1 files changed, 46 insertions, 29 deletions

diff --git a/lib/rwsem.c b/lib/rwsem.c
index 8337e1b9bb8d..ad5e0df16ab4 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -2,6 +2,8 @@
  *
  * Written by David Howells (dhowells@redhat.com).
  * Derived from arch/i386/kernel/semaphore.c
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
  */
 #include <linux/rwsem.h>
 #include <linux/sched.h>
@@ -60,7 +62,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
         struct rwsem_waiter *waiter;
         struct task_struct *tsk;
         struct list_head *next;
-        signed long oldcount, woken, loop, adjustment;
+        signed long woken, loop, adjustment;
 
         waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
         if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE))
@@ -72,30 +74,8 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
                  */
                 goto out;
 
-        /* There's a writer at the front of the queue - try to grant it the
-         * write lock.  However, we only wake this writer if we can transition
-         * the active part of the count from 0 -> 1
-         */
-        adjustment = RWSEM_ACTIVE_WRITE_BIAS;
-        if (waiter->list.next == &sem->wait_list)
-                adjustment -= RWSEM_WAITING_BIAS;
-
- try_again_write:
-        oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
-        if (oldcount & RWSEM_ACTIVE_MASK)
-                /* Someone grabbed the sem already */
-                goto undo_write;
-
-        /* We must be careful not to touch 'waiter' after we set ->task = NULL.
-         * It is an allocated on the waiter's stack and may become invalid at
-         * any time after that point (due to a wakeup from another source).
-         */
-        list_del(&waiter->list);
-        tsk = waiter->task;
-        smp_mb();
-        waiter->task = NULL;
-        wake_up_process(tsk);
-        put_task_struct(tsk);
+        /* Wake up the writing waiter and let the task grab the sem: */
+        wake_up_process(waiter->task);
         goto out;
 
  readers_only:
@@ -157,12 +137,40 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
 
  out:
         return sem;
+}
+
+/* Try to get write sem, caller holds sem->wait_lock: */
+static int try_get_writer_sem(struct rw_semaphore *sem,
+                                        struct rwsem_waiter *waiter)
+{
+        struct rwsem_waiter *fwaiter;
+        long oldcount, adjustment;
 
-        /* undo the change to the active count, but check for a transition
-         * 1->0 */
- undo_write:
+        /* only steal when first waiter is writing */
+        fwaiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+        if (!(fwaiter->flags & RWSEM_WAITING_FOR_WRITE))
+                return 0;
+
+        adjustment = RWSEM_ACTIVE_WRITE_BIAS;
+        /* Only one waiter in the queue: */
+        if (fwaiter == waiter && waiter->list.next == &sem->wait_list)
+                adjustment -= RWSEM_WAITING_BIAS;
+
+try_again_write:
+        oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+        if (!(oldcount & RWSEM_ACTIVE_MASK)) {
+                /* No active lock: */
+                struct task_struct *tsk = waiter->task;
+
+                list_del(&waiter->list);
+                smp_mb();
+                put_task_struct(tsk);
+                tsk->state = TASK_RUNNING;
+                return 1;
+        }
+        /* some one grabbed the sem already */
         if (rwsem_atomic_update(-adjustment, sem) & RWSEM_ACTIVE_MASK)
-                goto out;
+                return 0;
         goto try_again_write;
 }
 
@@ -210,6 +218,15 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
         for (;;) {
                 if (!waiter.task)
                         break;
+
+                raw_spin_lock_irq(&sem->wait_lock);
+                /* Try to get the writer sem, may steal from the head writer: */
+                if (flags == RWSEM_WAITING_FOR_WRITE)
+                        if (try_get_writer_sem(sem, &waiter)) {
+                                raw_spin_unlock_irq(&sem->wait_lock);
+                                return sem;
+                        }
+                raw_spin_unlock_irq(&sem->wait_lock);
                 schedule();
                 set_task_state(tsk, TASK_UNINTERRUPTIBLE);
         }