1 files changed, 49 insertions, 70 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 4b5e063..4f71627 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -160,7 +160,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	info->nr = nr_events;		/* trusted copy */
 
-	ring = kmap_atomic(info->ring_pages[0], KM_USER0);
+	ring = kmap_atomic(info->ring_pages[0]);
 	ring->nr = nr_events;	/* user copy */
 	ring->id = ctx->user_id;
 	ring->head = ring->tail = 0;
@@ -168,47 +168,38 @@ static int aio_setup_ring(struct kioctx *ctx)
 	ring->compat_features = AIO_RING_COMPAT_FEATURES;
 	ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
 	ring->header_length = sizeof(struct aio_ring);
-	kunmap_atomic(ring, KM_USER0);
+	kunmap_atomic(ring);
 
 	return 0;
 }
 
 
 /* aio_ring_event: returns a pointer to the event at the given index from
- * kmap_atomic(, km).  Release the pointer with put_aio_ring_event();
+ * kmap_atomic().  Release the pointer with put_aio_ring_event();
  */
 #define AIO_EVENTS_PER_PAGE	(PAGE_SIZE / sizeof(struct io_event))
 #define AIO_EVENTS_FIRST_PAGE	((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
 #define AIO_EVENTS_OFFSET	(AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
 
-#define aio_ring_event(info, nr, km) ({					\
+#define aio_ring_event(info, nr) ({					\
 	unsigned pos = (nr) + AIO_EVENTS_OFFSET;			\
 	struct io_event *__event;					\
 	__event = kmap_atomic(						\
-			(info)->ring_pages[pos / AIO_EVENTS_PER_PAGE], km); \
+			(info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
 	__event += pos % AIO_EVENTS_PER_PAGE;				\
 	__event;							\
 })
 
-#define put_aio_ring_event(event, km) do {	\
+#define put_aio_ring_event(event) do {		\
 	struct io_event *__event = (event);	\
 	(void)__event;				\
-	kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK), km); \
+	kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \
 } while(0)
 
 static void ctx_rcu_free(struct rcu_head *head)
 {
 	struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
-	unsigned nr_events = ctx->max_reqs;
-
 	kmem_cache_free(kioctx_cachep, ctx);
-
-	if (nr_events) {
-		spin_lock(&aio_nr_lock);
-		BUG_ON(aio_nr - nr_events > aio_nr);
-		aio_nr -= nr_events;
-		spin_unlock(&aio_nr_lock);
-	}
 }
 
 /* __put_ioctx
@@ -217,23 +208,23 @@ static void ctx_rcu_free(struct rcu_head *head)
  */
 static void __put_ioctx(struct kioctx *ctx)
 {
+	unsigned nr_events = ctx->max_reqs;
 	BUG_ON(ctx->reqs_active);
 
-	cancel_delayed_work(&ctx->wq);
-	cancel_work_sync(&ctx->wq.work);
+	cancel_delayed_work_sync(&ctx->wq);
 	aio_free_ring(ctx);
 	mmdrop(ctx->mm);
 	ctx->mm = NULL;
+	if (nr_events) {
+		spin_lock(&aio_nr_lock);
+		BUG_ON(aio_nr - nr_events > aio_nr);
+		aio_nr -= nr_events;
+		spin_unlock(&aio_nr_lock);
+	}
 	pr_debug("__put_ioctx: freeing %p\n", ctx);
 	call_rcu(&ctx->rcu_head, ctx_rcu_free);
 }
 
-static inline void get_ioctx(struct kioctx *kioctx)
-{
-	BUG_ON(atomic_read(&kioctx->users) <= 0);
-	atomic_inc(&kioctx->users);
-}
-
 static inline int try_get_ioctx(struct kioctx *kioctx)
 {
 	return atomic_inc_not_zero(&kioctx->users);
@@ -253,7 +244,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 {
 	struct mm_struct *mm;
 	struct kioctx *ctx;
-	int did_sync = 0;
+	int err = -ENOMEM;
 
 	/* Prevent overflows */
 	if ((nr_events > (0x10000000U / sizeof(struct io_event))) ||
@@ -262,7 +253,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 		return ERR_PTR(-EINVAL);
 	}
 
-	if ((unsigned long)nr_events > aio_max_nr)
+	if (!nr_events || (unsigned long)nr_events > aio_max_nr)
 		return ERR_PTR(-EAGAIN);
 
 	ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL);
@@ -273,7 +264,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	mm = ctx->mm = current->mm;
 	atomic_inc(&mm->mm_count);
 
-	atomic_set(&ctx->users, 1);
+	atomic_set(&ctx->users, 2);
 	spin_lock_init(&ctx->ctx_lock);
 	spin_lock_init(&ctx->ring_info.ring_lock);
 	init_waitqueue_head(&ctx->wait);
@@ -286,25 +277,14 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 		goto out_freectx;
 
 	/* limit the number of system wide aios */
-	do {
-		spin_lock_bh(&aio_nr_lock);
-		if (aio_nr + nr_events > aio_max_nr ||
-		    aio_nr + nr_events < aio_nr)
-			ctx->max_reqs = 0;
-		else
-			aio_nr += ctx->max_reqs;
-		spin_unlock_bh(&aio_nr_lock);
-		if (ctx->max_reqs || did_sync)
-			break;
-
-		/* wait for rcu callbacks to have completed before giving up */
-		synchronize_rcu();
-		did_sync = 1;
-		ctx->max_reqs = nr_events;
-	} while (1);
-
-	if (ctx->max_reqs == 0)
+	spin_lock(&aio_nr_lock);
+	if (aio_nr + nr_events > aio_max_nr ||
+	    aio_nr + nr_events < aio_nr) {
+		spin_unlock(&aio_nr_lock);
 		goto out_cleanup;
+	}
+	aio_nr += ctx->max_reqs;
+	spin_unlock(&aio_nr_lock);
 
 	/* now link into global list. */
 	spin_lock(&mm->ioctx_lock);
@@ -316,16 +296,13 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	return ctx;
 
 out_cleanup:
-	__put_ioctx(ctx);
-	return ERR_PTR(-EAGAIN);
-
+	err = -EAGAIN;
+	aio_free_ring(ctx);
 out_freectx:
 	mmdrop(mm);
 	kmem_cache_free(kioctx_cachep, ctx);
-	ctx = ERR_PTR(-ENOMEM);
-
-	dprintk("aio: error allocating ioctx %p\n", ctx);
-	return ctx;
+	dprintk("aio: error allocating ioctx %d\n", err);
+	return ERR_PTR(err);
 }
 
 /* aio_cancel_all
@@ -413,10 +390,6 @@ void exit_aio(struct mm_struct *mm)
 		aio_cancel_all(ctx);
 
 		wait_for_all_aios(ctx);
-		/*
-		 * Ensure we don't leave the ctx on the aio_wq
-		 */
-		cancel_work_sync(&ctx->wq.work);
 
 		if (1 != atomic_read(&ctx->users))
 			printk(KERN_DEBUG
@@ -490,6 +463,8 @@ static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
 		kmem_cache_free(kiocb_cachep, req);
 		ctx->reqs_active--;
 	}
+	if (unlikely(!ctx->reqs_active && ctx->dead))
+		wake_up_all(&ctx->wait);
 	spin_unlock_irq(&ctx->ctx_lock);
 }
 
@@ -607,11 +582,16 @@ static void aio_fput_routine(struct work_struct *data)
 			fput(req->ki_filp);
 
 		/* Link the iocb into the context's free list */
+		rcu_read_lock();
 		spin_lock_irq(&ctx->ctx_lock);
 		really_put_req(ctx, req);
+		/*
+		 * at that point ctx might've been killed, but actual
+		 * freeing is RCU'd
+		 */
 		spin_unlock_irq(&ctx->ctx_lock);
+		rcu_read_unlock();
 
-		put_ioctx(ctx);
 		spin_lock_irq(&fput_lock);
 	}
 	spin_unlock_irq(&fput_lock);
@@ -642,7 +622,6 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	 * this function will be executed w/out any aio kthread wakeup.
 	 */
 	if (unlikely(!fput_atomic(req->ki_filp))) {
-		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
 		spin_unlock(&fput_lock);
@@ -920,7 +899,7 @@ static void aio_kick_handler(struct work_struct *work)
  	unuse_mm(mm);
 	set_fs(oldfs);
 	/*
-	 * we're in a worker thread already, don't use queue_delayed_work,
+	 * we're in a worker thread already; no point using non-zero delay
 	 */
 	if (requeue)
 		queue_delayed_work(aio_wq, &ctx->wq, 0);
@@ -1019,10 +998,10 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
 	if (kiocbIsCancelled(iocb))
 		goto put_rq;
 
-	ring = kmap_atomic(info->ring_pages[0], KM_IRQ1);
+	ring = kmap_atomic(info->ring_pages[0]);
 
 	tail = info->tail;
-	event = aio_ring_event(info, tail, KM_IRQ0);
+	event = aio_ring_event(info, tail);
 	if (++tail >= info->nr)
 		tail = 0;
 
@@ -1043,8 +1022,8 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
 	info->tail = tail;
 	ring->tail = tail;
 
-	put_aio_ring_event(event, KM_IRQ0);
-	kunmap_atomic(ring, KM_IRQ1);
+	put_aio_ring_event(event);
+	kunmap_atomic(ring);
 
 	pr_debug("added to ring %p at [%lu]\n", iocb, tail);
 
@@ -1089,7 +1068,7 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
 	unsigned long head;
 	int ret = 0;
 
-	ring = kmap_atomic(info->ring_pages[0], KM_USER0);
+	ring = kmap_atomic(info->ring_pages[0]);
 	dprintk("in aio_read_evt h%lu t%lu m%lu\n",
 		 (unsigned long)ring->head, (unsigned long)ring->tail,
 		 (unsigned long)ring->nr);
@@ -1101,18 +1080,18 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
 
 	head = ring->head % info->nr;
 	if (head != ring->tail) {
-		struct io_event *evp = aio_ring_event(info, head, KM_USER1);
+		struct io_event *evp = aio_ring_event(info, head);
 		*ent = *evp;
 		head = (head + 1) % info->nr;
 		smp_mb(); /* finish reading the event before updatng the head */
 		ring->head = head;
 		ret = 1;
-		put_aio_ring_event(evp, KM_USER1);
+		put_aio_ring_event(evp);
 	}
 	spin_unlock(&info->ring_lock);
 
 out:
-	kunmap_atomic(ring, KM_USER0);
+	kunmap_atomic(ring);
 	dprintk("leaving aio_read_evt: %d  h%lu t%lu\n", ret,
 		 (unsigned long)ring->head, (unsigned long)ring->tail);
 	return ret;
@@ -1336,10 +1315,10 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	ret = PTR_ERR(ioctx);
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
-		if (!ret)
+		if (!ret) {
+			put_ioctx(ioctx);
 			return 0;
-
-		get_ioctx(ioctx); /* io_destroy() expects us to hold a ref */
+		}
 		io_destroy(ioctx);
 	}