9 files changed, 115 insertions, 42 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ba42b0a76961..12815d3f1a05 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1977,6 +1977,39 @@ void cpuset_fork(struct task_struct *child)
  * We don't need to task_lock() this reference to tsk->cpuset,
  * because tsk is already marked PF_EXITING, so attach_task() won't
  * mess with it, or task is a failed fork, never visible to attach_task.
+ *
+ * Hack:
+ *
+ *    Set the exiting tasks cpuset to the root cpuset (top_cpuset).
+ *
+ *    Don't leave a task unable to allocate memory, as that is an
+ *    accident waiting to happen should someone add a callout in
+ *    do_exit() after the cpuset_exit() call that might allocate.
+ *    If a task tries to allocate memory with an invalid cpuset,
+ *    it will oops in cpuset_update_task_memory_state().
+ *
+ *    We call cpuset_exit() while the task is still competent to
+ *    handle notify_on_release(), then leave the task attached to
+ *    the root cpuset (top_cpuset) for the remainder of its exit.
+ *
+ *    To do this properly, we would increment the reference count on
+ *    top_cpuset, and near the very end of the kernel/exit.c do_exit()
+ *    code we would add a second cpuset function call, to drop that
+ *    reference.  This would just create an unnecessary hot spot on
+ *    the top_cpuset reference count, to no avail.
+ *
+ *    Normally, holding a reference to a cpuset without bumping its
+ *    count is unsafe.   The cpuset could go away, or someone could
+ *    attach us to a different cpuset, decrementing the count on
+ *    the first cpuset that we never incremented.  But in this case,
+ *    top_cpuset isn't going away, and either task has PF_EXITING set,
+ *    which wards off any attach_task() attempts, or task is a failed
+ *    fork, never visible to attach_task.
+ *
+ *    Another way to do this would be to set the cpuset pointer
+ *    to NULL here, and check in cpuset_update_task_memory_state()
+ *    for a NULL pointer.  This hack avoids that NULL check, for no
+ *    cost (other than this way too long comment ;).
  **/
 
 void cpuset_exit(struct task_struct *tsk)
@@ -1984,7 +2017,7 @@ void cpuset_exit(struct task_struct *tsk)
         struct cpuset *cs;
 
         cs = tsk->cpuset;
-        tsk->cpuset = NULL;
+        tsk->cpuset = &top_cpuset;      /* Hack - see comment above */
 
         if (notify_on_release(cs)) {
                 char *pathbuf = NULL;
diff --git a/kernel/fork.c b/kernel/fork.c
index 8e88b374cee9..fbea12d7a943 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1123,8 +1123,8 @@ static task_t *copy_process(unsigned long clone_flags,
                 p->real_parent = current;
         p->parent = p->real_parent;
 
+        spin_lock(&current->sighand->siglock);
         if (clone_flags & CLONE_THREAD) {
-                spin_lock(&current->sighand->siglock);
                 /*
                  * Important: if an exit-all has been started then
                  * do not create this new thread - the whole thread
@@ -1162,8 +1162,6 @@ static task_t *copy_process(unsigned long clone_flags,
                          */
                         p->it_prof_expires = jiffies_to_cputime(1);
                 }
-
-                spin_unlock(&current->sighand->siglock);
         }
 
         /*
@@ -1175,8 +1173,6 @@ static task_t *copy_process(unsigned long clone_flags,
         if (unlikely(p->ptrace & PT_PTRACED))
                 __ptrace_link(p, current->parent);
 
-        attach_pid(p, PIDTYPE_PID, p->pid);
-        attach_pid(p, PIDTYPE_TGID, p->tgid);
         if (thread_group_leader(p)) {
                 p->signal->tty = current->signal->tty;
                 p->signal->pgrp = process_group(current);
@@ -1186,9 +1182,12 @@ static task_t *copy_process(unsigned long clone_flags,
                 if (p->pid)
                         __get_cpu_var(process_counts)++;
         }
+        attach_pid(p, PIDTYPE_TGID, p->tgid);
+        attach_pid(p, PIDTYPE_PID, p->pid);
 
         nr_threads++;
         total_forks++;
+        spin_unlock(&current->sighand->siglock);
         write_unlock_irq(&tasklist_lock);
         proc_fork_connector(p);
         return p;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2b6e1757aedd..5ae51f1bc7c8 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -418,8 +418,19 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
         /* Switch the timer base, if necessary: */
         new_base = switch_hrtimer_base(timer, base);
 
-        if (mode == HRTIMER_REL)
+        if (mode == HRTIMER_REL) {
                 tim = ktime_add(tim, new_base->get_time());
+                /*
+                 * CONFIG_TIME_LOW_RES is a temporary way for architectures
+                 * to signal that they simply return xtime in
+                 * do_gettimeoffset(). In this case we want to round up by
+                 * resolution when starting a relative timer, to avoid short
+                 * timeouts. This will go away with the GTOD framework.
+                 */
+#ifdef CONFIG_TIME_LOW_RES
+                tim = ktime_add(tim, base->resolution);
+#endif
+        }
         timer->expires = tim;
 
         enqueue_hrtimer(timer, new_base);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 41f66365f0d8..8d5a5986d621 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -91,10 +91,8 @@ static int save_highmem_zone(struct zone *zone)
                  * corrected eventually when the cases giving rise to this
                  * are better understood.
                  */
-                if (PageReserved(page)) {
-                        printk("highmem reserved page?!\n");
+                if (PageReserved(page))
                         continue;
-                }
                 BUG_ON(PageNosave(page));
                 if (PageNosaveFree(page))
                         continue;
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 4e90905f0e87..2d9d08f72f76 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -153,13 +153,11 @@ static int swsusp_swap_check(void) /* This is called before saving image */
 {
         int i;
 
-        if (!swsusp_resume_device)
-                return -ENODEV;
         spin_lock(&swap_lock);
         for (i = 0; i < MAX_SWAPFILES; i++) {
                 if (!(swap_info[i].flags & SWP_WRITEOK))
                         continue;
-                if (is_resume_device(swap_info + i)) {
+                if (!swsusp_resume_device || is_resume_device(swap_info + i)) {
                         spin_unlock(&swap_lock);
                         root_swap = i;
                         return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 5f33cdb6fff5..d95a72c9279d 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -72,8 +72,8 @@ void ptrace_untrace(task_t *child)
  */
 void __ptrace_unlink(task_t *child)
 {
-        if (!child->ptrace)
-                BUG();
+        BUG_ON(!child->ptrace);
+
         child->ptrace = 0;
         if (!list_empty(&child->ptrace_list)) {
                 list_del_init(&child->ptrace_list);
@@ -184,22 +184,27 @@ bad:
         return retval;
 }
 
+void __ptrace_detach(struct task_struct *child, unsigned int data)
+{
+        child->exit_code = data;
+        /* .. re-parent .. */
+        __ptrace_unlink(child);
+        /* .. and wake it up. */
+        if (child->exit_state != EXIT_ZOMBIE)
+                wake_up_process(child);
+}
+
 int ptrace_detach(struct task_struct *child, unsigned int data)
 {
         if (!valid_signal(data))
-                return  -EIO;
+                return -EIO;
 
         /* Architecture-specific hardware disable .. */
         ptrace_disable(child);
 
-        /* .. re-parent .. */
-        child->exit_code = data;
-
         write_lock_irq(&tasklist_lock);
-        __ptrace_unlink(child);
-        /* .. and wake it up. */
-        if (child->exit_state != EXIT_ZOMBIE)
-                wake_up_process(child);
+        if (child->ptrace)
+                __ptrace_detach(child, data);
         write_unlock_irq(&tasklist_lock);
 
         return 0;
@@ -242,8 +247,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
                 if (write) {
                         copy_to_user_page(vma, page, addr,
                                           maddr + offset, buf, bytes);
-                        if (!PageCompound(page))
-                                set_page_dirty_lock(page);
+                        set_page_dirty_lock(page);
                 } else {
                         copy_from_user_page(vma, page, addr,
                                             buf, maddr + offset, bytes);
diff --git a/kernel/sched.c b/kernel/sched.c
index 87d93be336a1..12d291bf3379 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1204,9 +1204,6 @@ static int try_to_wake_up(task_t *p, unsigned int state, int sync)
                 }
         }
 
-        if (p->last_waker_cpu != this_cpu)
-                goto out_set_cpu;
-
         if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
                 goto out_set_cpu;
 
@@ -1277,8 +1274,6 @@ out_set_cpu:
                 cpu = task_cpu(p);
         }
 
-        p->last_waker_cpu = this_cpu;
-
 out_activate:
 #endif /* CONFIG_SMP */
         if (old_state == TASK_UNINTERRUPTIBLE) {
@@ -1360,12 +1355,9 @@ void fastcall sched_fork(task_t *p, int clone_flags)
 #ifdef CONFIG_SCHEDSTATS
         memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
-#if defined(CONFIG_SMP)
-        p->last_waker_cpu = cpu;
-#if defined(__ARCH_WANT_UNLOCKED_CTXSW)
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
         p->oncpu = 0;
 #endif
-#endif
 #ifdef CONFIG_PREEMPT
         /* Want to start with kernel preemption disabled. */
         task_thread_info(p)->preempt_count = 1;
@@ -5066,7 +5058,18 @@ static void init_sched_build_groups(struct sched_group groups[], cpumask_t span,
 #define MAX_DOMAIN_DISTANCE 32
 
 static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] =
-                { [ 0 ... MAX_DOMAIN_DISTANCE-1 ] = -1LL };
+                { [ 0 ... MAX_DOMAIN_DISTANCE-1 ] =
+/*
+ * Architectures may override the migration cost and thus avoid
+ * boot-time calibration. Unit is nanoseconds. Mostly useful for
+ * virtualized hardware:
+ */
+#ifdef CONFIG_DEFAULT_MIGRATION_COST
+                        CONFIG_DEFAULT_MIGRATION_COST
+#else
+                        -1LL
+#endif
+};
 
 /*
  * Allow override of migration cost - in units of microseconds.
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 71dd6f62efec..7654d55c47f5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -126,8 +126,6 @@ extern int sysctl_hz_timer;
 extern int acct_parm[];
 #endif
 
-int randomize_va_space = 1;
-
 static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t,
                        ctl_table *, void **);
 static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
diff --git a/kernel/timer.c b/kernel/timer.c
index b9dad3994676..fe3a9a9f8328 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -717,12 +717,16 @@ static void second_overflow(void)
 #endif
 }
 
-/* in the NTP reference this is called "hardclock()" */
-static void update_wall_time_one_tick(void)
+/*
+ * Returns how many microseconds we need to add to xtime this tick
+ * in doing an adjustment requested with adjtime.
+ */
+static long adjtime_adjustment(void)
 {
-        long time_adjust_step, delta_nsec;
+        long time_adjust_step;
 
-        if ((time_adjust_step = time_adjust) != 0 ) {
+        time_adjust_step = time_adjust;
+        if (time_adjust_step) {
                 /*
                  * We are doing an adjtime thing.  Prepare time_adjust_step to
                  * be within bounds.  Note that a positive time_adjust means we
@@ -733,10 +737,19 @@ static void update_wall_time_one_tick(void)
                  */
                 time_adjust_step = min(time_adjust_step, (long)tickadj);
                 time_adjust_step = max(time_adjust_step, (long)-tickadj);
+        }
+        return time_adjust_step;
+}
 
+/* in the NTP reference this is called "hardclock()" */
+static void update_wall_time_one_tick(void)
+{
+        long time_adjust_step, delta_nsec;
+
+        time_adjust_step = adjtime_adjustment();
+        if (time_adjust_step)
                 /* Reduce by this step the amount of time left  */
                 time_adjust -= time_adjust_step;
-        }
         delta_nsec = tick_nsec + time_adjust_step * 1000;
         /*
          * Advance the phase, once it gets to one microsecond, then
@@ -759,6 +772,22 @@ static void update_wall_time_one_tick(void)
 }
 
 /*
+ * Return how long ticks are at the moment, that is, how much time
+ * update_wall_time_one_tick will add to xtime next time we call it
+ * (assuming no calls to do_adjtimex in the meantime).
+ * The return value is in fixed-point nanoseconds with SHIFT_SCALE-10
+ * bits to the right of the binary point.
+ * This function has no side-effects.
+ */
+u64 current_tick_length(void)
+{
+        long delta_nsec;
+
+        delta_nsec = tick_nsec + adjtime_adjustment() * 1000;
+        return ((u64) delta_nsec << (SHIFT_SCALE - 10)) + time_adj;
+}
+
+/*
  * Using a loop looks inefficient, but "ticks" is
  * usually just one (we shouldn't be losing ticks,
  * we're doing this this way mainly for interrupt