Merge tag 'v3.5-rc1'

Linux 3.5-rc1

Conflicts:
	net/ceph/messenger.c

1 files changed, 81 insertions, 104 deletions

diff --git a/fs/aio.c b/fs/aio.c
index b9d64d89a043..55c4c7656053 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -13,7 +13,7 @@
 #include <linux/errno.h>
 #include <linux/time.h>
 #include <linux/aio_abi.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
@@ -93,9 +93,8 @@ static void aio_free_ring(struct kioctx *ctx)
 		put_page(info->ring_pages[i]);
 
 	if (info->mmap_size) {
-		down_write(&ctx->mm->mmap_sem);
-		do_munmap(ctx->mm, info->mmap_base, info->mmap_size);
-		up_write(&ctx->mm->mmap_sem);
+		BUG_ON(ctx->mm != current->mm);
+		vm_munmap(info->mmap_base, info->mmap_size);
 	}
 
 	if (info->ring_pages && info->ring_pages != info->internal_pages)
@@ -135,9 +134,9 @@ static int aio_setup_ring(struct kioctx *ctx)
 	info->mmap_size = nr_pages * PAGE_SIZE;
 	dprintk("attempting mmap of %lu bytes\n", info->mmap_size);
 	down_write(&ctx->mm->mmap_sem);
-	info->mmap_base = do_mmap(NULL, 0, info->mmap_size, 
-				  PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE,
-				  0);
+	info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size, 
+					PROT_READ|PROT_WRITE,
+					MAP_ANONYMOUS|MAP_PRIVATE, 0);
 	if (IS_ERR((void *)info->mmap_base)) {
 		up_write(&ctx->mm->mmap_sem);
 		info->mmap_size = 0;
@@ -160,7 +159,7 @@ 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 +167,38 @@ 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
@@ -217,13 +207,19 @@ 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);
 }
@@ -247,7 +243,7 @@ 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))) ||
@@ -256,7 +252,7 @@ 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);
@@ -280,25 +276,14 @@ 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);
@@ -310,27 +295,27 @@ 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
+/* kill_ctx
  *	Cancels all outstanding aio requests on an aio context.  Used 
  *	when the processes owning a context have all exited to encourage 
  *	the rapid destruction of the kioctx.
  */
-static void aio_cancel_all(struct kioctx *ctx)
+static void kill_ctx(struct kioctx *ctx)
 {
 	int (*cancel)(struct kiocb *, struct io_event *);
+	struct task_struct *tsk = current;
+	DECLARE_WAITQUEUE(wait, tsk);
 	struct io_event res;
+
 	spin_lock_irq(&ctx->ctx_lock);
 	ctx->dead = 1;
 	while (!list_empty(&ctx->active_reqs)) {
@@ -346,15 +331,7 @@ static void aio_cancel_all(struct kioctx *ctx)
 			spin_lock_irq(&ctx->ctx_lock);
 		}
 	}
-	spin_unlock_irq(&ctx->ctx_lock);
-}
-
-static void wait_for_all_aios(struct kioctx *ctx)
-{
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
 
-	spin_lock_irq(&ctx->ctx_lock);
 	if (!ctx->reqs_active)
 		goto out;
 
@@ -404,19 +381,24 @@ void exit_aio(struct mm_struct *mm)
 		ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list);
 		hlist_del_rcu(&ctx->list);
 
-		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);
+		kill_ctx(ctx);
 
 		if (1 != atomic_read(&ctx->users))
 			printk(KERN_DEBUG
 				"exit_aio:ioctx still alive: %d %d %d\n",
 				atomic_read(&ctx->users), ctx->dead,
 				ctx->reqs_active);
+		/*
+		 * We don't need to bother with munmap() here -
+		 * exit_mmap(mm) is coming and it'll unmap everything.
+		 * Since aio_free_ring() uses non-zero ->mmap_size
+		 * as indicator that it needs to unmap the area,
+		 * just set it to 0; aio_free_ring() is the only
+		 * place that uses ->mmap_size, so it's safe.
+		 * That way we get all munmap done to current->mm -
+		 * all other callers have ctx->mm == current->mm.
+		 */
+		ctx->ring_info.mmap_size = 0;
 		put_ioctx(ctx);
 	}
 }
@@ -920,7 +902,7 @@ 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 +1001,10 @@ 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 +1025,8 @@ 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 +1071,7 @@ 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 +1083,18 @@ 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;
@@ -1290,8 +1272,7 @@ static void io_destroy(struct kioctx *ioctx)
 	if (likely(!was_dead))
 		put_ioctx(ioctx);	/* twice for the list */
 
-	aio_cancel_all(ioctx);
-	wait_for_all_aios(ioctx);
+	kill_ctx(ioctx);
 
 	/*
 	 * Wake up any waiters.  The setting of ctx->dead must be seen
@@ -1299,7 +1280,6 @@ static void io_destroy(struct kioctx *ioctx)
 	 * locking done by the above calls to ensure this consistency.
 	 */
 	wake_up_all(&ioctx->wait);
-	put_ioctx(ioctx);	/* once for the lookup */
 }
 
 /* sys_io_setup:
@@ -1336,11 +1316,9 @@ 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) {
-			put_ioctx(ioctx);
-			return 0;
-		}
-		io_destroy(ioctx);
+		if (ret)
+			io_destroy(ioctx);
+		put_ioctx(ioctx);
 	}
 
 out:
@@ -1358,6 +1336,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
 		io_destroy(ioctx);
+		put_ioctx(ioctx);
 		return 0;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
@@ -1467,13 +1446,17 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
 		ret = compat_rw_copy_check_uvector(type,
 				(struct compat_iovec __user *)kiocb->ki_buf,
 				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
-				&kiocb->ki_iovec, 1);
+				&kiocb->ki_iovec);
 	else
 #endif
 		ret = rw_copy_check_uvector(type,
 				(struct iovec __user *)kiocb->ki_buf,
 				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
-				&kiocb->ki_iovec, 1);
+				&kiocb->ki_iovec);
+	if (ret < 0)
+		goto out;
+
+	ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret);
 	if (ret < 0)
 		goto out;
 
@@ -1488,11 +1471,17 @@ out:
 	return ret;
 }
 
-static ssize_t aio_setup_single_vector(struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb)
 {
+	int bytes;
+
+	bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left);
+	if (bytes < 0)
+		return bytes;
+
 	kiocb->ki_iovec = &kiocb->ki_inline_vec;
 	kiocb->ki_iovec->iov_base = kiocb->ki_buf;
-	kiocb->ki_iovec->iov_len = kiocb->ki_left;
+	kiocb->ki_iovec->iov_len = bytes;
 	kiocb->ki_nr_segs = 1;
 	kiocb->ki_cur_seg = 0;
 	return 0;
@@ -1517,10 +1506,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf,
 			kiocb->ki_left)))
 			break;
-		ret = security_file_permission(file, MAY_READ);
-		if (unlikely(ret))
-			break;
-		ret = aio_setup_single_vector(kiocb);
+		ret = aio_setup_single_vector(READ, file, kiocb);
 		if (ret)
 			break;
 		ret = -EINVAL;
@@ -1535,10 +1521,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf,
 			kiocb->ki_left)))
 			break;
-		ret = security_file_permission(file, MAY_WRITE);
-		if (unlikely(ret))
-			break;
-		ret = aio_setup_single_vector(kiocb);
+		ret = aio_setup_single_vector(WRITE, file, kiocb);
 		if (ret)
 			break;
 		ret = -EINVAL;
@@ -1549,9 +1532,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		ret = -EBADF;
 		if (unlikely(!(file->f_mode & FMODE_READ)))
 			break;
-		ret = security_file_permission(file, MAY_READ);
-		if (unlikely(ret))
-			break;
 		ret = aio_setup_vectored_rw(READ, kiocb, compat);
 		if (ret)
 			break;
@@ -1563,9 +1543,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		ret = -EBADF;
 		if (unlikely(!(file->f_mode & FMODE_WRITE)))
 			break;
-		ret = security_file_permission(file, MAY_WRITE);
-		if (unlikely(ret))
-			break;
 		ret = aio_setup_vectored_rw(WRITE, kiocb, compat);
 		if (ret)
 			break;