Merge remote branch 'remotes/linux-linaro-2.6.35/master'

Conflicts:
	drivers/char/agp/intel-gtt.c
	sound/pci/hda/patch_realtek.c

23 files changed, 155 insertions, 70 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 1ccf25cef1f..5fb0fd7c80a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -712,8 +712,16 @@ static ssize_t aio_run_iocb(struct kiocb *iocb)
 	 */
 	ret = retry(iocb);
 
-	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED)
+	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) {
+		/*
+		 * There's no easy way to restart the syscall since other AIO's
+		 * may be already running. Just fail this IO with EINTR.
+		 */
+		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
+			     ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK))
+			ret = -EINTR;
 		aio_complete(iocb, ret, 0);
+	}
 out:
 	spin_lock_irq(&ctx->ctx_lock);
 
@@ -1659,6 +1667,9 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 	if (unlikely(nr < 0))
 		return -EINVAL;
 
+	if (unlikely(nr > LONG_MAX/sizeof(*iocbpp)))
+		nr = LONG_MAX/sizeof(*iocbpp);
+
 	if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp)))))
 		return -EFAULT;
 
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index c4e83537ead..42b60b04ea0 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -723,7 +723,7 @@ static int __init init_misc_binfmt(void)
 {
 	int err = register_filesystem(&bm_fs_type);
 	if (!err) {
-		err = register_binfmt(&misc_format);
+		err = insert_binfmt(&misc_format);
 		if (err)
 			unregister_filesystem(&bm_fs_type);
 	}
diff --git a/fs/char_dev.c b/fs/char_dev.c
index f80a4f25123..143d393881c 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -40,7 +40,9 @@ struct backing_dev_info directly_mappable_cdev_bdi = {
 #endif
 		/* permit direct mmap, for read, write or exec */
 		BDI_CAP_MAP_DIRECT |
-		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP),
+		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP |
+		/* no writeback happens */
+		BDI_CAP_NO_ACCT_AND_WRITEBACK),
 };
 
 static struct kobj_map *cdev_map;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2208f06e4c4..fa1039a7ac4 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1647,9 +1647,6 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 	if (ses) {
 		cFYI(1, "Existing smb sess found (status=%d)", ses->status);
 
-		/* existing SMB ses has a server reference already */
-		cifs_put_tcp_session(server);
-
 		mutex_lock(&ses->session_mutex);
 		rc = cifs_negotiate_protocol(xid, ses);
 		if (rc) {
@@ -1672,6 +1669,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 			}
 		}
 		mutex_unlock(&ses->session_mutex);
+
+		/* existing SMB ses has a server reference already */
+		cifs_put_tcp_session(server);
 		FreeXid(xid);
 		return ses;
 	}
diff --git a/fs/compat.c b/fs/compat.c
index 6490d2134ff..af7c2301a2e 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1150,7 +1150,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 {
 	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov;
+	struct iovec *iov = iovstack;
 	ssize_t ret;
 	io_fn_t fn;
 	iov_fn_t fnv;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 7600aacf531..458fdd360dd 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -218,7 +218,7 @@ static struct page *dio_get_page(struct dio *dio)
  * filesystems can use it to hold additional state between get_block calls and
  * dio_complete.
  */
-static int dio_complete(struct dio *dio, loff_t offset, int ret)
+static int dio_complete(struct dio *dio, loff_t offset, int ret, bool is_async)
 {
 	ssize_t transferred = 0;
 
@@ -239,14 +239,6 @@ static int dio_complete(struct dio *dio, loff_t offset, int ret)
 			transferred = dio->i_size - offset;
 	}
 
-	if (dio->end_io && dio->result)
-		dio->end_io(dio->iocb, offset, transferred,
-			    dio->map_bh.b_private);
-
-	if (dio->flags & DIO_LOCKING)
-		/* lockdep: non-owner release */
-		up_read_non_owner(&dio->inode->i_alloc_sem);
-
 	if (ret == 0)
 		ret = dio->page_errors;
 	if (ret == 0)
@@ -254,6 +246,17 @@ static int dio_complete(struct dio *dio, loff_t offset, int ret)
 	if (ret == 0)
 		ret = transferred;
 
+	if (dio->end_io && dio->result) {
+		dio->end_io(dio->iocb, offset, transferred,
+			    dio->map_bh.b_private, ret, is_async);
+	} else if (is_async) {
+		aio_complete(dio->iocb, ret, 0);
+	}
+
+	if (dio->flags & DIO_LOCKING)
+		/* lockdep: non-owner release */
+		up_read_non_owner(&dio->inode->i_alloc_sem);
+
 	return ret;
 }
 
@@ -277,8 +280,7 @@ static void dio_bio_end_aio(struct bio *bio, int error)
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
 	if (remaining == 0) {
-		int ret = dio_complete(dio, dio->iocb->ki_pos, 0);
-		aio_complete(dio->iocb, ret, 0);
+		dio_complete(dio, dio->iocb->ki_pos, 0, true);
 		kfree(dio);
 	}
 }
@@ -632,7 +634,7 @@ static int dio_send_cur_page(struct dio *dio)
 	int ret = 0;
 
 	if (dio->bio) {
-		loff_t cur_offset = dio->block_in_file << dio->blkbits;
+		loff_t cur_offset = dio->cur_page_fs_offset;
 		loff_t bio_next_offset = dio->logical_offset_in_bio +
 			dio->bio->bi_size;
 
@@ -657,7 +659,7 @@ static int dio_send_cur_page(struct dio *dio)
 		 * Submit now if the underlying fs is about to perform a
 		 * metadata read
 		 */
-		if (dio->boundary)
+		else if (dio->boundary)
 			dio_bio_submit(dio);
 	}
 
@@ -1126,7 +1128,7 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
 	if (ret2 == 0) {
-		ret = dio_complete(dio, offset, ret);
+		ret = dio_complete(dio, offset, ret, false);
 		kfree(dio);
 	} else
 		BUG_ON(ret != -EIOCBQUEUED);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 19a4de57128..4c9f05dc704 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -167,13 +167,15 @@ struct mpage_da_data {
 };
 #define	EXT4_IO_UNWRITTEN	0x1
 typedef struct ext4_io_end {
-	struct list_head	list;		/* per-file finished AIO list */
+	struct list_head	list;		/* per-file finished IO list */
 	struct inode		*inode;		/* file being written to */
 	unsigned int		flag;		/* unwritten or not */
 	struct page		*page;		/* page struct for buffer write */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
 	struct work_struct	work;		/* data work queue */
+	struct kiocb		*iocb;		/* iocb struct for AIO */
+	int			result;		/* error value for AIO */
 } ext4_io_end_t;
 
 /*
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 42272d67955..3fb64b9e47c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3668,6 +3668,8 @@ static int ext4_end_io_nolock(ext4_io_end_t *io)
 		return ret;
 	}
 
+	if (io->iocb)
+		aio_complete(io->iocb, io->result, 0);
 	/* clear the DIO AIO unwritten flag */
 	io->flag = 0;
 	return ret;
@@ -3767,6 +3769,8 @@ static ext4_io_end_t *ext4_init_io_end (struct inode *inode, gfp_t flags)
 		io->offset = 0;
 		io->size = 0;
 		io->page = NULL;
+		io->iocb = NULL;
+		io->result = 0;
 		INIT_WORK(&io->work, ext4_end_io_work);
 		INIT_LIST_HEAD(&io->list);
 	}
@@ -3775,7 +3779,8 @@ static ext4_io_end_t *ext4_init_io_end (struct inode *inode, gfp_t flags)
 }
 
 static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
-			    ssize_t size, void *private)
+			    ssize_t size, void *private, int ret,
+			    bool is_async)
 {
         ext4_io_end_t *io_end = iocb->private;
 	struct workqueue_struct *wq;
@@ -3784,7 +3789,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 
 	/* if not async direct IO or dio with 0 bytes write, just return */
 	if (!io_end || !size)
-		return;
+		goto out;
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p"
 		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
@@ -3795,12 +3800,18 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 	if (io_end->flag != EXT4_IO_UNWRITTEN){
 		ext4_free_io_end(io_end);
 		iocb->private = NULL;
+out:
+		if (is_async)
+			aio_complete(iocb, ret, 0);
 		return;
 	}
 
 	io_end->offset = offset;
 	io_end->size = size;
-	io_end->flag = EXT4_IO_UNWRITTEN;
+	if (is_async) {
+		io_end->iocb = iocb;
+		io_end->result = ret;
+	}
 	wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
 
 	/* queue the work to convert unwritten extents to written */
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 9424796d663..e5cdabf4945 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1552,6 +1552,14 @@ __acquires(&fc->lock)
 	}
 }
 
+static void end_queued_requests(struct fuse_conn *fc)
+{
+	fc->max_background = UINT_MAX;
+	flush_bg_queue(fc);
+	end_requests(fc, &fc->pending);
+	end_requests(fc, &fc->processing);
+}
+
 /*
  * Abort all requests.
  *
@@ -1578,8 +1586,7 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		fc->connected = 0;
 		fc->blocked = 0;
 		end_io_requests(fc);
-		end_requests(fc, &fc->pending);
-		end_requests(fc, &fc->processing);
+		end_queued_requests(fc);
 		wake_up_all(&fc->waitq);
 		wake_up_all(&fc->blocked_waitq);
 		kill_fasync(&fc->fasync, SIGIO, POLL_IN);
@@ -1594,8 +1601,9 @@ int fuse_dev_release(struct inode *inode, struct file *file)
 	if (fc) {
 		spin_lock(&fc->lock);
 		fc->connected = 0;
-		end_requests(fc, &fc->pending);
-		end_requests(fc, &fc->processing);
+		fc->blocked = 0;
+		end_queued_requests(fc);
+		wake_up_all(&fc->blocked_waitq);
 		spin_unlock(&fc->lock);
 		fuse_conn_put(fc);
 	}
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6a857e24f94..83917b50a19 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -932,7 +932,7 @@ int gfs2_logd(void *data)
 
 		do {
 			prepare_to_wait(&sdp->sd_logd_waitq, &wait,
-					TASK_UNINTERRUPTIBLE);
+					TASK_INTERRUPTIBLE);
 			if (!gfs2_ail_flush_reqd(sdp) &&
 			    !gfs2_jrnl_flush_reqd(sdp) &&
 			    !kthread_should_stop())
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index e20ee85955d..f3f3578393a 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -115,7 +115,7 @@ static int minix_mkdir(struct inode * dir, struct dentry *dentry, int mode)
 
 	inode_inc_link_count(dir);
 
-	inode = minix_new_inode(dir, mode, &err);
+	inode = minix_new_inode(dir, S_IFDIR | mode, &err);
 	if (!inode)
 		goto out_dir;
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index d25b5257b7a..e0067708a55 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -274,7 +274,7 @@ static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
 	    sin1->sin6_scope_id != sin2->sin6_scope_id)
 		return 0;
 
-	return ipv6_addr_equal(&sin1->sin6_addr, &sin1->sin6_addr);
+	return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
 }
 #else	/* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */
 static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 6bf11d745a3..381d9291ea1 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -431,7 +431,15 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		goto out_err;
 
 	error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
+	if (unlikely(error == -ESTALE)) {
+		struct dentry *pd_dentry;
 
+		pd_dentry = dget_parent(dentry);
+		if (pd_dentry != NULL) {
+			nfs_zap_caches(pd_dentry->d_inode);
+			dput(pd_dentry);
+		}
+	}
 	nfs_free_fattr(res.fattr);
 	if (error < 0)
 		goto out_err;
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e46ca685b9b..0c6bbc031f1 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -96,8 +96,11 @@ static inline __u32 inotify_arg_to_mask(u32 arg)
 {
 	__u32 mask;
 
-	/* everything should accept their own ignored and cares about children */
-	mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD);
+	/*
+	 * everything should accept their own ignored, cares about children,
+	 * and should receive events when the inode is unmounted
+	 */
+	mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD | FS_UNMOUNT);
 
 	/* mask off the flags used to open the fd */
 	mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT));
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 356e976772b..96337a4fbbd 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -578,7 +578,9 @@ bail:
 static void ocfs2_dio_end_io(struct kiocb *iocb,
 			     loff_t offset,
 			     ssize_t bytes,
-			     void *private)
+			     void *private,
+			     int ret,
+			     bool is_async)
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
 	int level;
@@ -592,6 +594,9 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	if (!level)
 		up_read(&inode->i_alloc_sem);
 	ocfs2_rw_unlock(inode, level);
+
+	if (is_async)
+		aio_complete(iocb, ret, 0);
 }
 
 /*
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index abb0a95cc71..201e7bcec75 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -488,7 +488,11 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 						     OCFS2_BH_IGNORE_CACHE);
 	} else {
 		status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
-		if (!status)
+		/*
+		 * If buffer is in jbd, then its checksum may not have been
+		 * computed as yet.
+		 */
+		if (!status && !buffer_jbd(bh))
 			status = ocfs2_validate_inode_block(osb->sb, bh);
 	}
 	if (status < 0) {
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 91c817ff02c..2367fb3f70b 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -163,7 +163,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 
 static const struct file_operations proc_vmcore_operations = {
 	.read		= read_vmcore,
-	.llseek		= generic_file_llseek,
+	.llseek		= default_llseek,
 };
 
 static struct vmcore* __init get_new_element(void)
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 1beaa739d0a..cd796847c81 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -340,7 +340,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	char *p;
 
 	p = d_path(&file->f_path, last_sysfs_file, sizeof(last_sysfs_file));
-	if (p)
+	if (!IS_ERR(p))
 		memmove(last_sysfs_file, p, strlen(p) + 1);
 
 	/* need attr_sd for attr and ops, its parent for kobj */
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 34640d6dbdc..f9f5567bf89 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -275,8 +275,11 @@ xfs_end_io(
 		xfs_finish_ioend(ioend, 0);
 		/* ensure we don't spin on blocked ioends */
 		delay(1);
-	} else
+	} else {
+		if (ioend->io_iocb)
+			aio_complete(ioend->io_iocb, ioend->io_result, 0);
 		xfs_destroy_ioend(ioend);
+	}
 }
 
 /*
@@ -309,6 +312,8 @@ xfs_alloc_ioend(
 	atomic_inc(&XFS_I(ioend->io_inode)->i_iocount);
 	ioend->io_offset = 0;
 	ioend->io_size = 0;
+	ioend->io_iocb = NULL;
+	ioend->io_result = 0;
 
 	INIT_WORK(&ioend->io_work, xfs_end_io);
 	return ioend;
@@ -1599,9 +1604,12 @@ xfs_end_io_direct(
 	struct kiocb	*iocb,
 	loff_t		offset,
 	ssize_t		size,
-	void		*private)
+	void		*private,
+	int		ret,
+	bool		is_async)
 {
 	xfs_ioend_t	*ioend = iocb->private;
+	bool		complete_aio = is_async;
 
 	/*
 	 * Non-NULL private data means we need to issue a transaction to
@@ -1627,7 +1635,14 @@ xfs_end_io_direct(
 	if (ioend->io_type == IO_READ) {
 		xfs_finish_ioend(ioend, 0);
 	} else if (private && size > 0) {
-		xfs_finish_ioend(ioend, is_sync_kiocb(iocb));
+		if (is_async) {
+			ioend->io_iocb = iocb;
+			ioend->io_result = ret;
+			complete_aio = false;
+			xfs_finish_ioend(ioend, 0);
+		} else {
+			xfs_finish_ioend(ioend, 1);
+		}
 	} else {
 		/*
 		 * A direct I/O write ioend starts it's life in unwritten
@@ -1645,6 +1660,9 @@ xfs_end_io_direct(
 	 * against double-freeing.
 	 */
 	iocb->private = NULL;
+
+	if (complete_aio)
+		aio_complete(iocb, ret, 0);
 }
 
 STATIC ssize_t
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h
index 4cfc6ea87df..9f566d92ae3 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/linux-2.6/xfs_aops.h
@@ -37,6 +37,8 @@ typedef struct xfs_ioend {
 	size_t			io_size;	/* size of the extent */
 	xfs_off_t		io_offset;	/* offset in the file */
 	struct work_struct	io_work;	/* xfsdatad work queue */
+	struct kiocb		*io_iocb;
+	int			io_result;
 } xfs_ioend_t;
 
 extern const struct address_space_operations xfs_address_space_operations;
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index e59a8106283..82a74f6142f 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -794,6 +794,8 @@ xfs_ioc_fsgetxattr(
 {
 	struct fsxattr		fa;
 
+	memset(&fa, 0, sizeof(struct fsxattr));
+
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	fa.fsx_xflags = xfs_ip2xflags(ip);
 	fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index c7142a064c4..eb779affaaa 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -1217,7 +1217,6 @@ xfs_imap_lookup(
 	struct xfs_inobt_rec_incore rec;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
-	xfs_agino_t		startino;
 	int			error;
 	int			i;
 
@@ -1231,13 +1230,13 @@ xfs_imap_lookup(
 	}
 
 	/*
-	 * derive and lookup the exact inode record for the given agino. If the
-	 * record cannot be found, then it's an invalid inode number and we
-	 * should abort.
+	 * Lookup the inode record for the given agino. If the record cannot be
+	 * found, then it's an invalid inode number and we should abort. Once
+	 * we have a record, we need to ensure it contains the inode number
+	 * we are looking up.
 	 */
 	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
-	startino = agino & ~(XFS_IALLOC_INODES(mp) - 1);
-	error = xfs_inobt_lookup(cur, startino, XFS_LOOKUP_EQ, &i);
+	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
 	if (!error) {
 		if (i)
 			error = xfs_inobt_get_rec(cur, &rec, &i);
@@ -1250,6 +1249,11 @@ xfs_imap_lookup(
 	if (error)
 		return error;
 
+	/* check that the returned record contains the required inode */
+	if (rec.ir_startino > agino ||
+	    rec.ir_startino + XFS_IALLOC_INODES(mp) <= agino)
+		return EINVAL;
+
 	/* for untrusted inodes check it is allocated first */
 	if ((flags & XFS_IGET_UNTRUSTED) &&
 	    (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino)))
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b76a829d7e2..f70221820a1 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1927,6 +1927,11 @@ xfs_iunlink_remove(
 	return 0;
 }
 
+/*
+ * A big issue when freeing the inode cluster is is that we _cannot_ skip any
+ * inodes that are in memory - they all must be marked stale and attached to
+ * the cluster buffer.
+ */
 STATIC void
 xfs_ifree_cluster(
 	xfs_inode_t	*free_ip,
@@ -1958,8 +1963,6 @@ xfs_ifree_cluster(
 	}
 
 	for (j = 0; j < nbufs; j++, inum += ninodes) {
-		int	found = 0;
-
 		blkno = XFS_AGB_TO_DADDR(mp, XFS_INO_TO_AGNO(mp, inum),
 					 XFS_INO_TO_AGBNO(mp, inum));
 
@@ -1978,7 +1981,9 @@ xfs_ifree_cluster(
 		/*
 		 * Walk the inodes already attached to the buffer and mark them
 		 * stale. These will all have the flush locks held, so an
-		 * in-memory inode walk can't lock them.
+		 * in-memory inode walk can't lock them. By marking them all
+		 * stale first, we will not attempt to lock them in the loop
+		 * below as the XFS_ISTALE flag will be set.
 		 */
 		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
 		while (lip) {
@@ -1990,11 +1995,11 @@ xfs_ifree_cluster(
 							&iip->ili_flush_lsn,
 							&iip->ili_item.li_lsn);
 				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
-				found++;
 			}
 			lip = lip->li_bio_list;
 		}
 
+
 		/*
 		 * For each inode in memory attempt to add it to the inode
 		 * buffer and set it up for being staled on buffer IO
@@ -2006,6 +2011,7 @@ xfs_ifree_cluster(
 		 * even trying to lock them.
 		 */
 		for (i = 0; i < ninodes; i++) {
+retry:
 			read_lock(&pag->pag_ici_lock);
 			ip = radix_tree_lookup(&pag->pag_ici_root,
 					XFS_INO_TO_AGINO(mp, (inum + i)));
@@ -2016,38 +2022,36 @@ xfs_ifree_cluster(
 				continue;
 			}
 
-			/* don't try to lock/unlock the current inode */
+			/*
+			 * Don't try to lock/unlock the current inode, but we
+			 * _cannot_ skip the other inodes that we did not find
+			 * in the list attached to the buffer and are not
+			 * already marked stale. If we can't lock it, back off
+			 * and retry.
+			 */
 			if (ip != free_ip &&
 			    !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
 				read_unlock(&pag->pag_ici_lock);
-				continue;
+				delay(1);
+				goto retry;
 			}
 			read_unlock(&pag->pag_ici_lock);
 
-			if (!xfs_iflock_nowait(ip)) {
-				if (ip != free_ip)
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
-
+			xfs_iflock(ip);
 			xfs_iflags_set(ip, XFS_ISTALE);
-			if (xfs_inode_clean(ip)) {
-				ASSERT(ip != free_ip);
-				xfs_ifunlock(ip);
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
 
+			/*
+			 * we don't need to attach clean inodes or those only
+			 * with unlogged changes (which we throw away, anyway).
+			 */
 			iip = ip->i_itemp;
-			if (!iip) {
-				/* inode with unlogged changes only */
+			if (!iip || xfs_inode_clean(ip)) {
 				ASSERT(ip != free_ip);
 				ip->i_update_core = 0;
 				xfs_ifunlock(ip);
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 				continue;
 			}
-			found++;
 
 			iip->ili_last_fields = iip->ili_format.ilf_fields;
 			iip->ili_format.ilf_fields = 0;
@@ -2063,8 +2067,7 @@ xfs_ifree_cluster(
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		}
 
-		if (found)
-			xfs_trans_stale_inode_buf(tp, bp);
+		xfs_trans_stale_inode_buf(tp, bp);
 		xfs_trans_binval(tp, bp);
 	}