_reset(struct trace_array *tr)
         struct trace_array_cpu *data;
         int cpu;
 
-        assert_spin_locked(&wakeup_lock);
-
         for_each_possible_cpu(cpu) {
                 data = tr->data[cpu];
                 tracing_reset(data);
@@ -229,9 +232,11 @@ static void wakeup_reset(struct trace_array *tr)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&wakeup_lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&wakeup_lock);
         __wakeup_reset(tr);
-        spin_unlock_irqrestore(&wakeup_lock, flags);
+        __raw_spin_unlock(&wakeup_lock);
+        local_irq_restore(flags);
 }
 
 static void
@@ -252,7 +257,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p,
                 goto out;
 
         /* interrupts should be off from try_to_wake_up */
-        spin_lock(&wakeup_lock);
+        __raw_spin_lock(&wakeup_lock);
 
         /* check for races. */
         if (!tracer_enabled || p->prio >= wakeup_prio)
@@ -274,7 +279,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p,
                        CALLER_ADDR1, CALLER_ADDR2, flags);
 
 out_locked:
-        spin_unlock(&wakeup_lock);
+        __raw_spin_unlock(&wakeup_lock);
 out:
         atomic_dec(&tr->data[cpu]->disabled);
 }
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 2301e1e7c606..bb948e52ce20 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -161,7 +161,7 @@ static void timer_notify(struct pt_regs *regs, int cpu)
                 __trace_special(tr, data, 2, regs->ip, 0);
 
                 while (i < sample_max_depth) {
-                        frame.next_fp = 0;
+                        frame.next_fp = NULL;
                         frame.return_address = 0;
                         if (!copy_stack_frame(fp, &frame))
                                 break;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 4ab1b584961b..8ebcd8532dfb 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -28,14 +28,14 @@
 void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 {
         struct timespec uptime, ts;
-        s64 ac_etime;
+        u64 ac_etime;
 
         BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
 
         /* calculate task elapsed time in timespec */
         do_posix_clock_monotonic_gettime(&uptime);
         ts = timespec_sub(uptime, tsk->start_time);
-        /* rebase elapsed time to usec */
+        /* rebase elapsed time to usec (should never be negative) */
         ac_etime = timespec_to_ns(&ts);
         do_div(ac_etime, NSEC_PER_USEC);
         stats->ac_etime = ac_etime;
@@ -84,9 +84,9 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 {
         struct mm_struct *mm;
 
-        /* convert pages-jiffies to Mbyte-usec */
-        stats->coremem = jiffies_to_usecs(p->acct_rss_mem1) * PAGE_SIZE / MB;
-        stats->virtmem = jiffies_to_usecs(p->acct_vm_mem1) * PAGE_SIZE / MB;
+        /* convert pages-usec to Mbyte-usec */
+        stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB;
+        stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB;
         mm = get_task_mm(p);
         if (mm) {
                 /* adjust to KB unit */
@@ -94,10 +94,10 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
                 stats->hiwater_vm    = mm->hiwater_vm * PAGE_SIZE / KB;
                 mmput(mm);
         }
-        stats->read_char        = p->rchar;
-        stats->write_char       = p->wchar;
-        stats->read_syscalls    = p->syscr;
-        stats->write_syscalls   = p->syscw;
+        stats->read_char        = p->ioac.rchar;
+        stats->write_char       = p->ioac.wchar;
+        stats->read_syscalls    = p->ioac.syscr;
+        stats->write_syscalls   = p->ioac.syscw;
 #ifdef CONFIG_TASK_IO_ACCOUNTING
         stats->read_bytes       = p->ioac.read_bytes;
         stats->write_bytes      = p->ioac.write_bytes;
@@ -118,12 +118,19 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 void acct_update_integrals(struct task_struct *tsk)
 {
         if (likely(tsk->mm)) {
-                long delta = cputime_to_jiffies(
-                        cputime_sub(tsk->stime, tsk->acct_stimexpd));
+                cputime_t time, dtime;
+                struct timeval value;
+                u64 delta;
+
+                time = tsk->stime + tsk->utime;
+                dtime = cputime_sub(time, tsk->acct_timexpd);
+                jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
+                delta = value.tv_sec;
+                delta = delta * USEC_PER_SEC + value.tv_usec;
 
                 if (delta == 0)
                         return;
-                tsk->acct_stimexpd = tsk->stime;
+                tsk->acct_timexpd = time;
                 tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
                 tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
         }
@@ -135,7 +142,7 @@ void acct_update_integrals(struct task_struct *tsk)
  */
 void acct_clear_integrals(struct task_struct *tsk)
 {
-        tsk->acct_stimexpd = 0;
+        tsk->acct_timexpd = 0;
         tsk->acct_rss_mem1 = 0;
         tsk->acct_vm_mem1 = 0;
 }
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index a9ab0596de44..532858fa5b88 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 64d398f12444..815237a55af8 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -12,7 +12,6 @@
 #include <linux/module.h>
 #include <linux/uts.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index fe3a56c2256d..4ab9659d269e 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -12,7 +12,6 @@
 #include <linux/module.h>
 #include <linux/uts.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/sysctl.h>
 
 static void *get_uts(ctl_table *table, int write)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ce7799540c91..4048e92aa04f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -125,7 +125,7 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
 }
 
 static void insert_work(struct cpu_workqueue_struct *cwq,
-                                struct work_struct *work, int tail)
+                        struct work_struct *work, struct list_head *head)
 {
         set_wq_data(work, cwq);
         /*
@@ -133,21 +133,17 @@ static void insert_work(struct cpu_workqueue_struct *cwq,
          * result of list_add() below, see try_to_grab_pending().
          */
         smp_wmb();
-        if (tail)
-                list_add_tail(&work->entry, &cwq->worklist);
-        else
-                list_add(&work->entry, &cwq->worklist);
+        list_add_tail(&work->entry, head);
         wake_up(&cwq->more_work);
 }
 
-/* Preempt must be disabled. */
 static void __queue_work(struct cpu_workqueue_struct *cwq,
                          struct work_struct *work)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&cwq->lock, flags);
-        insert_work(cwq, work, 1);
+        insert_work(cwq, work, &cwq->worklist);
         spin_unlock_irqrestore(&cwq->lock, flags);
 }
 
@@ -163,17 +159,39 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
  */
 int queue_work(struct workqueue_struct *wq, struct work_struct *work)
 {
+        int ret;
+
+        ret = queue_work_on(get_cpu(), wq, work);
+        put_cpu();
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(queue_work);
+
+/**
+ * queue_work_on - queue work on specific cpu
+ * @cpu: CPU number to execute work on
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * Returns 0 if @work was already on a queue, non-zero otherwise.
+ *
+ * We queue the work to a specific CPU, the caller must ensure it
+ * can't go away.
+ */
+int
+queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
+{
         int ret = 0;
 
         if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
                 BUG_ON(!list_empty(&work->entry));
-                __queue_work(wq_per_cpu(wq, get_cpu()), work);
-                put_cpu();
+                __queue_work(wq_per_cpu(wq, cpu), work);
                 ret = 1;
         }
         return ret;
 }
-EXPORT_SYMBOL_GPL(queue_work);
+EXPORT_SYMBOL_GPL(queue_work_on);
 
 static void delayed_work_timer_fn(unsigned long __data)
 {
@@ -272,11 +290,11 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
 
                 BUG_ON(get_wq_data(work) != cwq);
                 work_clear_pending(work);
-                lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-                lock_acquire(&lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+                lock_map_acquire(&cwq->wq->lockdep_map);
+                lock_map_acquire(&lockdep_map);
                 f(work);
-                lock_release(&lockdep_map, 1, _THIS_IP_);
-                lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+                lock_map_release(&lockdep_map);
+                lock_map_release(&cwq->wq->lockdep_map);
 
                 if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
                         printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
@@ -337,14 +355,14 @@ static void wq_barrier_func(struct work_struct *work)
 }
 
 static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
-                                        struct wq_barrier *barr, int tail)
+                        struct wq_barrier *barr, struct list_head *head)
 {
         INIT_WORK(&barr->work, wq_barrier_func);
         __set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
 
         init_completion(&barr->done);
 
-        insert_work(cwq, &barr->work, tail);
+        insert_work(cwq, &barr->work, head);
 }
 
 static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
@@ -364,7 +382,7 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
                 active = 0;
                 spin_lock_irq(&cwq->lock);
                 if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
-                        insert_wq_barrier(cwq, &barr, 1);
+                        insert_wq_barrier(cwq, &barr, &cwq->worklist);
                         active = 1;
                 }
                 spin_unlock_irq(&cwq->lock);
@@ -395,13 +413,64 @@ void flush_workqueue(struct workqueue_struct *wq)
         int cpu;
 
         might_sleep();
-        lock_acquire(&wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&wq->lockdep_map, 1, _THIS_IP_);
-        for_each_cpu_mask(cpu, *cpu_map)
+        lock_map_acquire(&wq->lockdep_map);
+        lock_map_release(&wq->lockdep_map);
+        for_each_cpu_mask_nr(cpu, *cpu_map)
                 flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
+/**
+ * flush_work - block until a work_struct's callback has terminated
+ * @work: the work which is to be flushed
+ *
+ * Returns false if @work has already terminated.
+ *
+ * It is expected that, prior to calling flush_work(), the caller has
+ * arranged for the work to not be requeued, otherwise it doesn't make
+ * sense to use this function.
+ */
+int flush_work(struct work_struct *work)
+{
+        struct cpu_workqueue_struct *cwq;
+        struct list_head *prev;
+        struct wq_barrier barr;
+
+        might_sleep();
+        cwq = get_wq_data(work);
+        if (!cwq)
+                return 0;
+
+        lock_map_acquire(&cwq->wq->lockdep_map);
+        lock_map_release(&cwq->wq->lockdep_map);
+
+        prev = NULL;
+        spin_lock_irq(&cwq->lock);
+        if (!list_empty(&work->entry)) {
+                /*
+                 * See the comment near try_to_grab_pending()->smp_rmb().
+                 * If it was re-queued under us we are not going to wait.
+                 */
+                smp_rmb();
+                if (unlikely(cwq != get_wq_data(work)))
+                        goto out;
+                prev = &work->entry;
+        } else {
+                if (cwq->current_work != work)
+                        goto out;
+                prev = &cwq->worklist;
+        }
+        insert_wq_barrier(cwq, &barr, prev->next);
+out:
+        spin_unlock_irq(&cwq->lock);
+        if (!prev)
+                return 0;
+
+        wait_for_completion(&barr.done);
+        return 1;
+}
+EXPORT_SYMBOL_GPL(flush_work);
+
 /*
  * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
  * so this work can't be re-armed in any way.
@@ -449,7 +518,7 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
 
         spin_lock_irq(&cwq->lock);
         if (unlikely(cwq->current_work == work)) {
-                insert_wq_barrier(cwq, &barr, 0);
+                insert_wq_barrier(cwq, &barr, cwq->worklist.next);
                 running = 1;
         }
         spin_unlock_irq(&cwq->lock);
@@ -467,8 +536,8 @@ static void wait_on_work(struct work_struct *work)
 
         might_sleep();
 
-        lock_acquire(&work->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&work->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&work->lockdep_map);
+        lock_map_release(&work->lockdep_map);
 
         cwq = get_wq_data(work);
         if (!cwq)
@@ -477,7 +546,7 @@ static void wait_on_work(struct work_struct *work)
         wq = cwq->wq;
         cpu_map = wq_cpu_map(wq);
 
-        for_each_cpu_mask(cpu, *cpu_map)
+        for_each_cpu_mask_nr(cpu, *cpu_map)
                 wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
 }
 
@@ -553,6 +622,19 @@ int schedule_work(struct work_struct *work)
 }
 EXPORT_SYMBOL(schedule_work);
 
+/*
+ * schedule_work_on - put work task on a specific cpu
+ * @cpu: cpu to put the work task on
+ * @work: job to be done
+ *
+ * This puts a job on a specific cpu
+ */
+int schedule_work_on(int cpu, struct work_struct *work)
+{
+        return queue_work_on(cpu, keventd_wq, work);
+}
+EXPORT_SYMBOL(schedule_work_on);
+
 /**
  * schedule_delayed_work - put work task in global workqueue after delay
  * @dwork: job to be done
@@ -607,10 +689,10 @@ int schedule_on_each_cpu(work_func_t func)
                 struct work_struct *work = per_cpu_ptr(works, cpu);
 
                 INIT_WORK(work, func);
-                set_bit(WORK_STRUCT_PENDING, work_data_bits(work));
-                __queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu), work);
+                schedule_work_on(cpu, work);
         }
-        flush_workqueue(keventd_wq);
+        for_each_online_cpu(cpu)
+                flush_work(per_cpu_ptr(works, cpu));
         put_online_cpus();
         free_percpu(works);
         return 0;
@@ -747,11 +829,22 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
                 err = create_workqueue_thread(cwq, singlethread_cpu);
                 start_workqueue_thread(cwq, -1);
         } else {
-                get_online_cpus();
+                cpu_maps_update_begin();
+                /*
+                 * We must place this wq on list even if the code below fails.
+                 * cpu_down(cpu) can remove cpu from cpu_populated_map before
+                 * destroy_workqueue() takes the lock, in that case we leak
+                 * cwq[cpu]->thread.
+                 */
                 spin_lock(&workqueue_lock);
                 list_add(&wq->list, &workqueues);
                 spin_unlock(&workqueue_lock);
-
+                /*
+                 * We must initialize cwqs for each possible cpu even if we
+                 * are going to call destroy_workqueue() finally. Otherwise
+                 * cpu_up() can hit the uninitialized cwq once we drop the
+                 * lock.
+                 */
                 for_each_possible_cpu(cpu) {
                         cwq = init_cpu_workqueue(wq, cpu);
                         if (err || !cpu_online(cpu))
@@ -759,7 +852,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
                         err = create_workqueue_thread(cwq, cpu);
                         start_workqueue_thread(cwq, cpu);
                 }
-                put_online_cpus();
+                cpu_maps_update_done();
         }
 
         if (err) {
@@ -773,18 +866,18 @@ EXPORT_SYMBOL_GPL(__create_workqueue_key);
 static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
 {
         /*
-         * Our caller is either destroy_workqueue() or CPU_DEAD,
-         * get_online_cpus() protects cwq->thread.
+         * Our caller is either destroy_workqueue() or CPU_POST_DEAD,
+         * cpu_add_remove_lock protects cwq->thread.
          */
         if (cwq->thread == NULL)
                 return;
 
-        lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&cwq->wq->lockdep_map);
+        lock_map_release(&cwq->wq->lockdep_map);
 
         flush_cpu_workqueue(cwq);
         /*
-         * If the caller is CPU_DEAD and cwq->worklist was not empty,
+         * If the caller is CPU_POST_DEAD and cwq->worklist was not empty,
          * a concurrent flush_workqueue() can insert a barrier after us.
          * However, in that case run_workqueue() won't return and check
          * kthread_should_stop() until it flushes all work_struct's.
@@ -808,14 +901,14 @@ void destroy_workqueue(struct workqueue_struct *wq)
         const cpumask_t *cpu_map = wq_cpu_map(wq);
         int cpu;
 
-        get_online_cpus();
+        cpu_maps_update_begin();
         spin_lock(&workqueue_lock);
         list_del(&wq->list);
         spin_unlock(&workqueue_lock);
 
-        for_each_cpu_mask(cpu, *cpu_map)
+        for_each_cpu_mask_nr(cpu, *cpu_map)
                 cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
-        put_online_cpus();
+        cpu_maps_update_done();
 
         free_percpu(wq->cpu_wq);
         kfree(wq);
@@ -829,6 +922,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
         unsigned int cpu = (unsigned long)hcpu;
         struct cpu_workqueue_struct *cwq;
         struct workqueue_struct *wq;
+        int ret = NOTIFY_OK;
 
         action &= ~CPU_TASKS_FROZEN;
 
@@ -836,7 +930,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
         case CPU_UP_PREPARE:
                 cpu_set(cpu, cpu_populated_map);
         }
-
+undo:
         list_for_each_entry(wq, &workqueues, list) {
                 cwq = per_cpu_ptr(wq->cpu_wq, cpu);
 
@@ -846,7 +940,9 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
                                 break;
                         printk(KERN_ERR "workqueue [%s] for %i failed\n",
                                 wq->name, cpu);
-                        return NOTIFY_BAD;
+                        action = CPU_UP_CANCELED;
+                        ret = NOTIFY_BAD;
+                        goto undo;
 
                 case CPU_ONLINE:
                         start_workqueue_thread(cwq, cpu);
@@ -854,7 +950,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
                 case CPU_UP_CANCELED:
                         start_workqueue_thread(cwq, -1);
-                case CPU_DEAD:
+                case CPU_POST_DEAD:
                         cleanup_workqueue_thread(cwq);
                         break;
                 }
@@ -862,11 +958,11 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
         switch (action) {
         case CPU_UP_CANCELED:
-        case CPU_DEAD:
+        case CPU_POST_DEAD:
                 cpu_clear(cpu, cpu_populated_map);
         }
 
-        return NOTIFY_OK;
+        return ret;
 }
 
 void __init init_workqueues(void)