5 files changed, 54 insertions, 21 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/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/ptrace.c b/kernel/ptrace.c
index d2cf144d0af5..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;
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,