7 files changed, 115 insertions, 78 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 72248d1b9e3f..ab81fdd4572b 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2231,19 +2231,25 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  * So only GFP_KERNEL allocations, if all nodes in the cpuset are
  * short of memory, might require taking the callback_mutex mutex.
  *
- * The first loop over the zonelist in mm/page_alloc.c:__alloc_pages()
- * calls here with __GFP_HARDWALL always set in gfp_mask, enforcing
- * hardwall cpusets - no allocation on a node outside the cpuset is
- * allowed (unless in interrupt, of course).
- *
- * The second loop doesn't even call here for GFP_ATOMIC requests
- * (if the __alloc_pages() local variable 'wait' is set).  That check
- * and the checks below have the combined affect in the second loop of
- * the __alloc_pages() routine that:
+ * The first call here from mm/page_alloc:get_page_from_freelist()
+ * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, so
+ * no allocation on a node outside the cpuset is allowed (unless in
+ * interrupt, of course).
+ *
+ * The second pass through get_page_from_freelist() doesn't even call
+ * here for GFP_ATOMIC calls.  For those calls, the __alloc_pages()
+ * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set
+ * in alloc_flags.  That logic and the checks below have the combined
+ * affect that:
  *      in_interrupt - any node ok (current task context irrelevant)
  *      GFP_ATOMIC   - any node ok
  *      GFP_KERNEL   - any node in enclosing mem_exclusive cpuset ok
  *      GFP_USER     - only nodes in current tasks mems allowed ok.
+ *
+ * Rule:
+ *    Don't call cpuset_zone_allowed() if you can't sleep, unless you
+ *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
+ *    the code that might scan up ancestor cpusets and sleep.
  **/
 
 int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
@@ -2255,6 +2261,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
         if (in_interrupt())
                 return 1;
         node = z->zone_pgdat->node_id;
+        might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
         if (node_isset(node, current->mems_allowed))
                 return 1;
         if (gfp_mask & __GFP_HARDWALL)  /* If hardwall request, stop here */
diff --git a/kernel/extable.c b/kernel/extable.c
index 7501b531ceed..7fe262855317 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -40,7 +40,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
         return e;
 }
 
-static int core_kernel_text(unsigned long addr)
+int core_kernel_text(unsigned long addr)
 {
         if (addr >= (unsigned long)_stext &&
             addr <= (unsigned long)_etext)
diff --git a/kernel/module.c b/kernel/module.c
index d24deb0dbbc9..bbe04862e1b0 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -705,14 +705,14 @@ EXPORT_SYMBOL(__symbol_put);
 
 void symbol_put_addr(void *addr)
 {
-        unsigned long flags;
+        struct module *modaddr;
 
-        spin_lock_irqsave(&modlist_lock, flags);
-        if (!kernel_text_address((unsigned long)addr))
-                BUG();
+        if (core_kernel_text((unsigned long)addr))
+                return;
 
-        module_put(module_text_address((unsigned long)addr));
-        spin_unlock_irqrestore(&modlist_lock, flags);
+        if (!(modaddr = module_text_address((unsigned long)addr)))
+                BUG();
+        module_put(modaddr);
 }
 EXPORT_SYMBOL_GPL(symbol_put_addr);
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4e0f0ec003f7..921c22ad16e4 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -148,12 +148,34 @@ int ptrace_may_attach(struct task_struct *task)
 int ptrace_attach(struct task_struct *task)
 {
         int retval;
-        task_lock(task);
+
         retval = -EPERM;
         if (task->pid <= 1)
-                goto bad;
+                goto out;
         if (task->tgid == current->tgid)
-                goto bad;
+                goto out;
+
+repeat:
+        /*
+         * Nasty, nasty.
+         *
+         * We want to hold both the task-lock and the
+         * tasklist_lock for writing at the same time.
+         * But that's against the rules (tasklist_lock
+         * is taken for reading by interrupts on other
+         * cpu's that may have task_lock).
+         */
+        task_lock(task);
+        local_irq_disable();
+        if (!write_trylock(&tasklist_lock)) {
+                local_irq_enable();
+                task_unlock(task);
+                do {
+                        cpu_relax();
+                } while (!write_can_lock(&tasklist_lock));
+                goto repeat;
+        }
+
         /* the same process cannot be attached many times */
         if (task->ptrace & PT_PTRACED)
                 goto bad;
@@ -166,17 +188,15 @@ int ptrace_attach(struct task_struct *task)
                                       ? PT_ATTACHED : 0);
         if (capable(CAP_SYS_PTRACE))
                 task->ptrace |= PT_PTRACE_CAP;
-        task_unlock(task);
 
-        write_lock_irq(&tasklist_lock);
         __ptrace_link(task, current);
-        write_unlock_irq(&tasklist_lock);
 
         force_sig_specific(SIGSTOP, task);
-        return 0;
 
 bad:
+        write_unlock_irq(&tasklist_lock);
         task_unlock(task);
+out:
         return retval;
 }
 
@@ -417,21 +437,22 @@ int ptrace_request(struct task_struct *child, long request,
  */
 int ptrace_traceme(void)
 {
-        int ret;
+        int ret = -EPERM;
 
         /*
          * Are we already being traced?
          */
-        if (current->ptrace & PT_PTRACED)
-                return -EPERM;
-        ret = security_ptrace(current->parent, current);
-        if (ret)
-                return -EPERM;
-        /*
-         * Set the ptrace bit in the process ptrace flags.
-         */
-        current->ptrace |= PT_PTRACED;
-        return 0;
+        task_lock(current);
+        if (!(current->ptrace & PT_PTRACED)) {
+                ret = security_ptrace(current->parent, current);
+                /*
+                 * Set the ptrace bit in the process ptrace flags.
+                 */
+                if (!ret)
+                        current->ptrace |= PT_PTRACED;
+        }
+        task_unlock(current);
+        return ret;
 }
 
 /**
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 6d32ff26f948..2058f88c7bbb 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -479,12 +479,31 @@ static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
         return 0;
 }
 
+/*
+ * Check to see if there is any immediate RCU-related work to be done
+ * by the current CPU, returning 1 if so.  This function is part of the
+ * RCU implementation; it is -not- an exported member of the RCU API.
+ */
 int rcu_pending(int cpu)
 {
         return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
                 __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
 }
 
+/*
+ * Check to see if any future RCU-related work will need to be done
+ * by the current CPU, even if none need be done immediately, returning
+ * 1 if so.  This function is part of the RCU implementation; it is -not-
+ * an exported member of the RCU API.
+ */
+int rcu_needs_cpu(int cpu)
+{
+        struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+        struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);
+
+        return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu));
+}
+
 void rcu_check_callbacks(int cpu, int user)
 {
         if (user || 
diff --git a/kernel/sched.c b/kernel/sched.c
index 4c64f85698ae..c13f1bd2df7d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -665,55 +665,13 @@ static int effective_prio(task_t *p)
 }
 
 /*
- * We place interactive tasks back into the active array, if possible.
- *
- * To guarantee that this does not starve expired tasks we ignore the
- * interactivity of a task if the first expired task had to wait more
- * than a 'reasonable' amount of time. This deadline timeout is
- * load-dependent, as the frequency of array switched decreases with
- * increasing number of running tasks. We also ignore the interactivity
- * if a better static_prio task has expired, and switch periodically
- * regardless, to ensure that highly interactive tasks do not starve
- * the less fortunate for unreasonably long periods.
- */
-static inline int expired_starving(runqueue_t *rq)
-{
-        int limit;
-
-        /*
-         * Arrays were recently switched, all is well
-         */
-        if (!rq->expired_timestamp)
-                return 0;
-
-        limit = STARVATION_LIMIT * rq->nr_running;
-
-        /*
-         * It's time to switch arrays
-         */
-        if (jiffies - rq->expired_timestamp >= limit)
-                return 1;
-
-        /*
-         * There's a better selection in the expired array
-         */
-        if (rq->curr->static_prio > rq->best_expired_prio)
-                return 1;
-
-        /*
-         * All is well
-         */
-        return 0;
-}
-
-/*
  * __activate_task - move a task to the runqueue.
  */
 static void __activate_task(task_t *p, runqueue_t *rq)
 {
         prio_array_t *target = rq->active;
 
-        if (unlikely(batch_task(p) || (expired_starving(rq) && !rt_task(p))))
+        if (batch_task(p))
                 target = rq->expired;
         enqueue_task(p, target);
         rq->nr_running++;
@@ -2532,6 +2490,22 @@ unsigned long long current_sched_time(const task_t *tsk)
 }
 
 /*
+ * We place interactive tasks back into the active array, if possible.
+ *
+ * To guarantee that this does not starve expired tasks we ignore the
+ * interactivity of a task if the first expired task had to wait more
+ * than a 'reasonable' amount of time. This deadline timeout is
+ * load-dependent, as the frequency of array switched decreases with
+ * increasing number of running tasks. We also ignore the interactivity
+ * if a better static_prio task has expired:
+ */
+#define EXPIRED_STARVING(rq) \
+        ((STARVATION_LIMIT && ((rq)->expired_timestamp && \
+                (jiffies - (rq)->expired_timestamp >= \
+                        STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
+                        ((rq)->curr->static_prio > (rq)->best_expired_prio))
+
+/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
@@ -2666,7 +2640,7 @@ void scheduler_tick(void)
 
                 if (!rq->expired_timestamp)
                         rq->expired_timestamp = jiffies;
-                if (!TASK_INTERACTIVE(p) || expired_starving(rq)) {
+                if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
                         enqueue_task(p, rq->expired);
                         if (p->static_prio < rq->best_expired_prio)
                                 rq->best_expired_prio = p->static_prio;
diff --git a/kernel/timer.c b/kernel/timer.c
index 67eaf0f54096..9e49deed468c 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -541,6 +541,22 @@ found:
         }
         spin_unlock(&base->lock);
 
+        /*
+         * It can happen that other CPUs service timer IRQs and increment
+         * jiffies, but we have not yet got a local timer tick to process
+         * the timer wheels.  In that case, the expiry time can be before
+         * jiffies, but since the high-resolution timer here is relative to
+         * jiffies, the default expression when high-resolution timers are
+         * not active,
+         *
+         *   time_before(MAX_JIFFY_OFFSET + jiffies, expires)
+         *
+         * would falsely evaluate to true.  If that is the case, just
+         * return jiffies so that we can immediately fire the local timer
+         */
+        if (time_before(expires, jiffies))
+                return jiffies;
+
         if (time_before(hr_expires, expires))
                 return hr_expires;