Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	sound/core/memalloc.c

62 files changed, 2241 insertions, 1836 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index c95295c65045..e83aa5ebe861 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -626,8 +626,7 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	return NULL;
 
 error:
-	if (fid)
-		p9_client_clunk(fid);
+	p9_client_clunk(fid);
 
 	return ERR_PTR(result);
 }
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index c3e174b35fe6..19caf7c962ac 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -107,7 +107,8 @@ void bio_integrity_free(struct bio *bio, struct bio_set *bs)
 	BUG_ON(bip == NULL);
 
 	/* A cloned bio doesn't own the integrity metadata */
-	if (!bio_flagged(bio, BIO_CLONED) && bip->bip_buf != NULL)
+	if (!bio_flagged(bio, BIO_CLONED) && !bio_flagged(bio, BIO_FS_INTEGRITY)
+	    && bip->bip_buf != NULL)
 		kfree(bip->bip_buf);
 
 	mempool_free(bip->bip_vec, bs->bvec_pools[bip->bip_pool]);
@@ -150,6 +151,24 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
+static int bdev_integrity_enabled(struct block_device *bdev, int rw)
+{
+	struct blk_integrity *bi = bdev_get_integrity(bdev);
+
+	if (bi == NULL)
+		return 0;
+
+	if (rw == READ && bi->verify_fn != NULL &&
+	    (bi->flags & INTEGRITY_FLAG_READ))
+		return 1;
+
+	if (rw == WRITE && bi->generate_fn != NULL &&
+	    (bi->flags & INTEGRITY_FLAG_WRITE))
+		return 1;
+
+	return 0;
+}
+
 /**
  * bio_integrity_enabled - Check whether integrity can be passed
  * @bio:	bio to check
@@ -313,6 +332,14 @@ static void bio_integrity_generate(struct bio *bio)
 	}
 }
 
+static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
+{
+	if (bi)
+		return bi->tuple_size;
+
+	return 0;
+}
+
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
diff --git a/fs/bio.c b/fs/bio.c
index 3cba7ae34d75..77a55bcceedb 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -30,7 +30,7 @@
 
 static struct kmem_cache *bio_slab __read_mostly;
 
-mempool_t *bio_split_pool __read_mostly;
+static mempool_t *bio_split_pool __read_mostly;
 
 /*
  * if you change this list, also change bvec_alloc or things will
@@ -60,25 +60,46 @@ struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct
 	struct bio_vec *bvl;
 
 	/*
-	 * see comment near bvec_array define!
+	 * If 'bs' is given, lookup the pool and do the mempool alloc.
+	 * If not, this is a bio_kmalloc() allocation and just do a
+	 * kzalloc() for the exact number of vecs right away.
 	 */
-	switch (nr) {
-		case   1        : *idx = 0; break;
-		case   2 ...   4: *idx = 1; break;
-		case   5 ...  16: *idx = 2; break;
-		case  17 ...  64: *idx = 3; break;
-		case  65 ... 128: *idx = 4; break;
-		case 129 ... BIO_MAX_PAGES: *idx = 5; break;
+	if (bs) {
+		/*
+		 * see comment near bvec_array define!
+		 */
+		switch (nr) {
+		case 1:
+			*idx = 0;
+			break;
+		case 2 ... 4:
+			*idx = 1;
+			break;
+		case 5 ... 16:
+			*idx = 2;
+			break;
+		case 17 ... 64:
+			*idx = 3;
+			break;
+		case 65 ... 128:
+			*idx = 4;
+			break;
+		case 129 ... BIO_MAX_PAGES:
+			*idx = 5;
+			break;
 		default:
 			return NULL;
-	}
-	/*
-	 * idx now points to the pool we want to allocate from
-	 */
+		}
 
-	bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
-	if (bvl)
-		memset(bvl, 0, bvec_nr_vecs(*idx) * sizeof(struct bio_vec));
+		/*
+		 * idx now points to the pool we want to allocate from
+		 */
+		bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
+		if (bvl)
+			memset(bvl, 0,
+				bvec_nr_vecs(*idx) * sizeof(struct bio_vec));
+	} else
+		bvl = kzalloc(nr * sizeof(struct bio_vec), gfp_mask);
 
 	return bvl;
 }
@@ -107,10 +128,17 @@ static void bio_fs_destructor(struct bio *bio)
 	bio_free(bio, fs_bio_set);
 }
 
+static void bio_kmalloc_destructor(struct bio *bio)
+{
+	kfree(bio->bi_io_vec);
+	kfree(bio);
+}
+
 void bio_init(struct bio *bio)
 {
 	memset(bio, 0, sizeof(*bio));
 	bio->bi_flags = 1 << BIO_UPTODATE;
+	bio->bi_comp_cpu = -1;
 	atomic_set(&bio->bi_cnt, 1);
 }
 
@@ -118,19 +146,25 @@ void bio_init(struct bio *bio)
  * bio_alloc_bioset - allocate a bio for I/O
  * @gfp_mask:   the GFP_ mask given to the slab allocator
  * @nr_iovecs:	number of iovecs to pre-allocate
- * @bs:		the bio_set to allocate from
+ * @bs:		the bio_set to allocate from. If %NULL, just use kmalloc
  *
  * Description:
- *   bio_alloc_bioset will first try it's on mempool to satisfy the allocation.
+ *   bio_alloc_bioset will first try its own mempool to satisfy the allocation.
  *   If %__GFP_WAIT is set then we will block on the internal pool waiting
- *   for a &struct bio to become free.
+ *   for a &struct bio to become free. If a %NULL @bs is passed in, we will
+ *   fall back to just using @kmalloc to allocate the required memory.
  *
  *   allocate bio and iovecs from the memory pools specified by the
- *   bio_set structure.
+ *   bio_set structure, or @kmalloc if none given.
  **/
 struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 {
-	struct bio *bio = mempool_alloc(bs->bio_pool, gfp_mask);
+	struct bio *bio;
+
+	if (bs)
+		bio = mempool_alloc(bs->bio_pool, gfp_mask);
+	else
+		bio = kmalloc(sizeof(*bio), gfp_mask);
 
 	if (likely(bio)) {
 		struct bio_vec *bvl = NULL;
@@ -141,7 +175,10 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 
 			bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
 			if (unlikely(!bvl)) {
-				mempool_free(bio, bs->bio_pool);
+				if (bs)
+					mempool_free(bio, bs->bio_pool);
+				else
+					kfree(bio);
 				bio = NULL;
 				goto out;
 			}
@@ -164,6 +201,23 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
 	return bio;
 }
 
+/*
+ * Like bio_alloc(), but doesn't use a mempool backing. This means that
+ * it CAN fail, but while bio_alloc() can only be used for allocations
+ * that have a short (finite) life span, bio_kmalloc() should be used
+ * for more permanent bio allocations (like allocating some bio's for
+ * initalization or setup purposes).
+ */
+struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
+{
+	struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
+
+	if (bio)
+		bio->bi_destructor = bio_kmalloc_destructor;
+
+	return bio;
+}
+
 void zero_fill_bio(struct bio *bio)
 {
 	unsigned long flags;
@@ -208,14 +262,6 @@ inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
 	return bio->bi_phys_segments;
 }
 
-inline int bio_hw_segments(struct request_queue *q, struct bio *bio)
-{
-	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
-		blk_recount_segments(q, bio);
-
-	return bio->bi_hw_segments;
-}
-
 /**
  * 	__bio_clone	-	clone a bio
  * 	@bio: destination bio
@@ -350,8 +396,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	 */
 
 	while (bio->bi_phys_segments >= q->max_phys_segments
-	       || bio->bi_hw_segments >= q->max_hw_segments
-	       || BIOVEC_VIRT_OVERSIZE(bio->bi_size)) {
+	       || bio->bi_phys_segments >= q->max_hw_segments) {
 
 		if (retried_segments)
 			return 0;
@@ -395,13 +440,11 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	}
 
 	/* If we may be able to merge these biovecs, force a recount */
-	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec) ||
-	    BIOVEC_VIRT_MERGEABLE(bvec-1, bvec)))
+	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
 		bio->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 	bio->bi_vcnt++;
 	bio->bi_phys_segments++;
-	bio->bi_hw_segments++;
  done:
 	bio->bi_size += len;
 	return len;
@@ -449,16 +492,19 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 
 struct bio_map_data {
 	struct bio_vec *iovecs;
-	int nr_sgvecs;
 	struct sg_iovec *sgvecs;
+	int nr_sgvecs;
+	int is_our_pages;
 };
 
 static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-			     struct sg_iovec *iov, int iov_count)
+			     struct sg_iovec *iov, int iov_count,
+			     int is_our_pages)
 {
 	memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
 	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
 	bmd->nr_sgvecs = iov_count;
+	bmd->is_our_pages = is_our_pages;
 	bio->bi_private = bmd;
 }
 
@@ -493,7 +539,8 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
 }
 
 static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
-			  struct sg_iovec *iov, int iov_count, int uncopy)
+			  struct sg_iovec *iov, int iov_count, int uncopy,
+			  int do_free_page)
 {
 	int ret = 0, i;
 	struct bio_vec *bvec;
@@ -536,7 +583,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 			}
 		}
 
-		if (uncopy)
+		if (do_free_page)
 			__free_page(bvec->bv_page);
 	}
 
@@ -553,10 +600,11 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 int bio_uncopy_user(struct bio *bio)
 {
 	struct bio_map_data *bmd = bio->bi_private;
-	int ret;
-
-	ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, bmd->nr_sgvecs, 1);
+	int ret = 0;
 
+	if (!bio_flagged(bio, BIO_NULL_MAPPED))
+		ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
+				     bmd->nr_sgvecs, 1, bmd->is_our_pages);
 	bio_free_map_data(bmd);
 	bio_put(bio);
 	return ret;
@@ -565,16 +613,20 @@ int bio_uncopy_user(struct bio *bio)
 /**
  *	bio_copy_user_iov	-	copy user data to bio
  *	@q: destination block queue
+ *	@map_data: pointer to the rq_map_data holding pages (if necessary)
  *	@iov:	the iovec.
  *	@iov_count: number of elements in the iovec
  *	@write_to_vm: bool indicating writing to pages or not
+ *	@gfp_mask: memory allocation flags
  *
  *	Prepares and returns a bio for indirect user io, bouncing data
  *	to/from kernel pages as necessary. Must be paired with
  *	call bio_uncopy_user() on io completion.
  */
-struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
-			      int iov_count, int write_to_vm)
+struct bio *bio_copy_user_iov(struct request_queue *q,
+			      struct rq_map_data *map_data,
+			      struct sg_iovec *iov, int iov_count,
+			      int write_to_vm, gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
 	struct bio_vec *bvec;
@@ -597,25 +649,38 @@ struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
 		len += iov[i].iov_len;
 	}
 
-	bmd = bio_alloc_map_data(nr_pages, iov_count, GFP_KERNEL);
+	bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
 	if (!bmd)
 		return ERR_PTR(-ENOMEM);
 
 	ret = -ENOMEM;
-	bio = bio_alloc(GFP_KERNEL, nr_pages);
+	bio = bio_alloc(gfp_mask, nr_pages);
 	if (!bio)
 		goto out_bmd;
 
 	bio->bi_rw |= (!write_to_vm << BIO_RW);
 
 	ret = 0;
+	i = 0;
 	while (len) {
-		unsigned int bytes = PAGE_SIZE;
+		unsigned int bytes;
+
+		if (map_data)
+			bytes = 1U << (PAGE_SHIFT + map_data->page_order);
+		else
+			bytes = PAGE_SIZE;
 
 		if (bytes > len)
 			bytes = len;
 
-		page = alloc_page(q->bounce_gfp | GFP_KERNEL);
+		if (map_data) {
+			if (i == map_data->nr_entries) {
+				ret = -ENOMEM;
+				break;
+			}
+			page = map_data->pages[i++];
+		} else
+			page = alloc_page(q->bounce_gfp | gfp_mask);
 		if (!page) {
 			ret = -ENOMEM;
 			break;
@@ -634,16 +699,17 @@ struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
 	 * success
 	 */
 	if (!write_to_vm) {
-		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0);
+		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0);
 		if (ret)
 			goto cleanup;
 	}
 
-	bio_set_map_data(bmd, bio, iov, iov_count);
+	bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
 	return bio;
 cleanup:
-	bio_for_each_segment(bvec, bio, i)
-		__free_page(bvec->bv_page);
+	if (!map_data)
+		bio_for_each_segment(bvec, bio, i)
+			__free_page(bvec->bv_page);
 
 	bio_put(bio);
 out_bmd:
@@ -654,29 +720,32 @@ out_bmd:
 /**
  *	bio_copy_user	-	copy user data to bio
  *	@q: destination block queue
+ *	@map_data: pointer to the rq_map_data holding pages (if necessary)
  *	@uaddr: start of user address
  *	@len: length in bytes
  *	@write_to_vm: bool indicating writing to pages or not
+ *	@gfp_mask: memory allocation flags
  *
  *	Prepares and returns a bio for indirect user io, bouncing data
  *	to/from kernel pages as necessary. Must be paired with
  *	call bio_uncopy_user() on io completion.
  */
-struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
-			  unsigned int len, int write_to_vm)
+struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
+			  unsigned long uaddr, unsigned int len,
+			  int write_to_vm, gfp_t gfp_mask)
 {
 	struct sg_iovec iov;
 
 	iov.iov_base = (void __user *)uaddr;
 	iov.iov_len = len;
 
-	return bio_copy_user_iov(q, &iov, 1, write_to_vm);
+	return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
 }
 
 static struct bio *__bio_map_user_iov(struct request_queue *q,
 				      struct block_device *bdev,
 				      struct sg_iovec *iov, int iov_count,
-				      int write_to_vm)
+				      int write_to_vm, gfp_t gfp_mask)
 {
 	int i, j;
 	int nr_pages = 0;
@@ -702,12 +771,12 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
 	if (!nr_pages)
 		return ERR_PTR(-EINVAL);
 
-	bio = bio_alloc(GFP_KERNEL, nr_pages);
+	bio = bio_alloc(gfp_mask, nr_pages);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
 
 	ret = -ENOMEM;
-	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
+	pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
 	if (!pages)
 		goto out;
 
@@ -786,19 +855,21 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
  *	@uaddr: start of user address
  *	@len: length in bytes
  *	@write_to_vm: bool indicating writing to pages or not
+ *	@gfp_mask: memory allocation flags
  *
  *	Map the user space address into a bio suitable for io to a block
  *	device. Returns an error pointer in case of error.
  */
 struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
-			 unsigned long uaddr, unsigned int len, int write_to_vm)
+			 unsigned long uaddr, unsigned int len, int write_to_vm,
+			 gfp_t gfp_mask)
 {
 	struct sg_iovec iov;
 
 	iov.iov_base = (void __user *)uaddr;
 	iov.iov_len = len;
 
-	return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm);
+	return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
 }
 
 /**
@@ -808,18 +879,19 @@ struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
  *	@iov:	the iovec.
  *	@iov_count: number of elements in the iovec
  *	@write_to_vm: bool indicating writing to pages or not
+ *	@gfp_mask: memory allocation flags
  *
  *	Map the user space address into a bio suitable for io to a block
  *	device. Returns an error pointer in case of error.
  */
 struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
 			     struct sg_iovec *iov, int iov_count,
-			     int write_to_vm)
+			     int write_to_vm, gfp_t gfp_mask)
 {
 	struct bio *bio;
 
-	bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm);
-
+	bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
+				 gfp_mask);
 	if (IS_ERR(bio))
 		return bio;
 
@@ -976,48 +1048,13 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 			  gfp_t gfp_mask, int reading)
 {
-	unsigned long kaddr = (unsigned long)data;
-	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	unsigned long start = kaddr >> PAGE_SHIFT;
-	const int nr_pages = end - start;
 	struct bio *bio;
 	struct bio_vec *bvec;
-	struct bio_map_data *bmd;
-	int i, ret;
-	struct sg_iovec iov;
-
-	iov.iov_base = data;
-	iov.iov_len = len;
-
-	bmd = bio_alloc_map_data(nr_pages, 1, gfp_mask);
-	if (!bmd)
-		return ERR_PTR(-ENOMEM);
-
-	ret = -ENOMEM;
-	bio = bio_alloc(gfp_mask, nr_pages);
-	if (!bio)
-		goto out_bmd;
-
-	while (len) {
-		struct page *page;
-		unsigned int bytes = PAGE_SIZE;
-
-		if (bytes > len)
-			bytes = len;
-
-		page = alloc_page(q->bounce_gfp | gfp_mask);
-		if (!page) {
-			ret = -ENOMEM;
-			goto cleanup;
-		}
-
-		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) {
-			ret = -EINVAL;
-			goto cleanup;
-		}
+	int i;
 
-		len -= bytes;
-	}
+	bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
+	if (IS_ERR(bio))
+		return bio;
 
 	if (!reading) {
 		void *p = data;
@@ -1030,20 +1067,9 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 		}
 	}
 
-	bio->bi_private = bmd;
 	bio->bi_end_io = bio_copy_kern_endio;
 
-	bio_set_map_data(bmd, bio, &iov, 1);
 	return bio;
-cleanup:
-	bio_for_each_segment(bvec, bio, i)
-		__free_page(bvec->bv_page);
-
-	bio_put(bio);
-out_bmd:
-	bio_free_map_data(bmd);
-
-	return ERR_PTR(ret);
 }
 
 /*
@@ -1230,9 +1256,9 @@ static void bio_pair_end_2(struct bio *bi, int err)
  * split a bio - only worry about a bio with a single page
  * in it's iovec
  */
-struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
+struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 {
-	struct bio_pair *bp = mempool_alloc(pool, GFP_NOIO);
+	struct bio_pair *bp = mempool_alloc(bio_split_pool, GFP_NOIO);
 
 	if (!bp)
 		return bp;
@@ -1266,7 +1292,7 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
 	bp->bio2.bi_end_io = bio_pair_end_2;
 
 	bp->bio1.bi_private = bi;
-	bp->bio2.bi_private = pool;
+	bp->bio2.bi_private = bio_split_pool;
 
 	if (bio_integrity(bi))
 		bio_integrity_split(bi, bp, first_sectors);
@@ -1274,6 +1300,42 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
 	return bp;
 }
 
+/**
+ *      bio_sector_offset - Find hardware sector offset in bio
+ *      @bio:           bio to inspect
+ *      @index:         bio_vec index
+ *      @offset:        offset in bv_page
+ *
+ *      Return the number of hardware sectors between beginning of bio
+ *      and an end point indicated by a bio_vec index and an offset
+ *      within that vector's page.
+ */
+sector_t bio_sector_offset(struct bio *bio, unsigned short index,
+			   unsigned int offset)
+{
+	unsigned int sector_sz = queue_hardsect_size(bio->bi_bdev->bd_disk->queue);
+	struct bio_vec *bv;
+	sector_t sectors;
+	int i;
+
+	sectors = 0;
+
+	if (index >= bio->bi_idx)
+		index = bio->bi_vcnt - 1;
+
+	__bio_for_each_segment(bv, bio, i, 0) {
+		if (i == index) {
+			if (offset > bv->bv_offset)
+				sectors += (offset - bv->bv_offset) / sector_sz;
+			break;
+		}
+
+		sectors += bv->bv_len / sector_sz;
+	}
+
+	return sectors;
+}
+EXPORT_SYMBOL(bio_sector_offset);
 
 /*
  * create memory pools for biovec's in a bio_set.
@@ -1376,6 +1438,7 @@ static int __init init_bio(void)
 subsys_initcall(init_bio);
 
 EXPORT_SYMBOL(bio_alloc);
+EXPORT_SYMBOL(bio_kmalloc);
 EXPORT_SYMBOL(bio_put);
 EXPORT_SYMBOL(bio_free);
 EXPORT_SYMBOL(bio_endio);
@@ -1383,7 +1446,6 @@ EXPORT_SYMBOL(bio_init);
 EXPORT_SYMBOL(__bio_clone);
 EXPORT_SYMBOL(bio_clone);
 EXPORT_SYMBOL(bio_phys_segments);
-EXPORT_SYMBOL(bio_hw_segments);
 EXPORT_SYMBOL(bio_add_page);
 EXPORT_SYMBOL(bio_add_pc_page);
 EXPORT_SYMBOL(bio_get_nr_vecs);
@@ -1393,7 +1455,6 @@ EXPORT_SYMBOL(bio_map_kern);
 EXPORT_SYMBOL(bio_copy_kern);
 EXPORT_SYMBOL(bio_pair_release);
 EXPORT_SYMBOL(bio_split);
-EXPORT_SYMBOL(bio_split_pool);
 EXPORT_SYMBOL(bio_copy_user);
 EXPORT_SYMBOL(bio_uncopy_user);
 EXPORT_SYMBOL(bioset_create);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index aff54219e049..d84f0469a016 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -540,22 +540,6 @@ EXPORT_SYMBOL(bd_release);
  *           /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
  */
 
-static struct kobject *bdev_get_kobj(struct block_device *bdev)
-{
-	if (bdev->bd_contains != bdev)
-		return kobject_get(&bdev->bd_part->dev.kobj);
-	else
-		return kobject_get(&bdev->bd_disk->dev.kobj);
-}
-
-static struct kobject *bdev_get_holder(struct block_device *bdev)
-{
-	if (bdev->bd_contains != bdev)
-		return kobject_get(bdev->bd_part->holder_dir);
-	else
-		return kobject_get(bdev->bd_disk->holder_dir);
-}
-
 static int add_symlink(struct kobject *from, struct kobject *to)
 {
 	if (!from || !to)
@@ -604,11 +588,11 @@ static int bd_holder_grab_dirs(struct block_device *bdev,
 	if (!bo->hdev)
 		goto fail_put_sdir;
 
-	bo->sdev = bdev_get_kobj(bdev);
+	bo->sdev = kobject_get(&part_to_dev(bdev->bd_part)->kobj);
 	if (!bo->sdev)
 		goto fail_put_hdev;
 
-	bo->hdir = bdev_get_holder(bdev);
+	bo->hdir = kobject_get(bdev->bd_part->holder_dir);
 	if (!bo->hdir)
 		goto fail_put_sdev;
 
@@ -868,6 +852,87 @@ struct block_device *open_by_devnum(dev_t dev, unsigned mode)
 
 EXPORT_SYMBOL(open_by_devnum);
 
+/**
+ * flush_disk - invalidates all buffer-cache entries on a disk
+ *
+ * @bdev:      struct block device to be flushed
+ *
+ * Invalidates all buffer-cache entries on a disk. It should be called
+ * when a disk has been changed -- either by a media change or online
+ * resize.
+ */
+static void flush_disk(struct block_device *bdev)
+{
+	if (__invalidate_device(bdev)) {
+		char name[BDEVNAME_SIZE] = "";
+
+		if (bdev->bd_disk)
+			disk_name(bdev->bd_disk, 0, name);
+		printk(KERN_WARNING "VFS: busy inodes on changed media or "
+		       "resized disk %s\n", name);
+	}
+
+	if (!bdev->bd_disk)
+		return;
+	if (disk_partitionable(bdev->bd_disk))
+		bdev->bd_invalidated = 1;
+}
+
+/**
+ * check_disk_size_change - checks for disk size change and adjusts bdev size.
+ * @disk: struct gendisk to check
+ * @bdev: struct bdev to adjust.
+ *
+ * This routine checks to see if the bdev size does not match the disk size
+ * and adjusts it if it differs.
+ */
+void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
+{
+	loff_t disk_size, bdev_size;
+
+	disk_size = (loff_t)get_capacity(disk) << 9;
+	bdev_size = i_size_read(bdev->bd_inode);
+	if (disk_size != bdev_size) {
+		char name[BDEVNAME_SIZE];
+
+		disk_name(disk, 0, name);
+		printk(KERN_INFO
+		       "%s: detected capacity change from %lld to %lld\n",
+		       name, bdev_size, disk_size);
+		i_size_write(bdev->bd_inode, disk_size);
+		flush_disk(bdev);
+	}
+}
+EXPORT_SYMBOL(check_disk_size_change);
+
+/**
+ * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
+ * @disk: struct gendisk to be revalidated
+ *
+ * This routine is a wrapper for lower-level driver's revalidate_disk
+ * call-backs.  It is used to do common pre and post operations needed
+ * for all revalidate_disk operations.
+ */
+int revalidate_disk(struct gendisk *disk)
+{
+	struct block_device *bdev;
+	int ret = 0;
+
+	if (disk->fops->revalidate_disk)
+		ret = disk->fops->revalidate_disk(disk);
+
+	bdev = bdget_disk(disk, 0);
+	if (!bdev)
+		return ret;
+
+	mutex_lock(&bdev->bd_mutex);
+	check_disk_size_change(disk, bdev);
+	mutex_unlock(&bdev->bd_mutex);
+	bdput(bdev);
+	return ret;
+}
+EXPORT_SYMBOL(revalidate_disk);
+
 /*
  * This routine checks whether a removable media has been changed,
  * and invalidates all buffer-cache-entries in that case. This
@@ -887,13 +952,9 @@ int check_disk_change(struct block_device *bdev)
 	if (!bdops->media_changed(bdev->bd_disk))
 		return 0;
 
-	if (__invalidate_device(bdev))
-		printk("VFS: busy inodes on changed media.\n");
-
+	flush_disk(bdev);
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
-	if (bdev->bd_disk->minors > 1)
-		bdev->bd_invalidated = 1;
 	return 1;
 }
 
@@ -927,10 +988,10 @@ static int __blkdev_put(struct block_device *bdev, int for_part);
 
 static int do_open(struct block_device *bdev, struct file *file, int for_part)
 {
-	struct module *owner = NULL;
 	struct gendisk *disk;
+	struct hd_struct *part = NULL;
 	int ret;
-	int part;
+	int partno;
 	int perm = 0;
 
 	if (file->f_mode & FMODE_READ)
@@ -948,25 +1009,27 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 
 	ret = -ENXIO;
 	file->f_mapping = bdev->bd_inode->i_mapping;
+
 	lock_kernel();
-	disk = get_gendisk(bdev->bd_dev, &part);
-	if (!disk) {
-		unlock_kernel();
-		bdput(bdev);
-		return ret;
-	}
-	owner = disk->fops->owner;
+
+	disk = get_gendisk(bdev->bd_dev, &partno);
+	if (!disk)
+		goto out_unlock_kernel;
+	part = disk_get_part(disk, partno);
+	if (!part)
+		goto out_unlock_kernel;
 
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
+		bdev->bd_part = part;
 		bdev->bd_contains = bdev;
-		if (!part) {
+		if (!partno) {
 			struct backing_dev_info *bdi;
 			if (disk->fops->open) {
 				ret = disk->fops->open(bdev->bd_inode, file);
 				if (ret)
-					goto out_first;
+					goto out_clear;
 			}
 			if (!bdev->bd_openers) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
@@ -978,36 +1041,36 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 			if (bdev->bd_invalidated)
 				rescan_partitions(disk, bdev);
 		} else {
-			struct hd_struct *p;
 			struct block_device *whole;
 			whole = bdget_disk(disk, 0);
 			ret = -ENOMEM;
 			if (!whole)
-				goto out_first;
+				goto out_clear;
 			BUG_ON(for_part);
 			ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1);
 			if (ret)
-				goto out_first;
+				goto out_clear;
 			bdev->bd_contains = whole;
-			p = disk->part[part - 1];
 			bdev->bd_inode->i_data.backing_dev_info =
 			   whole->bd_inode->i_data.backing_dev_info;
-			if (!(disk->flags & GENHD_FL_UP) || !p || !p->nr_sects) {
+			if (!(disk->flags & GENHD_FL_UP) ||
+			    !part || !part->nr_sects) {
 				ret = -ENXIO;
-				goto out_first;
+				goto out_clear;
 			}
-			kobject_get(&p->dev.kobj);
-			bdev->bd_part = p;
-			bd_set_size(bdev, (loff_t) p->nr_sects << 9);
+			bd_set_size(bdev, (loff_t)part->nr_sects << 9);
 		}
 	} else {
+		disk_put_part(part);
 		put_disk(disk);
-		module_put(owner);
+		module_put(disk->fops->owner);
+		part = NULL;
+		disk = NULL;
 		if (bdev->bd_contains == bdev) {
 			if (bdev->bd_disk->fops->open) {
 				ret = bdev->bd_disk->fops->open(bdev->bd_inode, file);
 				if (ret)
-					goto out;
+					goto out_unlock_bdev;
 			}
 			if (bdev->bd_invalidated)
 				rescan_partitions(bdev->bd_disk, bdev);
@@ -1020,19 +1083,24 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	unlock_kernel();
 	return 0;
 
-out_first:
+ out_clear:
 	bdev->bd_disk = NULL;
+	bdev->bd_part = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, 1);
 	bdev->bd_contains = NULL;
-	put_disk(disk);
-	module_put(owner);
-out:
+ out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
+ out_unlock_kernel:
 	unlock_kernel();
-	if (ret)
-		bdput(bdev);
+
+	disk_put_part(part);
+	if (disk)
+		module_put(disk->fops->owner);
+	put_disk(disk);
+	bdput(bdev);
+
 	return ret;
 }
 
@@ -1117,11 +1185,8 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 
 		put_disk(disk);
 		module_put(owner);
-
-		if (bdev->bd_contains != bdev) {
-			kobject_put(&bdev->bd_part->dev.kobj);
-			bdev->bd_part = NULL;
-		}
+		disk_put_part(bdev->bd_part);
+		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
 		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 		if (bdev != bdev->bd_contains)
@@ -1197,10 +1262,9 @@ EXPORT_SYMBOL(ioctl_by_bdev);
 
 /**
  * lookup_bdev  - lookup a struct block_device by name
+ * @pathname:	special file representing the block device
  *
- * @path:	special file representing the block device
- *
- * Get a reference to the blockdevice at @path in the current
+ * Get a reference to the blockdevice at @pathname in the current
  * namespace if possible and return it.  Return ERR_PTR(error)
  * otherwise.
  */
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 117ef4bba68e..fcee9298b620 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -66,11 +66,28 @@ struct key_type cifs_spnego_key_type = {
 	.describe	= user_describe,
 };
 
-#define MAX_VER_STR_LEN   8 /* length of longest version string e.g.
-				strlen("ver=0xFF") */
-#define MAX_MECH_STR_LEN 13 /* length of longest security mechanism name, eg
-			       in future could have strlen(";sec=ntlmsspi") */
-#define MAX_IPV6_ADDR_LEN 42 /* eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */
+/* length of longest version string e.g.  strlen("ver=0xFF") */
+#define MAX_VER_STR_LEN		8
+
+/* length of longest security mechanism name, eg in future could have
+ * strlen(";sec=ntlmsspi") */
+#define MAX_MECH_STR_LEN	13
+
+/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */
+#define MAX_IPV6_ADDR_LEN	42
+
+/* strlen of "host=" */
+#define HOST_KEY_LEN		5
+
+/* strlen of ";ip4=" or ";ip6=" */
+#define IP_KEY_LEN		5
+
+/* strlen of ";uid=0x" */
+#define UID_KEY_LEN		7
+
+/* strlen of ";user=" */
+#define USER_KEY_LEN		6
+
 /* get a key struct with a SPNEGO security blob, suitable for session setup */
 struct key *
 cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
@@ -84,11 +101,11 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
 	/* length of fields (with semicolons): ver=0xyz ip4=ipaddress
 	   host=hostname sec=mechanism uid=0xFF user=username */
 	desc_len = MAX_VER_STR_LEN +
-		   6 /* len of "host=" */ + strlen(hostname) +
-		   5 /* len of ";ipv4=" */ + MAX_IPV6_ADDR_LEN +
+		   HOST_KEY_LEN + strlen(hostname) +
+		   IP_KEY_LEN + MAX_IPV6_ADDR_LEN +
 		   MAX_MECH_STR_LEN +
-		   7 /* len of ";uid=0x" */ + (sizeof(uid_t) * 2) +
-		   6 /* len of ";user=" */ + strlen(sesInfo->userName) + 1;
+		   UID_KEY_LEN + (sizeof(uid_t) * 2) +
+		   USER_KEY_LEN + strlen(sesInfo->userName) + 1;
 
 	spnego_key = ERR_PTR(-ENOMEM);
 	description = kzalloc(desc_len, GFP_KERNEL);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 135c965c4137..f7b4a5cd837b 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -41,7 +41,7 @@ extern int cifs_create(struct inode *, struct dentry *, int,
 		       struct nameidata *);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
 				  struct nameidata *);
-extern int cifs_unlink(struct inode *, struct dentry *);
+extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
 extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
 extern int cifs_mknod(struct inode *, struct dentry *, int, dev_t);
 extern int cifs_mkdir(struct inode *, struct dentry *, int);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8dfd6f24d488..0d22479d99b7 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -309,6 +309,7 @@ struct cifs_search_info {
 	__u32 resume_key;
 	char *ntwrk_buf_start;
 	char *srch_entries_start;
+	char *last_entry;
 	char *presume_name;
 	unsigned int resume_name_len;
 	bool endOfSearch:1;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index a729d083e6f4..0cff7fe986e8 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -179,6 +179,8 @@ extern int CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
 extern int CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
 			const FILE_BASIC_INFO *data, __u16 fid,
 			__u32 pid_of_opener);
+extern int CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
+			bool delete_file, __u16 fid, __u32 pid_of_opener);
 #if 0
 extern int CIFSSMBSetAttrLegacy(int xid, struct cifsTconInfo *tcon,
 			char *fileName, __u16 dos_attributes,
@@ -229,7 +231,7 @@ extern int CIFSSMBRename(const int xid, struct cifsTconInfo *tcon,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 extern int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
-			int netfid, char *target_name,
+			int netfid, const char *target_name,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 extern int CIFSCreateHardLink(const int xid,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 994de7c90474..6f4ffe15d68d 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2017,7 +2017,7 @@ renameRetry:
 }
 
 int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
-		int netfid, char *target_name,
+		int netfid, const char *target_name,
 		const struct nls_table *nls_codepage, int remap)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
@@ -2071,7 +2071,7 @@ int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
 					remap);
 	}
 	rename_info->target_name_len = cpu_to_le32(2 * len_of_str);
-	count = 12 /* sizeof(struct set_file_rename) */ + (2 * len_of_str) + 2;
+	count = 12 /* sizeof(struct set_file_rename) */ + (2 * len_of_str);
 	byte_count += count;
 	pSMB->DataCount = cpu_to_le16(count);
 	pSMB->TotalDataCount = pSMB->DataCount;
@@ -3614,6 +3614,8 @@ findFirstRetry:
 		/* BB remember to free buffer if error BB */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 		if (rc == 0) {
+			unsigned int lnoff;
+
 			if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
 				psrch_inf->unicode = true;
 			else
@@ -3636,6 +3638,17 @@ findFirstRetry:
 					le16_to_cpu(parms->SearchCount);
 			psrch_inf->index_of_last_entry = 2 /* skip . and .. */ +
 				psrch_inf->entries_in_buffer;
+			lnoff = le16_to_cpu(parms->LastNameOffset);
+			if (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE <
+			      lnoff) {
+				cERROR(1, ("ignoring corrupt resume name"));
+				psrch_inf->last_entry = NULL;
+				return rc;
+			}
+
+			psrch_inf->last_entry = psrch_inf->srch_entries_start +
+							lnoff;
+
 			*pnetfid = parms->SearchHandle;
 		} else {
 			cifs_buf_release(pSMB);
@@ -3725,6 +3738,8 @@ int CIFSFindNext(const int xid, struct cifsTconInfo *tcon,
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
 		if (rc == 0) {
+			unsigned int lnoff;
+
 			/* BB fixme add lock for file (srch_info) struct here */
 			if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
 				psrch_inf->unicode = true;
@@ -3751,6 +3766,16 @@ int CIFSFindNext(const int xid, struct cifsTconInfo *tcon,
 						le16_to_cpu(parms->SearchCount);
 			psrch_inf->index_of_last_entry +=
 				psrch_inf->entries_in_buffer;
+			lnoff = le16_to_cpu(parms->LastNameOffset);
+			if (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE <
+			      lnoff) {
+				cERROR(1, ("ignoring corrupt resume name"));
+				psrch_inf->last_entry = NULL;
+				return rc;
+			} else
+				psrch_inf->last_entry =
+					psrch_inf->srch_entries_start + lnoff;
+
 /*  cFYI(1,("fnxt2 entries in buf %d index_of_last %d",
 	    psrch_inf->entries_in_buffer, psrch_inf->index_of_last_entry)); */
 
@@ -4876,6 +4901,61 @@ CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
 	return rc;
 }
 
+int
+CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
+			  bool delete_file, __u16 fid, __u32 pid_of_opener)
+{
+	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
+	char *data_offset;
+	int rc = 0;
+	__u16 params, param_offset, offset, byte_count, count;
+
+	cFYI(1, ("Set File Disposition (via SetFileInfo)"));
+	rc = small_smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB);
+
+	if (rc)
+		return rc;
+
+	pSMB->hdr.Pid = cpu_to_le16((__u16)pid_of_opener);
+	pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid_of_opener >> 16));
+
+	params = 6;
+	pSMB->MaxSetupCount = 0;
+	pSMB->Reserved = 0;
+	pSMB->Flags = 0;
+	pSMB->Timeout = 0;
+	pSMB->Reserved2 = 0;
+	param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
+	offset = param_offset + params;
+
+	data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
+
+	count = 1;
+	pSMB->MaxParameterCount = cpu_to_le16(2);
+	/* BB find max SMB PDU from sess */
+	pSMB->MaxDataCount = cpu_to_le16(1000);
+	pSMB->SetupCount = 1;
+	pSMB->Reserved3 = 0;
+	pSMB->SubCommand = cpu_to_le16(TRANS2_SET_FILE_INFORMATION);
+	byte_count = 3 /* pad */  + params + count;
+	pSMB->DataCount = cpu_to_le16(count);
+	pSMB->ParameterCount = cpu_to_le16(params);
+	pSMB->TotalDataCount = pSMB->DataCount;
+	pSMB->TotalParameterCount = pSMB->ParameterCount;
+	pSMB->ParameterOffset = cpu_to_le16(param_offset);
+	pSMB->DataOffset = cpu_to_le16(offset);
+	pSMB->Fid = fid;
+	pSMB->InformationLevel = cpu_to_le16(SMB_SET_FILE_DISPOSITION_INFO);
+	pSMB->Reserved4 = 0;
+	pSMB->hdr.smb_buf_length += byte_count;
+	pSMB->ByteCount = cpu_to_le16(byte_count);
+	*data_offset = delete_file ? 1 : 0;
+	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	if (rc)
+		cFYI(1, ("Send error in SetFileDisposition = %d", rc));
+
+	return rc;
+}
 
 int
 CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c
index a2e0673e1b08..1e0c1bd8f2e4 100644
--- a/fs/cifs/dns_resolve.c
+++ b/fs/cifs/dns_resolve.c
@@ -29,19 +29,55 @@
 #include "cifsproto.h"
 #include "cifs_debug.h"
 
-static int dns_resolver_instantiate(struct key *key, const void *data,
+/* Checks if supplied name is IP address
+ * returns:
+ * 		1 - name is IP
+ * 		0 - name is not IP
+ */
+static int
+is_ip(const char *name)
+{
+	int rc;
+	struct sockaddr_in sin_server;
+	struct sockaddr_in6 sin_server6;
+
+	rc = cifs_inet_pton(AF_INET, name,
+			&sin_server.sin_addr.s_addr);
+
+	if (rc <= 0) {
+		/* not ipv4 address, try ipv6 */
+		rc = cifs_inet_pton(AF_INET6, name,
+				&sin_server6.sin6_addr.in6_u);
+		if (rc > 0)
+			return 1;
+	} else {
+		return 1;
+	}
+	/* we failed translating address */
+	return 0;
+}
+
+static int
+dns_resolver_instantiate(struct key *key, const void *data,
 		size_t datalen)
 {
 	int rc = 0;
 	char *ip;
 
-	ip = kmalloc(datalen+1, GFP_KERNEL);
+	ip = kmalloc(datalen + 1, GFP_KERNEL);
 	if (!ip)
 		return -ENOMEM;
 
 	memcpy(ip, data, datalen);
 	ip[datalen] = '\0';
 
+	/* make sure this looks like an address */
+	if (!is_ip((const char *) ip)) {
+		kfree(ip);
+		return -EINVAL;
+	}
+
+	key->type_data.x[0] = datalen;
 	rcu_assign_pointer(key->payload.data, ip);
 
 	return rc;
@@ -62,33 +98,6 @@ struct key_type key_type_dns_resolver = {
 	.match       = user_match,
 };
 
-/* Checks if supplied name is IP address
- * returns:
- * 		1 - name is IP
- * 		0 - name is not IP
- */
-static int is_ip(const char *name)
-{
-	int rc;
-	struct sockaddr_in sin_server;
-	struct sockaddr_in6 sin_server6;
-
-	rc = cifs_inet_pton(AF_INET, name,
-			&sin_server.sin_addr.s_addr);
-
-	if (rc <= 0) {
-		/* not ipv4 address, try ipv6 */
-		rc = cifs_inet_pton(AF_INET6, name,
-				&sin_server6.sin6_addr.in6_u);
-		if (rc > 0)
-			return 1;
-	} else {
-		return 1;
-	}
-	/* we failed translating address */
-	return 0;
-}
-
 /* Resolves server name to ip address.
  * input:
  * 	unc - server UNC
@@ -140,6 +149,7 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
 
 	rkey = request_key(&key_type_dns_resolver, name, "");
 	if (!IS_ERR(rkey)) {
+		len = rkey->type_data.x[0];
 		data = rkey->payload.data;
 	} else {
 		cERROR(1, ("%s: unable to resolve: %s", __func__, name));
@@ -148,11 +158,9 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
 
 skip_upcall:
 	if (data) {
-		len = strlen(data);
-		*ip_addr = kmalloc(len+1, GFP_KERNEL);
+		*ip_addr = kmalloc(len + 1, GFP_KERNEL);
 		if (*ip_addr) {
-			memcpy(*ip_addr, data, len);
-			(*ip_addr)[len] = '\0';
+			memcpy(*ip_addr, data, len + 1);
 			if (!IS_ERR(rkey))
 				cFYI(1, ("%s: resolved: %s to %s", __func__,
 							name,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index cbefe1f1f9fe..c4a8a0605125 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -107,7 +107,7 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
 
 	/* want handles we can use to read with first
 	   in the list so we do not have to walk the
-	   list to search for one in prepare_write */
+	   list to search for one in write_begin */
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY) {
 		list_add_tail(&pCifsFile->flist,
 			      &pCifsInode->openFileList);
@@ -915,7 +915,7 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data,
 }
 
 static ssize_t cifs_write(struct file *file, const char *write_data,
-	size_t write_size, loff_t *poffset)
+			  size_t write_size, loff_t *poffset)
 {
 	int rc = 0;
 	unsigned int bytes_written = 0;
@@ -1065,6 +1065,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode)
 struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode)
 {
 	struct cifsFileInfo *open_file;
+	bool any_available = false;
 	int rc;
 
 	/* Having a null inode here (because mapping->host was set to zero by
@@ -1080,8 +1081,10 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode)
 	read_lock(&GlobalSMBSeslock);
 refind_writable:
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
-		if (open_file->closePend)
+		if (open_file->closePend ||
+		    (!any_available && open_file->pid != current->tgid))
 			continue;
+
 		if (open_file->pfile &&
 		    ((open_file->pfile->f_flags & O_RDWR) ||
 		     (open_file->pfile->f_flags & O_WRONLY))) {
@@ -1131,6 +1134,11 @@ refind_writable:
 			   of the loop here. */
 		}
 	}
+	/* couldn't find useable FH with same pid, try any available */
+	if (!any_available) {
+		any_available = true;
+		goto refind_writable;
+	}
 	read_unlock(&GlobalSMBSeslock);
 	return NULL;
 }
@@ -1447,49 +1455,52 @@ static int cifs_writepage(struct page *page, struct writeback_control *wbc)
 	return rc;
 }
 
-static int cifs_commit_write(struct file *file, struct page *page,
-	unsigned offset, unsigned to)
+static int cifs_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
 {
-	int xid;
-	int rc = 0;
-	struct inode *inode = page->mapping->host;
-	loff_t position = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
-	char *page_data;
+	int rc;
+	struct inode *inode = mapping->host;
 
-	xid = GetXid();
-	cFYI(1, ("commit write for page %p up to position %lld for %d",
-		 page, position, to));
-	spin_lock(&inode->i_lock);
-	if (position > inode->i_size)
-		i_size_write(inode, position);
+	cFYI(1, ("write_end for page %p from pos %lld with %d bytes",
+		 page, pos, copied));
+
+	if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE)
+		SetPageUptodate(page);
 
-	spin_unlock(&inode->i_lock);
 	if (!PageUptodate(page)) {
-		position =  ((loff_t)page->index << PAGE_CACHE_SHIFT) + offset;
-		/* can not rely on (or let) writepage write this data */
-		if (to < offset) {
-			cFYI(1, ("Illegal offsets, can not copy from %d to %d",
-				offset, to));
-			FreeXid(xid);
-			return rc;
-		}
+		char *page_data;
+		unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+		int xid;
+
+		xid = GetXid();
 		/* this is probably better than directly calling
 		   partialpage_write since in this function the file handle is
 		   known which we might as well	leverage */
 		/* BB check if anything else missing out of ppw
 		   such as updating last write time */
 		page_data = kmap(page);
-		rc = cifs_write(file, page_data + offset, to-offset,
-				&position);
-		if (rc > 0)
-			rc = 0;
-		/* else if (rc < 0) should we set writebehind rc? */
+		rc = cifs_write(file, page_data + offset, copied, &pos);
+		/* if (rc < 0) should we set writebehind rc? */
 		kunmap(page);
+
+		FreeXid(xid);
 	} else {
+		rc = copied;
+		pos += copied;
 		set_page_dirty(page);
 	}
 
-	FreeXid(xid);
+	if (rc > 0) {
+		spin_lock(&inode->i_lock);
+		if (pos > inode->i_size)
+			i_size_write(inode, pos);
+		spin_unlock(&inode->i_lock);
+	}
+
+	unlock_page(page);
+	page_cache_release(page);
+
 	return rc;
 }
 
@@ -2035,49 +2046,44 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
 		return true;
 }
 
-static int cifs_prepare_write(struct file *file, struct page *page,
-	unsigned from, unsigned to)
+static int cifs_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
 {
-	int rc = 0;
-	loff_t i_size;
-	loff_t offset;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	loff_t offset = pos & (PAGE_CACHE_SIZE - 1);
 
-	cFYI(1, ("prepare write for page %p from %d to %d", page, from, to));
-	if (PageUptodate(page))
+	cFYI(1, ("write_begin from %lld len %d", (long long)pos, len));
+
+	*pagep = __grab_cache_page(mapping, index);
+	if (!*pagep)
+		return -ENOMEM;
+
+	if (PageUptodate(*pagep))
 		return 0;
 
 	/* If we are writing a full page it will be up to date,
 	   no need to read from the server */
-	if ((to == PAGE_CACHE_SIZE) && (from == 0)) {
-		SetPageUptodate(page);
+	if (len == PAGE_CACHE_SIZE && flags & AOP_FLAG_UNINTERRUPTIBLE)
 		return 0;
-	}
 
-	offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
-	i_size = i_size_read(page->mapping->host);
+	if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
+		int rc;
 
-	if ((offset >= i_size) ||
-	    ((from == 0) && (offset + to) >= i_size)) {
-		/*
-		 * We don't need to read data beyond the end of the file.
-		 * zero it, and set the page uptodate
-		 */
-		simple_prepare_write(file, page, from, to);
-		SetPageUptodate(page);
-	} else if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
 		/* might as well read a page, it is fast enough */
-		rc = cifs_readpage_worker(file, page, &offset);
+		rc = cifs_readpage_worker(file, *pagep, &offset);
+
+		/* we do not need to pass errors back
+		   e.g. if we do not have read access to the file
+		   because cifs_write_end will attempt synchronous writes
+		   -- shaggy */
 	} else {
 		/* we could try using another file handle if there is one -
 		   but how would we lock it to prevent close of that handle
 		   racing with this read? In any case
-		   this will be written out by commit_write so is fine */
+		   this will be written out by write_end so is fine */
 	}
 
-	/* we do not need to pass errors back
-	   e.g. if we do not have read access to the file
-	   because cifs_commit_write will do the right thing.  -- shaggy */
-
 	return 0;
 }
 
@@ -2086,8 +2092,8 @@ const struct address_space_operations cifs_addr_ops = {
 	.readpages = cifs_readpages,
 	.writepage = cifs_writepage,
 	.writepages = cifs_writepages,
-	.prepare_write = cifs_prepare_write,
-	.commit_write = cifs_commit_write,
+	.write_begin = cifs_write_begin,
+	.write_end = cifs_write_end,
 	.set_page_dirty = __set_page_dirty_nobuffers,
 	/* .sync_page = cifs_sync_page, */
 	/* .direct_IO = */
@@ -2102,8 +2108,8 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
 	.readpage = cifs_readpage,
 	.writepage = cifs_writepage,
 	.writepages = cifs_writepages,
-	.prepare_write = cifs_prepare_write,
-	.commit_write = cifs_commit_write,
+	.write_begin = cifs_write_begin,
+	.write_end = cifs_write_end,
 	.set_page_dirty = __set_page_dirty_nobuffers,
 	/* .sync_page = cifs_sync_page, */
 	/* .direct_IO = */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9c548f110102..a8c833345fc9 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -665,40 +665,201 @@ struct inode *cifs_iget(struct super_block *sb, unsigned long ino)
 	return inode;
 }
 
-int cifs_unlink(struct inode *inode, struct dentry *direntry)
+static int
+cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid,
+		    char *full_path, __u32 dosattr)
+{
+	int rc;
+	int oplock = 0;
+	__u16 netfid;
+	__u32 netpid;
+	bool set_time = false;
+	struct cifsFileInfo *open_file;
+	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifsTconInfo *pTcon = cifs_sb->tcon;
+	FILE_BASIC_INFO	info_buf;
+
+	if (attrs->ia_valid & ATTR_ATIME) {
+		set_time = true;
+		info_buf.LastAccessTime =
+			cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
+	} else
+		info_buf.LastAccessTime = 0;
+
+	if (attrs->ia_valid & ATTR_MTIME) {
+		set_time = true;
+		info_buf.LastWriteTime =
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
+	} else
+		info_buf.LastWriteTime = 0;
+
+	/*
+	 * Samba throws this field away, but windows may actually use it.
+	 * Do not set ctime unless other time stamps are changed explicitly
+	 * (i.e. by utimes()) since we would then have a mix of client and
+	 * server times.
+	 */
+	if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
+		cFYI(1, ("CIFS - CTIME changed"));
+		info_buf.ChangeTime =
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
+	} else
+		info_buf.ChangeTime = 0;
+
+	info_buf.CreationTime = 0;	/* don't change */
+	info_buf.Attributes = cpu_to_le32(dosattr);
+
+	/*
+	 * If the file is already open for write, just use that fileid
+	 */
+	open_file = find_writable_file(cifsInode);
+	if (open_file) {
+		netfid = open_file->netfid;
+		netpid = open_file->pid;
+		goto set_via_filehandle;
+	}
+
+	/*
+	 * NT4 apparently returns success on this call, but it doesn't
+	 * really work.
+	 */
+	if (!(pTcon->ses->flags & CIFS_SES_NT4)) {
+		rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
+				     &info_buf, cifs_sb->local_nls,
+				     cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
+		if (rc == 0) {
+			cifsInode->cifsAttrs = dosattr;
+			goto out;
+		} else if (rc != -EOPNOTSUPP && rc != -EINVAL)
+			goto out;
+	}
+
+	cFYI(1, ("calling SetFileInfo since SetPathInfo for "
+		 "times not supported by this server"));
+	rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
+			 SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
+			 CREATE_NOT_DIR, &netfid, &oplock,
+			 NULL, cifs_sb->local_nls,
+			 cifs_sb->mnt_cifs_flags &
+				CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+	if (rc != 0) {
+		if (rc == -EIO)
+			rc = -EINVAL;
+		goto out;
+	}
+
+	netpid = current->tgid;
+
+set_via_filehandle:
+	rc = CIFSSMBSetFileInfo(xid, pTcon, &info_buf, netfid, netpid);
+	if (!rc)
+		cifsInode->cifsAttrs = dosattr;
+
+	if (open_file == NULL)
+		CIFSSMBClose(xid, pTcon, netfid);
+	else
+		atomic_dec(&open_file->wrtPending);
+out:
+	return rc;
+}
+
+/*
+ * open the given file (if it isn't already), set the DELETE_ON_CLOSE bit
+ * and rename it to a random name that hopefully won't conflict with
+ * anything else.
+ */
+static int
+cifs_rename_pending_delete(char *full_path, struct inode *inode, int xid)
+{
+	int oplock = 0;
+	int rc;
+	__u16 netfid;
+	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifsTconInfo *tcon = cifs_sb->tcon;
+	__u32 dosattr;
+	FILE_BASIC_INFO *info_buf;
+
+	rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
+			 DELETE|FILE_WRITE_ATTRIBUTES,
+			 CREATE_NOT_DIR|CREATE_DELETE_ON_CLOSE,
+			 &netfid, &oplock, NULL, cifs_sb->local_nls,
+			 cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+	if (rc != 0)
+		goto out;
+
+	/* set ATTR_HIDDEN and clear ATTR_READONLY */
+	cifsInode = CIFS_I(inode);
+	dosattr = cifsInode->cifsAttrs & ~ATTR_READONLY;
+	if (dosattr == 0)
+		dosattr |= ATTR_NORMAL;
+	dosattr |= ATTR_HIDDEN;
+
+	info_buf = kzalloc(sizeof(*info_buf), GFP_KERNEL);
+	if (info_buf == NULL) {
+		rc = -ENOMEM;
+		goto out_close;
+	}
+	info_buf->Attributes = cpu_to_le32(dosattr);
+	rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid, current->tgid);
+	kfree(info_buf);
+	if (rc != 0)
+		goto out_close;
+	cifsInode->cifsAttrs = dosattr;
+
+	/* silly-rename the file */
+	CIFSSMBRenameOpenFile(xid, tcon, netfid, NULL, cifs_sb->local_nls,
+				   cifs_sb->mnt_cifs_flags &
+					    CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+	/* set DELETE_ON_CLOSE */
+	rc = CIFSSMBSetFileDisposition(xid, tcon, true, netfid, current->tgid);
+
+	/*
+	 * some samba versions return -ENOENT when we try to set the file
+	 * disposition here. Likely a samba bug, but work around it for now
+	 */
+	if (rc == -ENOENT)
+		rc = 0;
+
+out_close:
+	CIFSSMBClose(xid, tcon, netfid);
+out:
+	return rc;
+}
+
+int cifs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int rc = 0;
 	int xid;
-	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *pTcon;
 	char *full_path = NULL;
-	struct cifsInodeInfo *cifsInode;
-	FILE_BASIC_INFO *pinfo_buf;
+	struct inode *inode = dentry->d_inode;
+	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	struct super_block *sb = dir->i_sb;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+	struct cifsTconInfo *tcon = cifs_sb->tcon;
+	struct iattr *attrs = NULL;
+	__u32 dosattr = 0, origattr = 0;
 
-	cFYI(1, ("cifs_unlink, inode = 0x%p", inode));
+	cFYI(1, ("cifs_unlink, dir=0x%p, dentry=0x%p", dir, dentry));
 
 	xid = GetXid();
 
-	if (inode)
-		cifs_sb = CIFS_SB(inode->i_sb);
-	else
-		cifs_sb = CIFS_SB(direntry->d_sb);
-	pTcon = cifs_sb->tcon;
-
-	/* Unlink can be called from rename so we can not grab the sem here
-	   since we deadlock otherwise */
-/*	mutex_lock(&direntry->d_sb->s_vfs_rename_mutex);*/
-	full_path = build_path_from_dentry(direntry);
-/*	mutex_unlock(&direntry->d_sb->s_vfs_rename_mutex);*/
+	/* Unlink can be called from rename so we can not take the
+	 * sb->s_vfs_rename_mutex here */
+	full_path = build_path_from_dentry(dentry);
 	if (full_path == NULL) {
 		FreeXid(xid);
 		return -ENOMEM;
 	}
 
-	if ((pTcon->ses->capabilities & CAP_UNIX) &&
+	if ((tcon->ses->capabilities & CAP_UNIX) &&
 		(CIFS_UNIX_POSIX_PATH_OPS_CAP &
-			le64_to_cpu(pTcon->fsUnixInfo.Capability))) {
-		rc = CIFSPOSIXDelFile(xid, pTcon, full_path,
+			le64_to_cpu(tcon->fsUnixInfo.Capability))) {
+		rc = CIFSPOSIXDelFile(xid, tcon, full_path,
 			SMB_POSIX_UNLINK_FILE_TARGET, cifs_sb->local_nls,
 			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 		cFYI(1, ("posix del rc %d", rc));
@@ -706,125 +867,60 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry)
 			goto psx_del_no_retry;
 	}
 
-	rc = CIFSSMBDelFile(xid, pTcon, full_path, cifs_sb->local_nls,
+retry_std_delete:
+	rc = CIFSSMBDelFile(xid, tcon, full_path, cifs_sb->local_nls,
 			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+
 psx_del_no_retry:
 	if (!rc) {
-		if (direntry->d_inode)
-			drop_nlink(direntry->d_inode);
+		if (inode)
+			drop_nlink(inode);
 	} else if (rc == -ENOENT) {
-		d_drop(direntry);
+		d_drop(dentry);
 	} else if (rc == -ETXTBSY) {
-		int oplock = 0;
-		__u16 netfid;
-
-		rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN, DELETE,
-				 CREATE_NOT_DIR | CREATE_DELETE_ON_CLOSE,
-				 &netfid, &oplock, NULL, cifs_sb->local_nls,
-				 cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
-		if (rc == 0) {
-			CIFSSMBRenameOpenFile(xid, pTcon, netfid, NULL,
-					      cifs_sb->local_nls,
-					      cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
-			CIFSSMBClose(xid, pTcon, netfid);
-			if (direntry->d_inode)
-				drop_nlink(direntry->d_inode);
+		rc = cifs_rename_pending_delete(full_path, inode, xid);
+		if (rc == 0)
+			drop_nlink(inode);
+	} else if (rc == -EACCES && dosattr == 0) {
+		attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
+		if (attrs == NULL) {
+			rc = -ENOMEM;
+			goto out_reval;
 		}
-	} else if (rc == -EACCES) {
-		/* try only if r/o attribute set in local lookup data? */
-		pinfo_buf = kzalloc(sizeof(FILE_BASIC_INFO), GFP_KERNEL);
-		if (pinfo_buf) {
-			/* ATTRS set to normal clears r/o bit */
-			pinfo_buf->Attributes = cpu_to_le32(ATTR_NORMAL);
-			if (!(pTcon->ses->flags & CIFS_SES_NT4))
-				rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
-						     pinfo_buf,
-						     cifs_sb->local_nls,
-						     cifs_sb->mnt_cifs_flags &
-							CIFS_MOUNT_MAP_SPECIAL_CHR);
-			else
-				rc = -EOPNOTSUPP;
 
-			if (rc == -EOPNOTSUPP) {
-				int oplock = 0;
-				__u16 netfid;
-			/*	rc = CIFSSMBSetAttrLegacy(xid, pTcon,
-							  full_path,
-							  (__u16)ATTR_NORMAL,
-							  cifs_sb->local_nls);
-			   For some strange reason it seems that NT4 eats the
-			   old setattr call without actually setting the
-			   attributes so on to the third attempted workaround
-			   */
-
-			/* BB could scan to see if we already have it open
-			   and pass in pid of opener to function */
-				rc = CIFSSMBOpen(xid, pTcon, full_path,
-						 FILE_OPEN, SYNCHRONIZE |
-						 FILE_WRITE_ATTRIBUTES, 0,
-						 &netfid, &oplock, NULL,
-						 cifs_sb->local_nls,
-						 cifs_sb->mnt_cifs_flags &
-						    CIFS_MOUNT_MAP_SPECIAL_CHR);
-				if (rc == 0) {
-					rc = CIFSSMBSetFileInfo(xid, pTcon,
-								pinfo_buf,
-								netfid,
-								current->tgid);
-					CIFSSMBClose(xid, pTcon, netfid);
-				}
-			}
-			kfree(pinfo_buf);
-		}
-		if (rc == 0) {
-			rc = CIFSSMBDelFile(xid, pTcon, full_path,
-					    cifs_sb->local_nls,
-					    cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
-			if (!rc) {
-				if (direntry->d_inode)
-					drop_nlink(direntry->d_inode);
-			} else if (rc == -ETXTBSY) {
-				int oplock = 0;
-				__u16 netfid;
-
-				rc = CIFSSMBOpen(xid, pTcon, full_path,
-						 FILE_OPEN, DELETE,
-						 CREATE_NOT_DIR |
-						 CREATE_DELETE_ON_CLOSE,
-						 &netfid, &oplock, NULL,
-						 cifs_sb->local_nls,
-						 cifs_sb->mnt_cifs_flags &
-						    CIFS_MOUNT_MAP_SPECIAL_CHR);
-				if (rc == 0) {
-					CIFSSMBRenameOpenFile(xid, pTcon,
-						netfid, NULL,
-						cifs_sb->local_nls,
-						cifs_sb->mnt_cifs_flags &
-						    CIFS_MOUNT_MAP_SPECIAL_CHR);
-					CIFSSMBClose(xid, pTcon, netfid);
-					if (direntry->d_inode)
-						drop_nlink(direntry->d_inode);
-				}
-			/* BB if rc = -ETXTBUSY goto the rename logic BB */
-			}
-		}
-	}
-	if (direntry->d_inode) {
-		cifsInode = CIFS_I(direntry->d_inode);
-		cifsInode->time = 0;	/* will force revalidate to get info
-					   when needed */
-		direntry->d_inode->i_ctime = current_fs_time(inode->i_sb);
+		/* try to reset dos attributes */
+		origattr = cifsInode->cifsAttrs;
+		if (origattr == 0)
+			origattr |= ATTR_NORMAL;
+		dosattr = origattr & ~ATTR_READONLY;
+		if (dosattr == 0)
+			dosattr |= ATTR_NORMAL;
+		dosattr |= ATTR_HIDDEN;
+
+		rc = cifs_set_file_info(inode, attrs, xid, full_path, dosattr);
+		if (rc != 0)
+			goto out_reval;
+
+		goto retry_std_delete;
 	}
+
+	/* undo the setattr if we errored out and it's needed */
+	if (rc != 0 && dosattr != 0)
+		cifs_set_file_info(inode, attrs, xid, full_path, origattr);
+
+out_reval:
 	if (inode) {
-		inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
 		cifsInode = CIFS_I(inode);
-		cifsInode->time = 0;	/* force revalidate of dir as well */
+		cifsInode->time = 0;	/* will force revalidate to get info
+					   when needed */
+		inode->i_ctime = current_fs_time(sb);
 	}
+	dir->i_ctime = dir->i_mtime = current_fs_time(sb);
+	cifsInode = CIFS_I(dir);
+	CIFS_I(dir)->time = 0;	/* force revalidate of dir as well */
 
 	kfree(full_path);
+	kfree(attrs);
 	FreeXid(xid);
 	return rc;
 }
@@ -869,7 +965,7 @@ static void posix_fill_in_inode(struct inode *tmp_inode,
 
 int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
 {
-	int rc = 0;
+	int rc = 0, tmprc;
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct cifsTconInfo *pTcon;
@@ -931,6 +1027,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
 				kfree(pInfo);
 				goto mkdir_get_info;
 			}
+
 			/* Is an i_ino of zero legal? */
 			/* Are there sanity checks we can use to ensure that
 			   the server is really filling in that field? */
@@ -1019,12 +1116,20 @@ mkdir_get_info:
 			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
 			    (mode & S_IWUGO) == 0) {
 				FILE_BASIC_INFO pInfo;
+				struct cifsInodeInfo *cifsInode;
+				u32 dosattrs;
+
 				memset(&pInfo, 0, sizeof(pInfo));
-				pInfo.Attributes = cpu_to_le32(ATTR_READONLY);
-				CIFSSMBSetPathInfo(xid, pTcon, full_path,
-						&pInfo, cifs_sb->local_nls,
+				cifsInode = CIFS_I(newinode);
+				dosattrs = cifsInode->cifsAttrs|ATTR_READONLY;
+				pInfo.Attributes = cpu_to_le32(dosattrs);
+				tmprc = CIFSSMBSetPathInfo(xid, pTcon,
+						full_path, &pInfo,
+						cifs_sb->local_nls,
 						cifs_sb->mnt_cifs_flags &
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
+				if (tmprc == 0)
+					cifsInode->cifsAttrs = dosattrs;
 			}
 			if (direntry->d_inode) {
 				if (cifs_sb->mnt_cifs_flags &
@@ -1096,117 +1201,141 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
 	return rc;
 }
 
+static int
+cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath,
+		struct dentry *to_dentry, const char *toPath)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(from_dentry->d_sb);
+	struct cifsTconInfo *pTcon = cifs_sb->tcon;
+	__u16 srcfid;
+	int oplock, rc;
+
+	/* try path-based rename first */
+	rc = CIFSSMBRename(xid, pTcon, fromPath, toPath, cifs_sb->local_nls,
+			   cifs_sb->mnt_cifs_flags &
+				CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+	/*
+	 * don't bother with rename by filehandle unless file is busy and
+	 * source Note that cross directory moves do not work with
+	 * rename by filehandle to various Windows servers.
+	 */
+	if (rc == 0 || rc != -ETXTBSY)
+		return rc;
+
+	/* open the file to be renamed -- we need DELETE perms */
+	rc = CIFSSMBOpen(xid, pTcon, fromPath, FILE_OPEN, DELETE,
+			 CREATE_NOT_DIR, &srcfid, &oplock, NULL,
+			 cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+				CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+	if (rc == 0) {
+		rc = CIFSSMBRenameOpenFile(xid, pTcon, srcfid,
+				(const char *) to_dentry->d_name.name,
+				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+					CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+		CIFSSMBClose(xid, pTcon, srcfid);
+	}
+
+	return rc;
+}
+
 int cifs_rename(struct inode *source_inode, struct dentry *source_direntry,
 	struct inode *target_inode, struct dentry *target_direntry)
 {
-	char *fromName;
-	char *toName;
+	char *fromName = NULL;
+	char *toName = NULL;
 	struct cifs_sb_info *cifs_sb_source;
 	struct cifs_sb_info *cifs_sb_target;
 	struct cifsTconInfo *pTcon;
+	FILE_UNIX_BASIC_INFO *info_buf_source = NULL;
+	FILE_UNIX_BASIC_INFO *info_buf_target;
 	int xid;
-	int rc = 0;
-
-	xid = GetXid();
+	int rc;
 
 	cifs_sb_target = CIFS_SB(target_inode->i_sb);
 	cifs_sb_source = CIFS_SB(source_inode->i_sb);
 	pTcon = cifs_sb_source->tcon;
 
+	xid = GetXid();
+
+	/*
+	 * BB: this might be allowed if same server, but different share.
+	 * Consider adding support for this
+	 */
 	if (pTcon != cifs_sb_target->tcon) {
-		FreeXid(xid);
-		return -EXDEV;	/* BB actually could be allowed if same server,
-				   but different share.
-				   Might eventually add support for this */
+		rc = -EXDEV;
+		goto cifs_rename_exit;
 	}
 
-	/* we already  have the rename sem so we do not need to grab it again
-	   here to protect the path integrity */
+	/*
+	 * we already have the rename sem so we do not need to
+	 * grab it again here to protect the path integrity
+	 */
 	fromName = build_path_from_dentry(source_direntry);
+	if (fromName == NULL) {
+		rc = -ENOMEM;
+		goto cifs_rename_exit;
+	}
+
 	toName = build_path_from_dentry(target_direntry);
-	if ((fromName == NULL) || (toName == NULL)) {
+	if (toName == NULL) {
 		rc = -ENOMEM;
 		goto cifs_rename_exit;
 	}
 
-	rc = CIFSSMBRename(xid, pTcon, fromName, toName,
-			   cifs_sb_source->local_nls,
-			   cifs_sb_source->mnt_cifs_flags &
-				CIFS_MOUNT_MAP_SPECIAL_CHR);
+	rc = cifs_do_rename(xid, source_direntry, fromName,
+			    target_direntry, toName);
+
 	if (rc == -EEXIST) {
-		/* check if they are the same file because rename of hardlinked
-		   files is a noop */
-		FILE_UNIX_BASIC_INFO *info_buf_source;
-		FILE_UNIX_BASIC_INFO *info_buf_target;
-
-		info_buf_source =
-			kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL);
-		if (info_buf_source != NULL) {
+		if (pTcon->unix_ext) {
+			/*
+			 * Are src and dst hardlinks of same inode? We can
+			 * only tell with unix extensions enabled
+			 */
+			info_buf_source =
+				kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO),
+						GFP_KERNEL);
+			if (info_buf_source == NULL)
+				goto unlink_target;
+
 			info_buf_target = info_buf_source + 1;
-			if (pTcon->unix_ext)
-				rc = CIFSSMBUnixQPathInfo(xid, pTcon, fromName,
-					info_buf_source,
-					cifs_sb_source->local_nls,
-					cifs_sb_source->mnt_cifs_flags &
+			rc = CIFSSMBUnixQPathInfo(xid, pTcon, fromName,
+						info_buf_source,
+						cifs_sb_source->local_nls,
+						cifs_sb_source->mnt_cifs_flags &
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
-			/* else rc is still EEXIST so will fall through to
-			   unlink the target and retry rename */
-			if (rc == 0) {
-				rc = CIFSSMBUnixQPathInfo(xid, pTcon, toName,
-						info_buf_target,
+			if (rc != 0)
+				goto unlink_target;
+
+			rc = CIFSSMBUnixQPathInfo(xid, pTcon,
+						toName, info_buf_target,
 						cifs_sb_target->local_nls,
 						/* remap based on source sb */
 						cifs_sb_source->mnt_cifs_flags &
-						    CIFS_MOUNT_MAP_SPECIAL_CHR);
-			}
-			if ((rc == 0) &&
-			    (info_buf_source->UniqueId ==
-			     info_buf_target->UniqueId)) {
-			/* do not rename since the files are hardlinked which
-			   is a noop */
-			} else {
-			/* we either can not tell the files are hardlinked
-			   (as with Windows servers) or files are not
-			   hardlinked so delete the target manually before
-			   renaming to follow POSIX rather than Windows
-			   semantics */
-				cifs_unlink(target_inode, target_direntry);
-				rc = CIFSSMBRename(xid, pTcon, fromName,
-						   toName,
-						   cifs_sb_source->local_nls,
-						   cifs_sb_source->mnt_cifs_flags
-						   & CIFS_MOUNT_MAP_SPECIAL_CHR);
-			}
-			kfree(info_buf_source);
-		} /* if we can not get memory just leave rc as EEXIST */
-	}
-
-	if (rc)
-		cFYI(1, ("rename rc %d", rc));
-
-	if ((rc == -EIO) || (rc == -EEXIST)) {
-		int oplock = 0;
-		__u16 netfid;
-
-		/* BB FIXME Is Generic Read correct for rename? */
-		/* if renaming directory - we should not say CREATE_NOT_DIR,
-		   need to test renaming open directory, also GENERIC_READ
-		   might not right be right access to request */
-		rc = CIFSSMBOpen(xid, pTcon, fromName, FILE_OPEN, GENERIC_READ,
-				 CREATE_NOT_DIR, &netfid, &oplock, NULL,
-				 cifs_sb_source->local_nls,
-				 cifs_sb_source->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
-		if (rc == 0) {
-			rc = CIFSSMBRenameOpenFile(xid, pTcon, netfid, toName,
-					      cifs_sb_source->local_nls,
-					      cifs_sb_source->mnt_cifs_flags &
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
-			CIFSSMBClose(xid, pTcon, netfid);
-		}
+
+			if (rc == 0 && (info_buf_source->UniqueId ==
+					info_buf_target->UniqueId))
+				/* same file, POSIX says that this is a noop */
+				goto cifs_rename_exit;
+		} /* else ... BB we could add the same check for Windows by
+		     checking the UniqueId via FILE_INTERNAL_INFO */
+unlink_target:
+		/*
+		 * we either can not tell the files are hardlinked (as with
+		 * Windows servers) or files are not hardlinked. Delete the
+		 * target manually before renaming to follow POSIX rather than
+		 * Windows semantics
+		 */
+		cifs_unlink(target_inode, target_direntry);
+		rc = cifs_do_rename(xid, source_direntry, fromName,
+				    target_direntry, toName);
 	}
 
 cifs_rename_exit:
+	kfree(info_buf_source);
 	kfree(fromName);
 	kfree(toName);
 	FreeXid(xid);
@@ -1507,101 +1636,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 }
 
 static int
-cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid,
-		    char *full_path, __u32 dosattr)
-{
-	int rc;
-	int oplock = 0;
-	__u16 netfid;
-	__u32 netpid;
-	bool set_time = false;
-	struct cifsFileInfo *open_file;
-	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	struct cifsTconInfo *pTcon = cifs_sb->tcon;
-	FILE_BASIC_INFO	info_buf;
-
-	if (attrs->ia_valid & ATTR_ATIME) {
-		set_time = true;
-		info_buf.LastAccessTime =
-			cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
-	} else
-		info_buf.LastAccessTime = 0;
-
-	if (attrs->ia_valid & ATTR_MTIME) {
-		set_time = true;
-		info_buf.LastWriteTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
-	} else
-		info_buf.LastWriteTime = 0;
-
-	/*
-	 * Samba throws this field away, but windows may actually use it.
-	 * Do not set ctime unless other time stamps are changed explicitly
-	 * (i.e. by utimes()) since we would then have a mix of client and
-	 * server times.
-	 */
-	if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
-		cFYI(1, ("CIFS - CTIME changed"));
-		info_buf.ChangeTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
-	} else
-		info_buf.ChangeTime = 0;
-
-	info_buf.CreationTime = 0;	/* don't change */
-	info_buf.Attributes = cpu_to_le32(dosattr);
-
-	/*
-	 * If the file is already open for write, just use that fileid
-	 */
-	open_file = find_writable_file(cifsInode);
-	if (open_file) {
-		netfid = open_file->netfid;
-		netpid = open_file->pid;
-		goto set_via_filehandle;
-	}
-
-	/*
-	 * NT4 apparently returns success on this call, but it doesn't
-	 * really work.
-	 */
-	if (!(pTcon->ses->flags & CIFS_SES_NT4)) {
-		rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
-				     &info_buf, cifs_sb->local_nls,
-				     cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
-		if (rc != -EOPNOTSUPP && rc != -EINVAL)
-			goto out;
-	}
-
-	cFYI(1, ("calling SetFileInfo since SetPathInfo for "
-		 "times not supported by this server"));
-	rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
-			 SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
-			 CREATE_NOT_DIR, &netfid, &oplock,
-			 NULL, cifs_sb->local_nls,
-			 cifs_sb->mnt_cifs_flags &
-				CIFS_MOUNT_MAP_SPECIAL_CHR);
-
-	if (rc != 0) {
-		if (rc == -EIO)
-			rc = -EINVAL;
-		goto out;
-	}
-
-	netpid = current->tgid;
-
-set_via_filehandle:
-	rc = CIFSSMBSetFileInfo(xid, pTcon, &info_buf, netfid, netpid);
-	if (open_file == NULL)
-		CIFSSMBClose(xid, pTcon, netfid);
-	else
-		atomic_dec(&open_file->wrtPending);
-out:
-	return rc;
-}
-
-static int
 cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 {
 	int rc;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 4b17f8fe3157..654d972a88f4 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -150,8 +150,7 @@ cifs_buf_get(void)
    but it may be more efficient to always alloc same size
    albeit slightly larger than necessary and maxbuffersize
    defaults to this and can not be bigger */
-	ret_buf = (struct smb_hdr *) mempool_alloc(cifs_req_poolp,
-						   GFP_KERNEL | GFP_NOFS);
+	ret_buf = mempool_alloc(cifs_req_poolp, GFP_NOFS);
 
 	/* clear the first few header bytes */
 	/* for most paths, more is cleared in header_assemble */
@@ -188,8 +187,7 @@ cifs_small_buf_get(void)
    but it may be more efficient to always alloc same size
    albeit slightly larger than necessary and maxbuffersize
    defaults to this and can not be bigger */
-	ret_buf = (struct smb_hdr *) mempool_alloc(cifs_sm_req_poolp,
-						   GFP_KERNEL | GFP_NOFS);
+	ret_buf = mempool_alloc(cifs_sm_req_poolp, GFP_NOFS);
 	if (ret_buf) {
 	/* No need to clear memory here, cleared in header assemble */
 	/*	memset(ret_buf, 0, sizeof(struct smb_hdr) + 27);*/
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 5f40ed3473f5..765adf12d54f 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -640,6 +640,70 @@ static int is_dir_changed(struct file *file)
 
 }
 
+static int cifs_save_resume_key(const char *current_entry,
+	struct cifsFileInfo *cifsFile)
+{
+	int rc = 0;
+	unsigned int len = 0;
+	__u16 level;
+	char *filename;
+
+	if ((cifsFile == NULL) || (current_entry == NULL))
+		return -EINVAL;
+
+	level = cifsFile->srch_inf.info_level;
+
+	if (level == SMB_FIND_FILE_UNIX) {
+		FILE_UNIX_INFO *pFindData = (FILE_UNIX_INFO *)current_entry;
+
+		filename = &pFindData->FileName[0];
+		if (cifsFile->srch_inf.unicode) {
+			len = cifs_unicode_bytelen(filename);
+		} else {
+			/* BB should we make this strnlen of PATH_MAX? */
+			len = strnlen(filename, PATH_MAX);
+		}
+		cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
+	} else if (level == SMB_FIND_FILE_DIRECTORY_INFO) {
+		FILE_DIRECTORY_INFO *pFindData =
+			(FILE_DIRECTORY_INFO *)current_entry;
+		filename = &pFindData->FileName[0];
+		len = le32_to_cpu(pFindData->FileNameLength);
+		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+	} else if (level == SMB_FIND_FILE_FULL_DIRECTORY_INFO) {
+		FILE_FULL_DIRECTORY_INFO *pFindData =
+			(FILE_FULL_DIRECTORY_INFO *)current_entry;
+		filename = &pFindData->FileName[0];
+		len = le32_to_cpu(pFindData->FileNameLength);
+		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+	} else if (level == SMB_FIND_FILE_ID_FULL_DIR_INFO) {
+		SEARCH_ID_FULL_DIR_INFO *pFindData =
+			(SEARCH_ID_FULL_DIR_INFO *)current_entry;
+		filename = &pFindData->FileName[0];
+		len = le32_to_cpu(pFindData->FileNameLength);
+		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+	} else if (level == SMB_FIND_FILE_BOTH_DIRECTORY_INFO) {
+		FILE_BOTH_DIRECTORY_INFO *pFindData =
+			(FILE_BOTH_DIRECTORY_INFO *)current_entry;
+		filename = &pFindData->FileName[0];
+		len = le32_to_cpu(pFindData->FileNameLength);
+		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+	} else if (level == SMB_FIND_FILE_INFO_STANDARD) {
+		FIND_FILE_STANDARD_INFO *pFindData =
+			(FIND_FILE_STANDARD_INFO *)current_entry;
+		filename = &pFindData->FileName[0];
+		/* one byte length, no name conversion */
+		len = (unsigned int)pFindData->FileNameLength;
+		cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
+	} else {
+		cFYI(1, ("Unknown findfirst level %d", level));
+		return -EINVAL;
+	}
+	cifsFile->srch_inf.resume_name_len = len;
+	cifsFile->srch_inf.presume_name = filename;
+	return rc;
+}
+
 /* find the corresponding entry in the search */
 /* Note that the SMB server returns search entries for . and .. which
    complicates logic here if we choose to parse for them and we do not
@@ -703,6 +767,7 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon,
 	while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) &&
 	      (rc == 0) && !cifsFile->srch_inf.endOfSearch) {
 		cFYI(1, ("calling findnext2"));
+		cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
 		rc = CIFSFindNext(xid, pTcon, cifsFile->netfid,
 				  &cifsFile->srch_inf);
 		if (rc)
@@ -919,69 +984,6 @@ static int cifs_filldir(char *pfindEntry, struct file *file,
 	return rc;
 }
 
-static int cifs_save_resume_key(const char *current_entry,
-	struct cifsFileInfo *cifsFile)
-{
-	int rc = 0;
-	unsigned int len = 0;
-	__u16 level;
-	char *filename;
-
-	if ((cifsFile == NULL) || (current_entry == NULL))
-		return -EINVAL;
-
-	level = cifsFile->srch_inf.info_level;
-
-	if (level == SMB_FIND_FILE_UNIX) {
-		FILE_UNIX_INFO *pFindData = (FILE_UNIX_INFO *)current_entry;
-
-		filename = &pFindData->FileName[0];
-		if (cifsFile->srch_inf.unicode) {
-			len = cifs_unicode_bytelen(filename);
-		} else {
-			/* BB should we make this strnlen of PATH_MAX? */
-			len = strnlen(filename, PATH_MAX);
-		}
-		cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
-	} else if (level == SMB_FIND_FILE_DIRECTORY_INFO) {
-		FILE_DIRECTORY_INFO *pFindData =
-			(FILE_DIRECTORY_INFO *)current_entry;
-		filename = &pFindData->FileName[0];
-		len = le32_to_cpu(pFindData->FileNameLength);
-		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-	} else if (level == SMB_FIND_FILE_FULL_DIRECTORY_INFO) {
-		FILE_FULL_DIRECTORY_INFO *pFindData =
-			(FILE_FULL_DIRECTORY_INFO *)current_entry;
-		filename = &pFindData->FileName[0];
-		len = le32_to_cpu(pFindData->FileNameLength);
-		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-	} else if (level == SMB_FIND_FILE_ID_FULL_DIR_INFO) {
-		SEARCH_ID_FULL_DIR_INFO *pFindData =
-			(SEARCH_ID_FULL_DIR_INFO *)current_entry;
-		filename = &pFindData->FileName[0];
-		len = le32_to_cpu(pFindData->FileNameLength);
-		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-	} else if (level == SMB_FIND_FILE_BOTH_DIRECTORY_INFO) {
-		FILE_BOTH_DIRECTORY_INFO *pFindData =
-			(FILE_BOTH_DIRECTORY_INFO *)current_entry;
-		filename = &pFindData->FileName[0];
-		len = le32_to_cpu(pFindData->FileNameLength);
-		cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-	} else if (level == SMB_FIND_FILE_INFO_STANDARD) {
-		FIND_FILE_STANDARD_INFO *pFindData =
-			(FIND_FILE_STANDARD_INFO *)current_entry;
-		filename = &pFindData->FileName[0];
-		/* one byte length, no name conversion */
-		len = (unsigned int)pFindData->FileNameLength;
-		cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
-	} else {
-		cFYI(1, ("Unknown findfirst level %d", level));
-		return -EINVAL;
-	}
-	cifsFile->srch_inf.resume_name_len = len;
-	cifsFile->srch_inf.presume_name = filename;
-	return rc;
-}
 
 int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
 {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 252fdc0567f1..2851d5da0c8c 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -624,8 +624,10 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time,
 					 ses, nls_cp);
 
 ssetup_exit:
-	if (spnego_key)
+	if (spnego_key) {
+		key_revoke(spnego_key);
 		key_put(spnego_key);
+	}
 	kfree(str_area);
 	if (resp_buf_type == CIFS_SMALL_BUFFER) {
 		cFYI(1, ("ssetup freeing small buf %p", iov[0].iov_base));
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index e286db9f5ee2..bf0e6d8e382a 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -50,8 +50,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct cifsSesInfo *ses)
 		return NULL;
 	}
 
-	temp = (struct mid_q_entry *) mempool_alloc(cifs_mid_poolp,
-						    GFP_KERNEL | GFP_NOFS);
+	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
 	if (temp == NULL)
 		return temp;
 	else {
diff --git a/fs/dcache.c b/fs/dcache.c
index 80e93956aced..e7a1a99b7464 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1395,6 +1395,10 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
 		if (dentry->d_parent != parent)
 			goto next;
 
+		/* non-existing due to RCU? */
+		if (d_unhashed(dentry))
+			goto next;
+
 		/*
 		 * It is safe to compare names since d_move() cannot
 		 * change the qstr (protected by d_lock).
@@ -1410,10 +1414,8 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
 				goto next;
 		}
 
-		if (!d_unhashed(dentry)) {
-			atomic_inc(&dentry->d_count);
-			found = dentry;
-		}
+		atomic_inc(&dentry->d_count);
+		found = dentry;
 		spin_unlock(&dentry->d_lock);
 		break;
 next:
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 89d2fb7b991a..fd9859f92fad 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -14,6 +14,9 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/configfs.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <net/ipv6.h>
 #include <net/sock.h>
 
 #include "config.h"
@@ -377,24 +380,24 @@ static struct config_item_type node_type = {
 	.ct_owner = THIS_MODULE,
 };
 
-static struct dlm_cluster *to_cluster(struct config_item *i)
+static struct dlm_cluster *config_item_to_cluster(struct config_item *i)
 {
 	return i ? container_of(to_config_group(i), struct dlm_cluster, group) :
 		   NULL;
 }
 
-static struct dlm_space *to_space(struct config_item *i)
+static struct dlm_space *config_item_to_space(struct config_item *i)
 {
 	return i ? container_of(to_config_group(i), struct dlm_space, group) :
 		   NULL;
 }
 
-static struct dlm_comm *to_comm(struct config_item *i)
+static struct dlm_comm *config_item_to_comm(struct config_item *i)
 {
 	return i ? container_of(i, struct dlm_comm, item) : NULL;
 }
 
-static struct dlm_node *to_node(struct config_item *i)
+static struct dlm_node *config_item_to_node(struct config_item *i)
 {
 	return i ? container_of(i, struct dlm_node, item) : NULL;
 }
@@ -450,7 +453,7 @@ static struct config_group *make_cluster(struct config_group *g,
 
 static void drop_cluster(struct config_group *g, struct config_item *i)
 {
-	struct dlm_cluster *cl = to_cluster(i);
+	struct dlm_cluster *cl = config_item_to_cluster(i);
 	struct config_item *tmp;
 	int j;
 
@@ -468,7 +471,7 @@ static void drop_cluster(struct config_group *g, struct config_item *i)
 
 static void release_cluster(struct config_item *i)
 {
-	struct dlm_cluster *cl = to_cluster(i);
+	struct dlm_cluster *cl = config_item_to_cluster(i);
 	kfree(cl->group.default_groups);
 	kfree(cl);
 }
@@ -507,7 +510,7 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 
 static void drop_space(struct config_group *g, struct config_item *i)
 {
-	struct dlm_space *sp = to_space(i);
+	struct dlm_space *sp = config_item_to_space(i);
 	struct config_item *tmp;
 	int j;
 
@@ -524,7 +527,7 @@ static void drop_space(struct config_group *g, struct config_item *i)
 
 static void release_space(struct config_item *i)
 {
-	struct dlm_space *sp = to_space(i);
+	struct dlm_space *sp = config_item_to_space(i);
 	kfree(sp->group.default_groups);
 	kfree(sp);
 }
@@ -546,7 +549,7 @@ static struct config_item *make_comm(struct config_group *g, const char *name)
 
 static void drop_comm(struct config_group *g, struct config_item *i)
 {
-	struct dlm_comm *cm = to_comm(i);
+	struct dlm_comm *cm = config_item_to_comm(i);
 	if (local_comm == cm)
 		local_comm = NULL;
 	dlm_lowcomms_close(cm->nodeid);
@@ -557,13 +560,13 @@ static void drop_comm(struct config_group *g, struct config_item *i)
 
 static void release_comm(struct config_item *i)
 {
-	struct dlm_comm *cm = to_comm(i);
+	struct dlm_comm *cm = config_item_to_comm(i);
 	kfree(cm);
 }
 
 static struct config_item *make_node(struct config_group *g, const char *name)
 {
-	struct dlm_space *sp = to_space(g->cg_item.ci_parent);
+	struct dlm_space *sp = config_item_to_space(g->cg_item.ci_parent);
 	struct dlm_node *nd;
 
 	nd = kzalloc(sizeof(struct dlm_node), GFP_KERNEL);
@@ -585,8 +588,8 @@ static struct config_item *make_node(struct config_group *g, const char *name)
 
 static void drop_node(struct config_group *g, struct config_item *i)
 {
-	struct dlm_space *sp = to_space(g->cg_item.ci_parent);
-	struct dlm_node *nd = to_node(i);
+	struct dlm_space *sp = config_item_to_space(g->cg_item.ci_parent);
+	struct dlm_node *nd = config_item_to_node(i);
 
 	mutex_lock(&sp->members_lock);
 	list_del(&nd->list);
@@ -598,7 +601,7 @@ static void drop_node(struct config_group *g, struct config_item *i)
 
 static void release_node(struct config_item *i)
 {
-	struct dlm_node *nd = to_node(i);
+	struct dlm_node *nd = config_item_to_node(i);
 	kfree(nd);
 }
 
@@ -632,7 +635,7 @@ void dlm_config_exit(void)
 static ssize_t show_cluster(struct config_item *i, struct configfs_attribute *a,
 			    char *buf)
 {
-	struct dlm_cluster *cl = to_cluster(i);
+	struct dlm_cluster *cl = config_item_to_cluster(i);
 	struct cluster_attribute *cla =
 			container_of(a, struct cluster_attribute, attr);
 	return cla->show ? cla->show(cl, buf) : 0;
@@ -642,7 +645,7 @@ static ssize_t store_cluster(struct config_item *i,
 			     struct configfs_attribute *a,
 			     const char *buf, size_t len)
 {
-	struct dlm_cluster *cl = to_cluster(i);
+	struct dlm_cluster *cl = config_item_to_cluster(i);
 	struct cluster_attribute *cla =
 		container_of(a, struct cluster_attribute, attr);
 	return cla->store ? cla->store(cl, buf, len) : -EINVAL;
@@ -651,7 +654,7 @@ static ssize_t store_cluster(struct config_item *i,
 static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
 			 char *buf)
 {
-	struct dlm_comm *cm = to_comm(i);
+	struct dlm_comm *cm = config_item_to_comm(i);
 	struct comm_attribute *cma =
 			container_of(a, struct comm_attribute, attr);
 	return cma->show ? cma->show(cm, buf) : 0;
@@ -660,7 +663,7 @@ static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
 static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
 			  const char *buf, size_t len)
 {
-	struct dlm_comm *cm = to_comm(i);
+	struct dlm_comm *cm = config_item_to_comm(i);
 	struct comm_attribute *cma =
 		container_of(a, struct comm_attribute, attr);
 	return cma->store ? cma->store(cm, buf, len) : -EINVAL;
@@ -714,7 +717,7 @@ static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len)
 static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
 			 char *buf)
 {
-	struct dlm_node *nd = to_node(i);
+	struct dlm_node *nd = config_item_to_node(i);
 	struct node_attribute *nda =
 			container_of(a, struct node_attribute, attr);
 	return nda->show ? nda->show(nd, buf) : 0;
@@ -723,7 +726,7 @@ static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
 static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
 			  const char *buf, size_t len)
 {
-	struct dlm_node *nd = to_node(i);
+	struct dlm_node *nd = config_item_to_node(i);
 	struct node_attribute *nda =
 		container_of(a, struct node_attribute, attr);
 	return nda->store ? nda->store(nd, buf, len) : -EINVAL;
@@ -768,7 +771,7 @@ static struct dlm_space *get_space(char *name)
 	i = config_group_find_item(space_list, name);
 	mutex_unlock(&space_list->cg_subsys->su_mutex);
 
-	return to_space(i);
+	return config_item_to_space(i);
 }
 
 static void put_space(struct dlm_space *sp)
@@ -776,6 +779,33 @@ static void put_space(struct dlm_space *sp)
 	config_item_put(&sp->group.cg_item);
 }
 
+static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
+{
+	switch (x->ss_family) {
+	case AF_INET: {
+		struct sockaddr_in *sinx = (struct sockaddr_in *)x;
+		struct sockaddr_in *siny = (struct sockaddr_in *)y;
+		if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
+			return 0;
+		if (sinx->sin_port != siny->sin_port)
+			return 0;
+		break;
+	}
+	case AF_INET6: {
+		struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
+		struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
+		if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
+			return 0;
+		if (sinx->sin6_port != siny->sin6_port)
+			return 0;
+		break;
+	}
+	default:
+		return 0;
+	}
+	return 1;
+}
+
 static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
 {
 	struct config_item *i;
@@ -788,7 +818,7 @@ static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
 	mutex_lock(&clusters_root.subsys.su_mutex);
 
 	list_for_each_entry(i, &comm_list->cg_children, ci_entry) {
-		cm = to_comm(i);
+		cm = config_item_to_comm(i);
 
 		if (nodeid) {
 			if (cm->nodeid != nodeid)
@@ -797,8 +827,7 @@ static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
 			config_item_get(i);
 			break;
 		} else {
-			if (!cm->addr_count ||
-			    memcmp(cm->addr[0], addr, sizeof(*addr)))
+			if (!cm->addr_count || !addr_compare(cm->addr[0], addr))
 				continue;
 			found = 1;
 			config_item_get(i);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 5a7ac33b629c..868e4c9ef127 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -441,8 +441,11 @@ struct dlm_ls {
 	uint32_t		ls_global_id;	/* global unique lockspace ID */
 	uint32_t		ls_exflags;
 	int			ls_lvblen;
-	int			ls_count;	/* reference count */
+	int			ls_count;	/* refcount of processes in
+						   the dlm using this ls */
+	int			ls_create_count; /* create/release refcount */
 	unsigned long		ls_flags;	/* LSFL_ */
+	unsigned long		ls_scan_time;
 	struct kobject		ls_kobj;
 
 	struct dlm_rsbtable	*ls_rsbtbl;
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 499e16759e96..d910501de6d2 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -23,6 +23,7 @@
 #include "lock.h"
 #include "recover.h"
 #include "requestqueue.h"
+#include "user.h"
 
 static int			ls_count;
 static struct mutex		ls_lock;
@@ -211,19 +212,41 @@ void dlm_lockspace_exit(void)
 	kset_unregister(dlm_kset);
 }
 
+static struct dlm_ls *find_ls_to_scan(void)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (time_after_eq(jiffies, ls->ls_scan_time +
+					    dlm_config.ci_scan_secs * HZ)) {
+			spin_unlock(&lslist_lock);
+			return ls;
+		}
+	}
+	spin_unlock(&lslist_lock);
+	return NULL;
+}
+
 static int dlm_scand(void *data)
 {
 	struct dlm_ls *ls;
+	int timeout_jiffies = dlm_config.ci_scan_secs * HZ;
 
 	while (!kthread_should_stop()) {
-		list_for_each_entry(ls, &lslist, ls_list) {
+		ls = find_ls_to_scan();
+		if (ls) {
 			if (dlm_lock_recovery_try(ls)) {
+				ls->ls_scan_time = jiffies;
 				dlm_scan_rsbs(ls);
 				dlm_scan_timeout(ls);
 				dlm_unlock_recovery(ls);
+			} else {
+				ls->ls_scan_time += HZ;
 			}
+		} else {
+			schedule_timeout_interruptible(timeout_jiffies);
 		}
-		schedule_timeout_interruptible(dlm_config.ci_scan_secs * HZ);
 	}
 	return 0;
 }
@@ -246,23 +269,6 @@ static void dlm_scand_stop(void)
 	kthread_stop(scand_task);
 }
 
-static struct dlm_ls *dlm_find_lockspace_name(char *name, int namelen)
-{
-	struct dlm_ls *ls;
-
-	spin_lock(&lslist_lock);
-
-	list_for_each_entry(ls, &lslist, ls_list) {
-		if (ls->ls_namelen == namelen &&
-		    memcmp(ls->ls_name, name, namelen) == 0)
-			goto out;
-	}
-	ls = NULL;
- out:
-	spin_unlock(&lslist_lock);
-	return ls;
-}
-
 struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
 {
 	struct dlm_ls *ls;
@@ -327,6 +333,7 @@ static void remove_lockspace(struct dlm_ls *ls)
 	for (;;) {
 		spin_lock(&lslist_lock);
 		if (ls->ls_count == 0) {
+			WARN_ON(ls->ls_create_count != 0);
 			list_del(&ls->ls_list);
 			spin_unlock(&lslist_lock);
 			return;
@@ -381,7 +388,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 			 uint32_t flags, int lvblen)
 {
 	struct dlm_ls *ls;
-	int i, size, error = -ENOMEM;
+	int i, size, error;
 	int do_unreg = 0;
 
 	if (namelen > DLM_LOCKSPACE_LEN)
@@ -393,12 +400,37 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 	if (!try_module_get(THIS_MODULE))
 		return -EINVAL;
 
-	ls = dlm_find_lockspace_name(name, namelen);
-	if (ls) {
-		*lockspace = ls;
+	if (!dlm_user_daemon_available()) {
+		module_put(THIS_MODULE);
+		return -EUNATCH;
+	}
+
+	error = 0;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		WARN_ON(ls->ls_create_count <= 0);
+		if (ls->ls_namelen != namelen)
+			continue;
+		if (memcmp(ls->ls_name, name, namelen))
+			continue;
+		if (flags & DLM_LSFL_NEWEXCL) {
+			error = -EEXIST;
+			break;
+		}
+		ls->ls_create_count++;
 		module_put(THIS_MODULE);
-		return -EEXIST;
+		error = 1; /* not an error, return 0 */
+		break;
 	}
+	spin_unlock(&lslist_lock);
+
+	if (error < 0)
+		goto out;
+	if (error)
+		goto ret_zero;
+
+	error = -ENOMEM;
 
 	ls = kzalloc(sizeof(struct dlm_ls) + namelen, GFP_KERNEL);
 	if (!ls)
@@ -408,6 +440,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 	ls->ls_lvblen = lvblen;
 	ls->ls_count = 0;
 	ls->ls_flags = 0;
+	ls->ls_scan_time = jiffies;
 
 	if (flags & DLM_LSFL_TIMEWARN)
 		set_bit(LSFL_TIMEWARN, &ls->ls_flags);
@@ -418,8 +451,9 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 		ls->ls_allocation = GFP_KERNEL;
 
 	/* ls_exflags are forced to match among nodes, and we don't
-	   need to require all nodes to have TIMEWARN or FS set */
-	ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS));
+	   need to require all nodes to have some flags set */
+	ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
+				    DLM_LSFL_NEWEXCL));
 
 	size = dlm_config.ci_rsbtbl_size;
 	ls->ls_rsbtbl_size = size;
@@ -510,6 +544,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 	down_write(&ls->ls_in_recovery);
 
 	spin_lock(&lslist_lock);
+	ls->ls_create_count = 1;
 	list_add(&ls->ls_list, &lslist);
 	spin_unlock(&lslist_lock);
 
@@ -548,7 +583,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 	dlm_create_debug_file(ls);
 
 	log_debug(ls, "join complete");
-
+ ret_zero:
 	*lockspace = ls;
 	return 0;
 
@@ -635,13 +670,34 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 	struct dlm_lkb *lkb;
 	struct dlm_rsb *rsb;
 	struct list_head *head;
-	int i;
-	int busy = lockspace_busy(ls);
+	int i, busy, rv;
+
+	busy = lockspace_busy(ls);
+
+	spin_lock(&lslist_lock);
+	if (ls->ls_create_count == 1) {
+		if (busy > force)
+			rv = -EBUSY;
+		else {
+			/* remove_lockspace takes ls off lslist */
+			ls->ls_create_count = 0;
+			rv = 0;
+		}
+	} else if (ls->ls_create_count > 1) {
+		rv = --ls->ls_create_count;
+	} else {
+		rv = -EINVAL;
+	}
+	spin_unlock(&lslist_lock);
 
-	if (busy > force)
-		return -EBUSY;
+	if (rv) {
+		log_debug(ls, "release_lockspace no remove %d", rv);
+		return rv;
+	}
+
+	dlm_device_deregister(ls);
 
-	if (force < 3)
+	if (force < 3 && dlm_user_daemon_available())
 		do_uevent(ls, 0);
 
 	dlm_recoverd_stop(ls);
@@ -720,15 +776,10 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 	dlm_clear_members(ls);
 	dlm_clear_members_gone(ls);
 	kfree(ls->ls_node_array);
+	log_debug(ls, "release_lockspace final free");
 	kobject_put(&ls->ls_kobj);
 	/* The ls structure will be freed when the kobject is done with */
 
-	mutex_lock(&ls_lock);
-	ls_count--;
-	if (!ls_count)
-		threads_stop();
-	mutex_unlock(&ls_lock);
-
 	module_put(THIS_MODULE);
 	return 0;
 }
@@ -750,11 +801,38 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 int dlm_release_lockspace(void *lockspace, int force)
 {
 	struct dlm_ls *ls;
+	int error;
 
 	ls = dlm_find_lockspace_local(lockspace);
 	if (!ls)
 		return -EINVAL;
 	dlm_put_lockspace(ls);
-	return release_lockspace(ls, force);
+
+	mutex_lock(&ls_lock);
+	error = release_lockspace(ls, force);
+	if (!error)
+		ls_count--;
+	else if (!ls_count)
+		threads_stop();
+	mutex_unlock(&ls_lock);
+
+	return error;
+}
+
+void dlm_stop_lockspaces(void)
+{
+	struct dlm_ls *ls;
+
+ restart:
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (!test_bit(LSFL_RUNNING, &ls->ls_flags))
+			continue;
+		spin_unlock(&lslist_lock);
+		log_error(ls, "no userland control daemon, stopping lockspace");
+		dlm_ls_stop(ls);
+		goto restart;
+	}
+	spin_unlock(&lslist_lock);
 }
 
diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h
index 891eabbdd021..f879f87901f8 100644
--- a/fs/dlm/lockspace.h
+++ b/fs/dlm/lockspace.h
@@ -20,6 +20,7 @@ struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
 struct dlm_ls *dlm_find_lockspace_local(void *id);
 struct dlm_ls *dlm_find_lockspace_device(int minor);
 void dlm_put_lockspace(struct dlm_ls *ls);
+void dlm_stop_lockspaces(void);
 
 #endif				/* __LOCKSPACE_DOT_H__ */
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 34f14a14fb4e..b3832c67194a 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006-2007 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006-2008 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -15,7 +15,6 @@
 #include <linux/poll.h>
 #include <linux/signal.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
 #include <linux/dlm.h>
 #include <linux/dlm_device.h>
 
@@ -27,6 +26,8 @@
 
 static const char name_prefix[] = "dlm";
 static const struct file_operations device_fops;
+static atomic_t dlm_monitor_opened;
+static int dlm_monitor_unused = 1;
 
 #ifdef CONFIG_COMPAT
 
@@ -340,10 +341,15 @@ static int device_user_deadlock(struct dlm_user_proc *proc,
 	return error;
 }
 
-static int create_misc_device(struct dlm_ls *ls, char *name)
+static int dlm_device_register(struct dlm_ls *ls, char *name)
 {
 	int error, len;
 
+	/* The device is already registered.  This happens when the
+	   lockspace is created multiple times from userspace. */
+	if (ls->ls_device.name)
+		return 0;
+
 	error = -ENOMEM;
 	len = strlen(name) + strlen(name_prefix) + 2;
 	ls->ls_device.name = kzalloc(len, GFP_KERNEL);
@@ -363,6 +369,22 @@ fail:
 	return error;
 }
 
+int dlm_device_deregister(struct dlm_ls *ls)
+{
+	int error;
+
+	/* The device is not registered.  This happens when the lockspace
+	   was never used from userspace, or when device_create_lockspace()
+	   calls dlm_release_lockspace() after the register fails. */
+	if (!ls->ls_device.name)
+		return 0;
+
+	error = misc_deregister(&ls->ls_device);
+	if (!error)
+		kfree(ls->ls_device.name);
+	return error;
+}
+
 static int device_user_purge(struct dlm_user_proc *proc,
 			     struct dlm_purge_params *params)
 {
@@ -397,7 +419,7 @@ static int device_create_lockspace(struct dlm_lspace_params *params)
 	if (!ls)
 		return -ENOENT;
 
-	error = create_misc_device(ls, params->name);
+	error = dlm_device_register(ls, params->name);
 	dlm_put_lockspace(ls);
 
 	if (error)
@@ -421,31 +443,22 @@ static int device_remove_lockspace(struct dlm_lspace_params *params)
 	if (!ls)
 		return -ENOENT;
 
-	/* Deregister the misc device first, so we don't have
-	 * a device that's not attached to a lockspace. If
-	 * dlm_release_lockspace fails then we can recreate it
-	 */
-	error = misc_deregister(&ls->ls_device);
-	if (error) {
-		dlm_put_lockspace(ls);
-		goto out;
-	}
-	kfree(ls->ls_device.name);
-
 	if (params->flags & DLM_USER_LSFLG_FORCEFREE)
 		force = 2;
 
 	lockspace = ls->ls_local_handle;
+	dlm_put_lockspace(ls);
 
-	/* dlm_release_lockspace waits for references to go to zero,
-	   so all processes will need to close their device for the ls
-	   before the release will procede */
+	/* The final dlm_release_lockspace waits for references to go to
+	   zero, so all processes will need to close their device for the
+	   ls before the release will proceed.  release also calls the
+	   device_deregister above.  Converting a positive return value
+	   from release to zero means that userspace won't know when its
+	   release was the final one, but it shouldn't need to know. */
 
-	dlm_put_lockspace(ls);
 	error = dlm_release_lockspace(lockspace, force);
-	if (error)
-		create_misc_device(ls, ls->ls_name);
- out:
+	if (error > 0)
+		error = 0;
 	return error;
 }
 
@@ -623,17 +636,13 @@ static int device_open(struct inode *inode, struct file *file)
 	struct dlm_user_proc *proc;
 	struct dlm_ls *ls;
 
-	lock_kernel();
 	ls = dlm_find_lockspace_device(iminor(inode));
-	if (!ls) {
-		unlock_kernel();
+	if (!ls)
 		return -ENOENT;
-	}
 
 	proc = kzalloc(sizeof(struct dlm_user_proc), GFP_KERNEL);
 	if (!proc) {
 		dlm_put_lockspace(ls);
-		unlock_kernel();
 		return -ENOMEM;
 	}
 
@@ -645,7 +654,6 @@ static int device_open(struct inode *inode, struct file *file)
 	spin_lock_init(&proc->locks_spin);
 	init_waitqueue_head(&proc->wait);
 	file->private_data = proc;
-	unlock_kernel();
 
 	return 0;
 }
@@ -878,9 +886,28 @@ static unsigned int device_poll(struct file *file, poll_table *wait)
 	return 0;
 }
 
+int dlm_user_daemon_available(void)
+{
+	/* dlm_controld hasn't started (or, has started, but not
+	   properly populated configfs) */
+
+	if (!dlm_our_nodeid())
+		return 0;
+
+	/* This is to deal with versions of dlm_controld that don't
+	   know about the monitor device.  We assume that if the
+	   dlm_controld was started (above), but the monitor device
+	   was never opened, that it's an old version.  dlm_controld
+	   should open the monitor device before populating configfs. */
+
+	if (dlm_monitor_unused)
+		return 1;
+
+	return atomic_read(&dlm_monitor_opened) ? 1 : 0;
+}
+
 static int ctl_device_open(struct inode *inode, struct file *file)
 {
-	cycle_kernel_lock();
 	file->private_data = NULL;
 	return 0;
 }
@@ -890,6 +917,20 @@ static int ctl_device_close(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int monitor_device_open(struct inode *inode, struct file *file)
+{
+	atomic_inc(&dlm_monitor_opened);
+	dlm_monitor_unused = 0;
+	return 0;
+}
+
+static int monitor_device_close(struct inode *inode, struct file *file)
+{
+	if (atomic_dec_and_test(&dlm_monitor_opened))
+		dlm_stop_lockspaces();
+	return 0;
+}
+
 static const struct file_operations device_fops = {
 	.open    = device_open,
 	.release = device_close,
@@ -913,19 +954,42 @@ static struct miscdevice ctl_device = {
 	.minor = MISC_DYNAMIC_MINOR,
 };
 
+static const struct file_operations monitor_device_fops = {
+	.open    = monitor_device_open,
+	.release = monitor_device_close,
+	.owner   = THIS_MODULE,
+};
+
+static struct miscdevice monitor_device = {
+	.name  = "dlm-monitor",
+	.fops  = &monitor_device_fops,
+	.minor = MISC_DYNAMIC_MINOR,
+};
+
 int __init dlm_user_init(void)
 {
 	int error;
 
+	atomic_set(&dlm_monitor_opened, 0);
+
 	error = misc_register(&ctl_device);
-	if (error)
+	if (error) {
 		log_print("misc_register failed for control device");
+		goto out;
+	}
 
+	error = misc_register(&monitor_device);
+	if (error) {
+		log_print("misc_register failed for monitor device");
+		misc_deregister(&ctl_device);
+	}
+ out:
 	return error;
 }
 
 void dlm_user_exit(void)
 {
 	misc_deregister(&ctl_device);
+	misc_deregister(&monitor_device);
 }
 
diff --git a/fs/dlm/user.h b/fs/dlm/user.h
index d38e9f3e4151..35eb6a13d616 100644
--- a/fs/dlm/user.h
+++ b/fs/dlm/user.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006-2008 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -12,5 +12,7 @@
 void dlm_user_add_ast(struct dlm_lkb *lkb, int type);
 int dlm_user_init(void);
 void dlm_user_exit(void);
+int dlm_device_deregister(struct dlm_ls *ls);
+int dlm_user_daemon_available(void);
 
 #endif
diff --git a/fs/exec.c b/fs/exec.c
index 32993beecbe9..cecee501ce78 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -752,11 +752,11 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
 	task_unlock(tsk);
-	mm_update_next_owner(old_mm);
 	arch_pick_mmap_layout(mm);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
 		BUG_ON(active_mm != old_mm);
+		mm_update_next_owner(old_mm);
 		mmput(old_mm);
 		return 0;
 	}
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 302e95c4af7e..fb98b3d847ed 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/msdos_fs.h>
+#include <linux/blkdev.h>
 
 struct fatent_operations {
 	void (*ent_blocknr)(struct super_block *, int, int *, sector_t *);
@@ -535,6 +536,7 @@ int fat_free_clusters(struct inode *inode, int cluster)
 	struct fat_entry fatent;
 	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
 	int i, err, nr_bhs;
+	int first_cl = cluster;
 
 	nr_bhs = 0;
 	fatent_init(&fatent);
@@ -551,6 +553,18 @@ int fat_free_clusters(struct inode *inode, int cluster)
 			goto error;
 		}
 
+		/* 
+		 * Issue discard for the sectors we no longer care about,
+		 * batching contiguous clusters into one request
+		 */
+		if (cluster != fatent.entry + 1) {
+			int nr_clus = fatent.entry - first_cl + 1;
+
+			sb_issue_discard(sb, fat_clus_to_blknr(sbi, first_cl),
+					 nr_clus * sbi->sec_per_clus);
+			first_cl = cluster;
+		}
+
 		ops->ent_put(&fatent, FAT_ENT_FREE);
 		if (sbi->free_clusters != -1) {
 			sbi->free_clusters++;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 13391e546616..c962283d4e7f 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1265,6 +1265,8 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
 	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
 	if (time_before(now, holdtime))
 		delay = holdtime - now;
+	if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
 
 	spin_lock(&gl->gl_spin);
 	handle_callback(gl, state, 1, delay);
@@ -1578,8 +1580,6 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
 		*p++ = 'a';
 	if (flags & GL_EXACT)
 		*p++ = 'E';
-	if (flags & GL_ATIME)
-		*p++ = 'a';
 	if (flags & GL_NOCACHE)
 		*p++ = 'c';
 	if (test_bit(HIF_HOLDER, &iflags))
@@ -1816,15 +1816,17 @@ restart:
 	if (gl) {
 		gi->gl = hlist_entry(gl->gl_list.next,
 				     struct gfs2_glock, gl_list);
-		if (gi->gl)
-			gfs2_glock_hold(gi->gl);
+	} else {
+		gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+				     struct gfs2_glock, gl_list);
 	}
+	if (gi->gl)
+		gfs2_glock_hold(gi->gl);
 	read_unlock(gl_lock_addr(gi->hash));
 	if (gl)
 		gfs2_glock_put(gl);
-	if (gl && gi->gl == NULL)
-		gi->hash++;
 	while (gi->gl == NULL) {
+		gi->hash++;
 		if (gi->hash >= GFS2_GL_HASH_SIZE)
 			return 1;
 		read_lock(gl_lock_addr(gi->hash));
@@ -1833,7 +1835,6 @@ restart:
 		if (gi->gl)
 			gfs2_glock_hold(gi->gl);
 		read_unlock(gl_lock_addr(gi->hash));
-		gi->hash++;
 	}
 
 	if (gi->sdp != gi->gl->gl_sbd)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 971d92af70fc..695c6b193611 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -24,7 +24,6 @@
 #define GL_ASYNC		0x00000040
 #define GL_EXACT		0x00000080
 #define GL_SKIP			0x00000100
-#define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
 
 #define GLR_TRYFAILED		13
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 448697a5c462..f566ec1b4e8e 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -386,20 +386,21 @@ struct gfs2_statfs_change_host {
 #define GFS2_DATA_ORDERED	2
 
 struct gfs2_args {
-	char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */
-	char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */
-	char ar_hostdata[GFS2_LOCKNAME_LEN]; /* Host specific data */
-	int ar_spectator; /* Don't get a journal because we're always RO */
-	int ar_ignore_local_fs; /* Don't optimize even if local_fs is 1 */
-	int ar_localflocks; /* Let the VFS do flock|fcntl locks for us */
-	int ar_localcaching; /* Local-style caching (dangerous on multihost) */
-	int ar_debug; /* Oops on errors instead of trying to be graceful */
-	int ar_upgrade; /* Upgrade ondisk/multihost format */
-	unsigned int ar_num_glockd; /* Number of glockd threads */
-	int ar_posix_acl; /* Enable posix acls */
-	int ar_quota; /* off/account/on */
-	int ar_suiddir; /* suiddir support */
-	int ar_data; /* ordered/writeback */
+	char ar_lockproto[GFS2_LOCKNAME_LEN];	/* Name of the Lock Protocol */
+	char ar_locktable[GFS2_LOCKNAME_LEN];	/* Name of the Lock Table */
+	char ar_hostdata[GFS2_LOCKNAME_LEN];	/* Host specific data */
+	unsigned int ar_spectator:1;		/* Don't get a journal */
+	unsigned int ar_ignore_local_fs:1;	/* Ignore optimisations */
+	unsigned int ar_localflocks:1;		/* Let the VFS do flock|fcntl */
+	unsigned int ar_localcaching:1;		/* Local caching */
+	unsigned int ar_debug:1;		/* Oops on errors */
+	unsigned int ar_upgrade:1;		/* Upgrade ondisk format */
+	unsigned int ar_posix_acl:1;		/* Enable posix acls */
+	unsigned int ar_quota:2;		/* off/account/on */
+	unsigned int ar_suiddir:1;		/* suiddir support */
+	unsigned int ar_data:2;			/* ordered/writeback */
+	unsigned int ar_meta:1;			/* mount metafs */
+	unsigned int ar_num_glockd;		/* Number of glockd threads */
 };
 
 struct gfs2_tune {
@@ -419,7 +420,6 @@ struct gfs2_tune {
 	unsigned int gt_quota_scale_den; /* Denominator */
 	unsigned int gt_quota_cache_secs;
 	unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
-	unsigned int gt_atime_quantum; /* Min secs between atime updates */
 	unsigned int gt_new_files_jdata;
 	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
 	unsigned int gt_stall_secs; /* Detects trouble! */
@@ -432,7 +432,7 @@ enum {
 	SDF_JOURNAL_CHECKED	= 0,
 	SDF_JOURNAL_LIVE	= 1,
 	SDF_SHUTDOWN		= 2,
-	SDF_NOATIME		= 3,
+	SDF_NOBARRIERS		= 3,
 };
 
 #define GFS2_FSNAME_LEN		256
@@ -461,7 +461,6 @@ struct gfs2_sb_host {
 
 struct gfs2_sbd {
 	struct super_block *sd_vfs;
-	struct super_block *sd_vfs_meta;
 	struct kobject sd_kobj;
 	unsigned long sd_flags;	/* SDF_... */
 	struct gfs2_sb_host sd_sb;
@@ -499,7 +498,9 @@ struct gfs2_sbd {
 
 	/* Inode Stuff */
 
-	struct inode *sd_master_dir;
+	struct dentry *sd_master_dir;
+	struct dentry *sd_root_dir;
+
 	struct inode *sd_jindex;
 	struct inode *sd_inum_inode;
 	struct inode *sd_statfs_inode;
@@ -634,7 +635,6 @@ struct gfs2_sbd {
 	/* Debugging crud */
 
 	unsigned long sd_last_warning;
-	struct vfsmount *sd_gfs2mnt;
 	struct dentry *debugfs_dir;    /* debugfs directory */
 	struct dentry *debugfs_dentry_glocks; /* for debugfs */
 };
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8b0806a32948..7cee695fa441 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -18,6 +18,7 @@
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
 #include <linux/security.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -249,6 +250,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 {
 	struct gfs2_dinode_host *di = &ip->i_di;
 	const struct gfs2_dinode *str = buf;
+	struct timespec atime;
 	u16 height, depth;
 
 	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
@@ -275,8 +277,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	di->di_size = be64_to_cpu(str->di_size);
 	i_size_write(&ip->i_inode, di->di_size);
 	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
-	ip->i_inode.i_atime.tv_sec = be64_to_cpu(str->di_atime);
-	ip->i_inode.i_atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	atime.tv_sec = be64_to_cpu(str->di_atime);
+	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+		ip->i_inode.i_atime = atime;
 	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
 	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
 	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
@@ -1033,13 +1037,11 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 
 	if (bh)
 		brelse(bh);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
 	return inode;
 
 fail_gunlock2:
 	gfs2_glock_dq_uninit(ghs + 1);
-	if (inode)
+	if (inode && !IS_ERR(inode))
 		iput(inode);
 fail_gunlock:
 	gfs2_glock_dq(ghs);
@@ -1140,54 +1142,6 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 	return 0;
 }
 
-/*
- * gfs2_ok_to_move - check if it's ok to move a directory to another directory
- * @this: move this
- * @to: to here
- *
- * Follow @to back to the root and make sure we don't encounter @this
- * Assumes we already hold the rename lock.
- *
- * Returns: errno
- */
-
-int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
-{
-	struct inode *dir = &to->i_inode;
-	struct super_block *sb = dir->i_sb;
-	struct inode *tmp;
-	struct qstr dotdot;
-	int error = 0;
-
-	gfs2_str2qstr(&dotdot, "..");
-
-	igrab(dir);
-
-	for (;;) {
-		if (dir == &this->i_inode) {
-			error = -EINVAL;
-			break;
-		}
-		if (dir == sb->s_root->d_inode) {
-			error = 0;
-			break;
-		}
-
-		tmp = gfs2_lookupi(dir, &dotdot, 1);
-		if (IS_ERR(tmp)) {
-			error = PTR_ERR(tmp);
-			break;
-		}
-
-		iput(dir);
-		dir = tmp;
-	}
-
-	iput(dir);
-
-	return error;
-}
-
 /**
  * gfs2_readlinki - return the contents of a symlink
  * @ip: the symlink's inode
@@ -1207,8 +1161,8 @@ int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
 	unsigned int x;
 	int error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
-	error = gfs2_glock_nq_atime(&i_gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+	error = gfs2_glock_nq(&i_gh);
 	if (error) {
 		gfs2_holder_uninit(&i_gh);
 		return error;
@@ -1243,101 +1197,6 @@ out:
 	return error;
 }
 
-/**
- * gfs2_glock_nq_atime - Acquire a hold on an inode's glock, and
- *       conditionally update the inode's atime
- * @gh: the holder to acquire
- *
- * Tests atime (access time) for gfs2_read, gfs2_readdir and gfs2_mmap
- * Update if the difference between the current time and the inode's current
- * atime is greater than an interval specified at mount.
- *
- * Returns: errno
- */
-
-int gfs2_glock_nq_atime(struct gfs2_holder *gh)
-{
-	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
-	struct gfs2_inode *ip = gl->gl_object;
-	s64 quantum = gfs2_tune_get(sdp, gt_atime_quantum);
-	unsigned int state;
-	int flags;
-	int error;
-	struct timespec tv = CURRENT_TIME;
-
-	if (gfs2_assert_warn(sdp, gh->gh_flags & GL_ATIME) ||
-	    gfs2_assert_warn(sdp, !(gh->gh_flags & GL_ASYNC)) ||
-	    gfs2_assert_warn(sdp, gl->gl_ops == &gfs2_inode_glops))
-		return -EINVAL;
-
-	state = gh->gh_state;
-	flags = gh->gh_flags;
-
-	error = gfs2_glock_nq(gh);
-	if (error)
-		return error;
-
-	if (test_bit(SDF_NOATIME, &sdp->sd_flags) ||
-	    (sdp->sd_vfs->s_flags & MS_RDONLY))
-		return 0;
-
-	if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
-		gfs2_glock_dq(gh);
-		gfs2_holder_reinit(LM_ST_EXCLUSIVE, gh->gh_flags & ~LM_FLAG_ANY,
-				   gh);
-		error = gfs2_glock_nq(gh);
-		if (error)
-			return error;
-
-		/* Verify that atime hasn't been updated while we were
-		   trying to get exclusive lock. */
-
-		tv = CURRENT_TIME;
-		if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
-			struct buffer_head *dibh;
-			struct gfs2_dinode *di;
-
-			error = gfs2_trans_begin(sdp, RES_DINODE, 0);
-			if (error == -EROFS)
-				return 0;
-			if (error)
-				goto fail;
-
-			error = gfs2_meta_inode_buffer(ip, &dibh);
-			if (error)
-				goto fail_end_trans;
-
-			ip->i_inode.i_atime = tv;
-
-			gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-			di = (struct gfs2_dinode *)dibh->b_data;
-			di->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
-			di->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
-			brelse(dibh);
-
-			gfs2_trans_end(sdp);
-		}
-
-		/* If someone else has asked for the glock,
-		   unlock and let them have it. Then reacquire
-		   in the original state. */
-		if (gfs2_glock_is_blocking(gl)) {
-			gfs2_glock_dq(gh);
-			gfs2_holder_reinit(state, flags, gh);
-			return gfs2_glock_nq(gh);
-		}
-	}
-
-	return 0;
-
-fail_end_trans:
-	gfs2_trans_end(sdp);
-fail:
-	gfs2_glock_dq(gh);
-	return error;
-}
-
 static int
 __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 {
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 58f9607d6a86..2d43f69610a0 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -91,9 +91,7 @@ int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
 int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 		   const struct gfs2_inode *ip);
 int gfs2_permission(struct inode *inode, int mask);
-int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to);
 int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
-int gfs2_glock_nq_atime(struct gfs2_holder *gh);
 int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
 struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c
index 09d78c216f48..0c4cbe6c8285 100644
--- a/fs/gfs2/locking/dlm/mount.c
+++ b/fs/gfs2/locking/dlm/mount.c
@@ -144,7 +144,8 @@ static int gdlm_mount(char *table_name, char *host_data,
 
 	error = dlm_new_lockspace(ls->fsname, strlen(ls->fsname),
 				  &ls->dlm_lockspace,
-				  DLM_LSFL_FS | (nodir ? DLM_LSFL_NODIR : 0),
+				  DLM_LSFL_FS | DLM_LSFL_NEWEXCL |
+				  (nodir ? DLM_LSFL_NODIR : 0),
 				  GDLM_LVB_SIZE);
 	if (error) {
 		log_error("dlm_new_lockspace error %d", error);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6c6af9f5e3ab..ad305854bdc6 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/bio.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -584,7 +585,6 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	memset(bh->b_data, 0, bh->b_size);
 	set_buffer_uptodate(bh);
 	clear_buffer_dirty(bh);
-	unlock_buffer(bh);
 
 	gfs2_ail1_empty(sdp, 0);
 	tail = current_tail(sdp);
@@ -601,8 +601,23 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
 	lh->lh_hash = cpu_to_be32(hash);
 
-	set_buffer_dirty(bh);
-	if (sync_dirty_buffer(bh))
+	bh->b_end_io = end_buffer_write_sync;
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
+		goto skip_barrier;
+	get_bh(bh);
+	submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh);
+	wait_on_buffer(bh);
+	if (buffer_eopnotsupp(bh)) {
+		clear_buffer_eopnotsupp(bh);
+		set_buffer_uptodate(bh);
+		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
+		lock_buffer(bh);
+skip_barrier:
+		get_bh(bh);
+		submit_bh(WRITE_SYNC | (1 << BIO_RW_META), bh);
+		wait_on_buffer(bh);
+	}
+	if (!buffer_uptodate(bh))
 		gfs2_io_error_bh(sdp, bh);
 	brelse(bh);
 
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index b941f9f9f958..df48333e6f01 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -42,6 +42,7 @@ enum {
 	Opt_nosuiddir,
 	Opt_data_writeback,
 	Opt_data_ordered,
+	Opt_meta,
 	Opt_err,
 };
 
@@ -66,6 +67,7 @@ static match_table_t tokens = {
 	{Opt_nosuiddir, "nosuiddir"},
 	{Opt_data_writeback, "data=writeback"},
 	{Opt_data_ordered, "data=ordered"},
+	{Opt_meta, "meta"},
 	{Opt_err, NULL}
 };
 
@@ -239,6 +241,11 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 		case Opt_data_ordered:
 			args->ar_data = GFS2_DATA_ORDERED;
 			break;
+		case Opt_meta:
+			if (remount && args->ar_meta != 1)
+				goto cant_remount;
+			args->ar_meta = 1;
+			break;
 		case Opt_err:
 		default:
 			fs_info(sdp, "unknown option: %s\n", o);
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index e64a1b04117a..27563816e1c5 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -512,8 +512,8 @@ static int gfs2_readpage(struct file *file, struct page *page)
 	int error;
 
 	unlock_page(page);
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-	error = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
 	if (unlikely(error))
 		goto out;
 	error = AOP_TRUNCATED_PAGE;
@@ -594,8 +594,8 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
 	struct gfs2_holder gh;
 	int ret;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-	ret = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
 	if (unlikely(ret))
 		goto out_uninit;
 	if (!gfs2_is_stuffed(ip))
@@ -636,8 +636,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	unsigned to = from + len;
 	struct page *page;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &ip->i_gh);
-	error = gfs2_glock_nq_atime(&ip->i_gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
 	if (unlikely(error))
 		goto out_uninit;
 
@@ -975,7 +975,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
 	if (gfs2_is_stuffed(ip))
 		return 0;
 
-	if (offset > i_size_read(&ip->i_inode))
+	if (offset >= i_size_read(&ip->i_inode))
 		return 0;
 	return 1;
 }
@@ -1000,8 +1000,8 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	 * unfortunately have the option of only flushing a range like
 	 * the VFS does.
 	 */
-	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, GL_ATIME, &gh);
-	rv = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	rv = gfs2_glock_nq(&gh);
 	if (rv)
 		return rv;
 	rv = gfs2_ok_for_dio(ip, rw, offset);
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index e9a366d4411c..3a747f8e2188 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -89,8 +89,8 @@ static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
 	u64 offset = file->f_pos;
 	int error;
 
-	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
-	error = gfs2_glock_nq_atime(&d_gh);
+	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+	error = gfs2_glock_nq(&d_gh);
 	if (error) {
 		gfs2_holder_uninit(&d_gh);
 		return error;
@@ -153,8 +153,8 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
 	int error;
 	u32 fsflags;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-	error = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
 	if (error)
 		return error;
 
@@ -351,8 +351,8 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 	struct gfs2_alloc *al;
 	int ret;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &gh);
-	ret = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
 	if (ret)
 		goto out;
 
@@ -434,8 +434,8 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 	struct gfs2_holder i_gh;
 	int error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
-	error = gfs2_glock_nq_atime(&i_gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+	error = gfs2_glock_nq(&i_gh);
 	if (error) {
 		gfs2_holder_uninit(&i_gh);
 		return error;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b4d1d6490633..b117fcf2c4f5 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -40,6 +40,44 @@
 #define DO 0
 #define UNDO 1
 
+static const u32 gfs2_old_fs_formats[] = {
+        0
+};
+
+static const u32 gfs2_old_multihost_formats[] = {
+        0
+};
+
+/**
+ * gfs2_tune_init - Fill a gfs2_tune structure with default values
+ * @gt: tune
+ *
+ */
+
+static void gfs2_tune_init(struct gfs2_tune *gt)
+{
+	spin_lock_init(&gt->gt_spin);
+
+	gt->gt_demote_secs = 300;
+	gt->gt_incore_log_blocks = 1024;
+	gt->gt_log_flush_secs = 60;
+	gt->gt_recoverd_secs = 60;
+	gt->gt_logd_secs = 1;
+	gt->gt_quotad_secs = 5;
+	gt->gt_quota_simul_sync = 64;
+	gt->gt_quota_warn_period = 10;
+	gt->gt_quota_scale_num = 1;
+	gt->gt_quota_scale_den = 1;
+	gt->gt_quota_cache_secs = 300;
+	gt->gt_quota_quantum = 60;
+	gt->gt_new_files_jdata = 0;
+	gt->gt_max_readahead = 1 << 18;
+	gt->gt_stall_secs = 600;
+	gt->gt_complain_secs = 10;
+	gt->gt_statfs_quantum = 30;
+	gt->gt_statfs_slow = 0;
+}
+
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp;
@@ -96,21 +134,271 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	return sdp;
 }
 
-static void init_vfs(struct super_block *sb, unsigned noatime)
+
+/**
+ * gfs2_check_sb - Check superblock
+ * @sdp: the filesystem
+ * @sb: The superblock
+ * @silent: Don't print a message if the check fails
+ *
+ * Checks the version code of the FS is one that we understand how to
+ * read and that the sizes of the various on-disk structures have not
+ * changed.
+ */
+
+static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
 {
-	struct gfs2_sbd *sdp = sb->s_fs_info;
+	unsigned int x;
 
-	sb->s_magic = GFS2_MAGIC;
-	sb->s_op = &gfs2_super_ops;
-	sb->s_export_op = &gfs2_export_ops;
-	sb->s_time_gran = 1;
-	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	if (sb->sb_magic != GFS2_MAGIC ||
+	    sb->sb_type != GFS2_METATYPE_SB) {
+		if (!silent)
+			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
+		return -EINVAL;
+	}
+
+	/*  If format numbers match exactly, we're done.  */
+
+	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
+	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
+		return 0;
+
+	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
+		for (x = 0; gfs2_old_fs_formats[x]; x++)
+			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
+				break;
+
+		if (!gfs2_old_fs_formats[x]) {
+			printk(KERN_WARNING
+			       "GFS2: code version (%u, %u) is incompatible "
+			       "with ondisk format (%u, %u)\n",
+			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+			       sb->sb_fs_format, sb->sb_multihost_format);
+			printk(KERN_WARNING
+			       "GFS2: I don't know how to upgrade this FS\n");
+			return -EINVAL;
+		}
+	}
+
+	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
+		for (x = 0; gfs2_old_multihost_formats[x]; x++)
+			if (gfs2_old_multihost_formats[x] ==
+			    sb->sb_multihost_format)
+				break;
+
+		if (!gfs2_old_multihost_formats[x]) {
+			printk(KERN_WARNING
+			       "GFS2: code version (%u, %u) is incompatible "
+			       "with ondisk format (%u, %u)\n",
+			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+			       sb->sb_fs_format, sb->sb_multihost_format);
+			printk(KERN_WARNING
+			       "GFS2: I don't know how to upgrade this FS\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!sdp->sd_args.ar_upgrade) {
+		printk(KERN_WARNING
+		       "GFS2: code version (%u, %u) is incompatible "
+		       "with ondisk format (%u, %u)\n",
+		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+		       sb->sb_fs_format, sb->sb_multihost_format);
+		printk(KERN_INFO
+		       "GFS2: Use the \"upgrade\" mount option to upgrade "
+		       "the FS\n");
+		printk(KERN_INFO "GFS2: See the manual for more details\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void end_bio_io_page(struct bio *bio, int error)
+{
+	struct page *page = bio->bi_private;
 
-	if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
-		set_bit(noatime, &sdp->sd_flags);
+	if (!error)
+		SetPageUptodate(page);
+	else
+		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
+	unlock_page(page);
+}
+
+static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
+{
+	const struct gfs2_sb *str = buf;
+
+	sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
+	sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
+	sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
+	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
+	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
+	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
+	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
+	sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
+	sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
+	sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
+	sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
+
+	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
+	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
+}
+
+/**
+ * gfs2_read_super - Read the gfs2 super block from disk
+ * @sdp: The GFS2 super block
+ * @sector: The location of the super block
+ * @error: The error code to return
+ *
+ * This uses the bio functions to read the super block from disk
+ * because we want to be 100% sure that we never read cached data.
+ * A super block is read twice only during each GFS2 mount and is
+ * never written to by the filesystem. The first time its read no
+ * locks are held, and the only details which are looked at are those
+ * relating to the locking protocol. Once locking is up and working,
+ * the sb is read again under the lock to establish the location of
+ * the master directory (contains pointers to journals etc) and the
+ * root directory.
+ *
+ * Returns: 0 on success or error
+ */
+
+static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_sb *p;
+	struct page *page;
+	struct bio *bio;
+
+	page = alloc_page(GFP_NOFS);
+	if (unlikely(!page))
+		return -ENOBUFS;
+
+	ClearPageUptodate(page);
+	ClearPageDirty(page);
+	lock_page(page);
+
+	bio = bio_alloc(GFP_NOFS, 1);
+	if (unlikely(!bio)) {
+		__free_page(page);
+		return -ENOBUFS;
+	}
 
-	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
-	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
+	bio->bi_sector = sector * (sb->s_blocksize >> 9);
+	bio->bi_bdev = sb->s_bdev;
+	bio_add_page(bio, page, PAGE_SIZE, 0);
+
+	bio->bi_end_io = end_bio_io_page;
+	bio->bi_private = page;
+	submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
+	wait_on_page_locked(page);
+	bio_put(bio);
+	if (!PageUptodate(page)) {
+		__free_page(page);
+		return -EIO;
+	}
+	p = kmap(page);
+	gfs2_sb_in(&sdp->sd_sb, p);
+	kunmap(page);
+	__free_page(page);
+	return 0;
+}
+/**
+ * gfs2_read_sb - Read super block
+ * @sdp: The GFS2 superblock
+ * @gl: the glock for the superblock (assumed to be held)
+ * @silent: Don't print message if mount fails
+ *
+ */
+
+static int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
+{
+	u32 hash_blocks, ind_blocks, leaf_blocks;
+	u32 tmp_blocks;
+	unsigned int x;
+	int error;
+
+	error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+	if (error) {
+		if (!silent)
+			fs_err(sdp, "can't read superblock\n");
+		return error;
+	}
+
+	error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
+	if (error)
+		return error;
+
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+			       GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_dinode)) / sizeof(u64);
+	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
+	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
+	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
+	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
+	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_meta_header)) /
+			        sizeof(struct gfs2_quota_change);
+
+	/* Compute maximum reservation required to add a entry to a directory */
+
+	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
+			     sdp->sd_jbsize);
+
+	ind_blocks = 0;
+	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
+		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
+		ind_blocks += tmp_blocks;
+	}
+
+	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
+
+	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
+
+	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_dinode);
+	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_heightsize[x - 1] || m)
+			break;
+		sdp->sd_heightsize[x] = space;
+	}
+	sdp->sd_max_height = x;
+	sdp->sd_heightsize[x] = ~0;
+	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
+
+	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
+				 sizeof(struct gfs2_dinode);
+	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_jheightsize[x - 1] || m)
+			break;
+		sdp->sd_jheightsize[x] = space;
+	}
+	sdp->sd_max_jheight = x;
+	sdp->sd_jheightsize[x] = ~0;
+	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
+
+	return 0;
 }
 
 static int init_names(struct gfs2_sbd *sdp, int silent)
@@ -224,51 +512,59 @@ fail:
 	return error;
 }
 
-static inline struct inode *gfs2_lookup_root(struct super_block *sb,
-					     u64 no_addr)
+static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
+			    u64 no_addr, const char *name)
 {
-	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct dentry *dentry;
+	struct inode *inode;
+
+	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+	if (IS_ERR(inode)) {
+		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
+		return PTR_ERR(inode);
+	}
+	dentry = d_alloc_root(inode);
+	if (!dentry) {
+		fs_err(sdp, "can't alloc %s dentry\n", name);
+		iput(inode);
+		return -ENOMEM;
+	}
+	dentry->d_op = &gfs2_dops;
+	*dptr = dentry;
+	return 0;
 }
 
-static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
+static int init_sb(struct gfs2_sbd *sdp, int silent)
 {
 	struct super_block *sb = sdp->sd_vfs;
 	struct gfs2_holder sb_gh;
 	u64 no_addr;
-	struct inode *inode;
-	int error = 0;
+	int ret;
 
-	if (undo) {
-		if (sb->s_root) {
-			dput(sb->s_root);
-			sb->s_root = NULL;
-		}
-		return 0;
+	ret = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
+				LM_ST_SHARED, 0, &sb_gh);
+	if (ret) {
+		fs_err(sdp, "can't acquire superblock glock: %d\n", ret);
+		return ret;
 	}
 
-	error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
-				 LM_ST_SHARED, 0, &sb_gh);
-	if (error) {
-		fs_err(sdp, "can't acquire superblock glock: %d\n", error);
-		return error;
-	}
-
-	error = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
-	if (error) {
-		fs_err(sdp, "can't read superblock: %d\n", error);
+	ret = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
+	if (ret) {
+		fs_err(sdp, "can't read superblock: %d\n", ret);
 		goto out;
 	}
 
 	/* Set up the buffer cache and SB for real */
 	if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
-		error = -EINVAL;
+		ret = -EINVAL;
 		fs_err(sdp, "FS block size (%u) is too small for device "
 		       "block size (%u)\n",
 		       sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
 		goto out;
 	}
 	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
-		error = -EINVAL;
+		ret = -EINVAL;
 		fs_err(sdp, "FS block size (%u) is too big for machine "
 		       "page size (%u)\n",
 		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
@@ -278,26 +574,21 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
 
 	/* Get the root inode */
 	no_addr = sdp->sd_sb.sb_root_dir.no_addr;
-	if (sb->s_type == &gfs2meta_fs_type)
-		no_addr = sdp->sd_sb.sb_master_dir.no_addr;
-	inode = gfs2_lookup_root(sb, no_addr);
-	if (IS_ERR(inode)) {
-		error = PTR_ERR(inode);
-		fs_err(sdp, "can't read in root inode: %d\n", error);
+	ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
+	if (ret)
 		goto out;
-	}
 
-	sb->s_root = d_alloc_root(inode);
-	if (!sb->s_root) {
-		fs_err(sdp, "can't get root dentry\n");
-		error = -ENOMEM;
-		iput(inode);
-	} else
-		sb->s_root->d_op = &gfs2_dops;
-	
+	/* Get the master inode */
+	no_addr = sdp->sd_sb.sb_master_dir.no_addr;
+	ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
+	if (ret) {
+		dput(sdp->sd_root_dir);
+		goto out;
+	}
+	sb->s_root = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
 out:
 	gfs2_glock_dq_uninit(&sb_gh);
-	return error;
+	return ret;
 }
 
 /**
@@ -372,6 +663,7 @@ static void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
 
 static int init_journal(struct gfs2_sbd *sdp, int undo)
 {
+	struct inode *master = sdp->sd_master_dir->d_inode;
 	struct gfs2_holder ji_gh;
 	struct task_struct *p;
 	struct gfs2_inode *ip;
@@ -383,7 +675,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		goto fail_recoverd;
 	}
 
-	sdp->sd_jindex = gfs2_lookup_simple(sdp->sd_master_dir, "jindex");
+	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
 	if (IS_ERR(sdp->sd_jindex)) {
 		fs_err(sdp, "can't lookup journal index: %d\n", error);
 		return PTR_ERR(sdp->sd_jindex);
@@ -506,25 +798,17 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 {
 	int error = 0;
 	struct gfs2_inode *ip;
-	struct inode *inode;
+	struct inode *master = sdp->sd_master_dir->d_inode;
 
 	if (undo)
 		goto fail_qinode;
 
-	inode = gfs2_lookup_root(sdp->sd_vfs, sdp->sd_sb.sb_master_dir.no_addr);
-	if (IS_ERR(inode)) {
-		error = PTR_ERR(inode);
-		fs_err(sdp, "can't read in master directory: %d\n", error);
-		goto fail;
-	}
-	sdp->sd_master_dir = inode;
-
 	error = init_journal(sdp, undo);
 	if (error)
-		goto fail_master;
+		goto fail;
 
 	/* Read in the master inode number inode */
-	sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
+	sdp->sd_inum_inode = gfs2_lookup_simple(master, "inum");
 	if (IS_ERR(sdp->sd_inum_inode)) {
 		error = PTR_ERR(sdp->sd_inum_inode);
 		fs_err(sdp, "can't read in inum inode: %d\n", error);
@@ -533,7 +817,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 
 
 	/* Read in the master statfs inode */
-	sdp->sd_statfs_inode = gfs2_lookup_simple(sdp->sd_master_dir, "statfs");
+	sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
 	if (IS_ERR(sdp->sd_statfs_inode)) {
 		error = PTR_ERR(sdp->sd_statfs_inode);
 		fs_err(sdp, "can't read in statfs inode: %d\n", error);
@@ -541,7 +825,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 	}
 
 	/* Read in the resource index inode */
-	sdp->sd_rindex = gfs2_lookup_simple(sdp->sd_master_dir, "rindex");
+	sdp->sd_rindex = gfs2_lookup_simple(master, "rindex");
 	if (IS_ERR(sdp->sd_rindex)) {
 		error = PTR_ERR(sdp->sd_rindex);
 		fs_err(sdp, "can't get resource index inode: %d\n", error);
@@ -552,7 +836,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 	sdp->sd_rindex_uptodate = 0;
 
 	/* Read in the quota inode */
-	sdp->sd_quota_inode = gfs2_lookup_simple(sdp->sd_master_dir, "quota");
+	sdp->sd_quota_inode = gfs2_lookup_simple(master, "quota");
 	if (IS_ERR(sdp->sd_quota_inode)) {
 		error = PTR_ERR(sdp->sd_quota_inode);
 		fs_err(sdp, "can't get quota file inode: %d\n", error);
@@ -571,8 +855,6 @@ fail_inum:
 	iput(sdp->sd_inum_inode);
 fail_journal:
 	init_journal(sdp, UNDO);
-fail_master:
-	iput(sdp->sd_master_dir);
 fail:
 	return error;
 }
@@ -583,6 +865,7 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
 	char buf[30];
 	int error = 0;
 	struct gfs2_inode *ip;
+	struct inode *master = sdp->sd_master_dir->d_inode;
 
 	if (sdp->sd_args.ar_spectator)
 		return 0;
@@ -590,7 +873,7 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
 	if (undo)
 		goto fail_qc_gh;
 
-	pn = gfs2_lookup_simple(sdp->sd_master_dir, "per_node");
+	pn = gfs2_lookup_simple(master, "per_node");
 	if (IS_ERR(pn)) {
 		error = PTR_ERR(pn);
 		fs_err(sdp, "can't find per_node directory: %d\n", error);
@@ -800,7 +1083,11 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 		goto fail;
 	}
 
-	init_vfs(sb, SDF_NOATIME);
+	sb->s_magic = GFS2_MAGIC;
+	sb->s_op = &gfs2_super_ops;
+	sb->s_export_op = &gfs2_export_ops;
+	sb->s_time_gran = 1;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
 
 	/* Set up the buffer cache and fill in some fake block size values
 	   to allow us to read-in the on-disk superblock. */
@@ -828,7 +1115,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 	if (error)
 		goto fail_lm;
 
-	error = init_sb(sdp, silent, DO);
+	error = init_sb(sdp, silent);
 	if (error)
 		goto fail_locking;
 
@@ -869,7 +1156,11 @@ fail_per_node:
 fail_inodes:
 	init_inodes(sdp, UNDO);
 fail_sb:
-	init_sb(sdp, 0, UNDO);
+	if (sdp->sd_root_dir)
+		dput(sdp->sd_root_dir);
+	if (sdp->sd_master_dir)
+		dput(sdp->sd_master_dir);
+	sb->s_root = NULL;
 fail_locking:
 	init_locking(sdp, &mount_gh, UNDO);
 fail_lm:
@@ -887,151 +1178,63 @@ fail:
 }
 
 static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data, struct vfsmount *mnt)
+		       const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	struct super_block *sb;
-	struct gfs2_sbd *sdp;
-	int error = get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
-	if (error)
-		goto out;
-	sb = mnt->mnt_sb;
-	sdp = sb->s_fs_info;
-	sdp->sd_gfs2mnt = mnt;
-out:
-	return error;
+	return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
 }
 
-static int fill_super_meta(struct super_block *sb, struct super_block *new,
-			   void *data, int silent)
+static struct super_block *get_gfs2_sb(const char *dev_name)
 {
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct inode *inode;
-	int error = 0;
-
-	new->s_fs_info = sdp;
-	sdp->sd_vfs_meta = sb;
-
-	init_vfs(new, SDF_NOATIME);
-
-        /* Get the master inode */
-	inode = igrab(sdp->sd_master_dir);
-
-	new->s_root = d_alloc_root(inode);
-	if (!new->s_root) {
-		fs_err(sdp, "can't get root dentry\n");
-		error = -ENOMEM;
-		iput(inode);
-	} else
-		new->s_root->d_op = &gfs2_dops;
-
-	return error;
-}
-
-static int set_bdev_super(struct super_block *s, void *data)
-{
-	s->s_bdev = data;
-	s->s_dev = s->s_bdev->bd_dev;
-	return 0;
-}
-
-static int test_bdev_super(struct super_block *s, void *data)
-{
-	return s->s_bdev == data;
-}
-
-static struct super_block* get_gfs2_sb(const char *dev_name)
-{
-	struct kstat stat;
+	struct super_block *sb;
 	struct nameidata nd;
-	struct super_block *sb = NULL, *s;
 	int error;
 
 	error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
 	if (error) {
-		printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
-		       dev_name);
-		goto out;
-	}
-	error = vfs_getattr(nd.path.mnt, nd.path.dentry, &stat);
-
-	list_for_each_entry(s, &gfs2_fs_type.fs_supers, s_instances) {
-		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
-		    (S_ISDIR(stat.mode) &&
-		     s == nd.path.dentry->d_inode->i_sb)) {
-			sb = s;
-			goto free_nd;
-		}
+		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
+		       dev_name, error);
+		return NULL;
 	}
-
-	printk(KERN_WARNING "GFS2: Unrecognized block device or "
-	       "mount point %s\n", dev_name);
-
-free_nd:
+	sb = nd.path.dentry->d_inode->i_sb;
+	if (sb && (sb->s_type == &gfs2_fs_type))
+		atomic_inc(&sb->s_active);
+	else
+		sb = NULL;
 	path_put(&nd.path);
-out:
 	return sb;
 }
 
 static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 			    const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	int error = 0;
-	struct super_block *sb = NULL, *new;
+	struct super_block *sb = NULL;
 	struct gfs2_sbd *sdp;
 
 	sb = get_gfs2_sb(dev_name);
 	if (!sb) {
 		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
-		error = -ENOENT;
-		goto error;
+		return -ENOENT;
 	}
 	sdp = sb->s_fs_info;
-	if (sdp->sd_vfs_meta) {
-		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
-		error = -EBUSY;
-		goto error;
-	}
-	down(&sb->s_bdev->bd_mount_sem);
-	new = sget(fs_type, test_bdev_super, set_bdev_super, sb->s_bdev);
-	up(&sb->s_bdev->bd_mount_sem);
-	if (IS_ERR(new)) {
-		error = PTR_ERR(new);
-		goto error;
-	}
-	new->s_flags = flags;
-	strlcpy(new->s_id, sb->s_id, sizeof(new->s_id));
-	sb_set_blocksize(new, sb->s_blocksize);
-	error = fill_super_meta(sb, new, data, flags & MS_SILENT ? 1 : 0);
-	if (error) {
-		up_write(&new->s_umount);
-		deactivate_super(new);
-		goto error;
-	}
-
-	new->s_flags |= MS_ACTIVE;
-
-	/* Grab a reference to the gfs2 mount point */
-	atomic_inc(&sdp->sd_gfs2mnt->mnt_count);
-	return simple_set_mnt(mnt, new);
-error:
-	return error;
+	mnt->mnt_sb = sb;
+	mnt->mnt_root = dget(sdp->sd_master_dir);
+	return 0;
 }
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-	if (sb->s_fs_info) {
-		gfs2_delete_debugfs_file(sb->s_fs_info);
-		gfs2_meta_syncfs(sb->s_fs_info);
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	if (sdp) {
+		gfs2_meta_syncfs(sdp);
+		dput(sdp->sd_root_dir);
+		dput(sdp->sd_master_dir);
+		sdp->sd_root_dir = NULL;
+		sdp->sd_master_dir = NULL;
 	}
+	shrink_dcache_sb(sb);
 	kill_block_super(sb);
-}
-
-static void gfs2_kill_sb_meta(struct super_block *sb)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	generic_shutdown_super(sb);
-	sdp->sd_vfs_meta = NULL;
-	atomic_dec(&sdp->sd_gfs2mnt->mnt_count);
+	if (sdp)
+		gfs2_delete_debugfs_file(sdp);
 }
 
 struct file_system_type gfs2_fs_type = {
@@ -1046,7 +1249,6 @@ struct file_system_type gfs2meta_fs_type = {
 	.name = "gfs2meta",
 	.fs_flags = FS_REQUIRES_DEV,
 	.get_sb = gfs2_get_sb_meta,
-	.kill_sb = gfs2_kill_sb_meta,
 	.owner = THIS_MODULE,
 };
 
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index e2c62f73a778..534e1e2c65ca 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -159,9 +159,13 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
 
-	error = gfs2_glock_nq_m(2, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
 
 	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
 	if (error)
@@ -245,8 +249,10 @@ out_alloc:
 	if (alloc_required)
 		gfs2_alloc_put(dip);
 out_gunlock:
-	gfs2_glock_dq_m(2, ghs);
-out:
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_glock_dq(ghs);
+out_parent:
 	gfs2_holder_uninit(ghs);
 	gfs2_holder_uninit(ghs + 1);
 	if (!error) {
@@ -302,7 +308,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
-		goto out_rgrp;
+		goto out_gunlock;
 
 	error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
 	if (error)
@@ -316,6 +322,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 out_end_trans:
 	gfs2_trans_end(sdp);
+out_gunlock:
 	gfs2_glock_dq(ghs + 2);
 out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
@@ -485,7 +492,6 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
 	struct gfs2_holder ri_gh;
 	int error;
 
-
 	error = gfs2_rindex_hold(sdp, &ri_gh);
 	if (error)
 		return error;
@@ -495,9 +501,17 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
 	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
 	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
 
-	error = gfs2_glock_nq_m(3, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = gfs2_glock_nq(ghs + 2); /* rgrp */
+	if (error)
+		goto out_rgrp;
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
@@ -523,11 +537,15 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
 	gfs2_trans_end(sdp);
 
 out_gunlock:
-	gfs2_glock_dq_m(3, ghs);
-out:
-	gfs2_holder_uninit(ghs);
-	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs + 2);
+out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
 	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
@@ -571,6 +589,54 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
 	return 0;
 }
 
+/*
+ * gfs2_ok_to_move - check if it's ok to move a directory to another directory
+ * @this: move this
+ * @to: to here
+ *
+ * Follow @to back to the root and make sure we don't encounter @this
+ * Assumes we already hold the rename lock.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
+{
+	struct inode *dir = &to->i_inode;
+	struct super_block *sb = dir->i_sb;
+	struct inode *tmp;
+	struct qstr dotdot;
+	int error = 0;
+
+	gfs2_str2qstr(&dotdot, "..");
+
+	igrab(dir);
+
+	for (;;) {
+		if (dir == &this->i_inode) {
+			error = -EINVAL;
+			break;
+		}
+		if (dir == sb->s_root->d_inode) {
+			error = 0;
+			break;
+		}
+
+		tmp = gfs2_lookupi(dir, &dotdot, 1);
+		if (IS_ERR(tmp)) {
+			error = PTR_ERR(tmp);
+			break;
+		}
+
+		iput(dir);
+		dir = tmp;
+	}
+
+	iput(dir);
+
+	return error;
+}
+
 /**
  * gfs2_rename - Rename a file
  * @odir: Parent directory of old file name
@@ -589,7 +655,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
 	struct gfs2_inode *nip = NULL;
 	struct gfs2_sbd *sdp = GFS2_SB(odir);
-	struct gfs2_holder ghs[5], r_gh;
+	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
@@ -603,19 +669,20 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			return 0;
 	}
 
-	/* Make sure we aren't trying to move a dirctory into it's subdir */
-
-	if (S_ISDIR(ip->i_inode.i_mode) && odip != ndip) {
-		dir_rename = 1;
 
-		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE, 0,
-					   &r_gh);
+	if (odip != ndip) {
+		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
+					   0, &r_gh);
 		if (error)
 			goto out;
 
-		error = gfs2_ok_to_move(ip, ndip);
-		if (error)
-			goto out_gunlock_r;
+		if (S_ISDIR(ip->i_inode.i_mode)) {
+			dir_rename = 1;
+			/* don't move a dirctory into it's subdir */
+			error = gfs2_ok_to_move(ip, ndip);
+			if (error)
+				goto out_gunlock_r;
+		}
 	}
 
 	num_gh = 1;
@@ -639,9 +706,11 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
 	}
 
-	error = gfs2_glock_nq_m(num_gh, ghs);
-	if (error)
-		goto out_uninit;
+	for (x = 0; x < num_gh; x++) {
+		error = gfs2_glock_nq(ghs + x);
+		if (error)
+			goto out_gunlock;
+	}
 
 	/* Check out the old directory */
 
@@ -804,12 +873,12 @@ out_alloc:
 	if (alloc_required)
 		gfs2_alloc_put(ndip);
 out_gunlock:
-	gfs2_glock_dq_m(num_gh, ghs);
-out_uninit:
-	for (x = 0; x < num_gh; x++)
+	while (x--) {
+		gfs2_glock_dq(ghs + x);
 		gfs2_holder_uninit(ghs + x);
+	}
 out_gunlock_r:
-	if (dir_rename)
+	if (r_gh.gh_gl)
 		gfs2_glock_dq_uninit(&r_gh);
 out:
 	return error;
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index f66ea0f7a356..d5355d9b5926 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -20,6 +20,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -38,6 +39,7 @@
 #include "dir.h"
 #include "eattr.h"
 #include "bmap.h"
+#include "meta_io.h"
 
 /**
  * gfs2_write_inode - Make sure the inode is stable on the disk
@@ -50,16 +52,74 @@
 static int gfs2_write_inode(struct inode *inode, int sync)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-
-	/* Check this is a "normal" inode */
-	if (test_bit(GIF_USER, &ip->i_flags)) {
-		if (current->flags & PF_MEMALLOC)
-			return 0;
-		if (sync)
-			gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	struct buffer_head *bh;
+	struct timespec atime;
+	struct gfs2_dinode *di;
+	int ret = 0;
+
+	/* Check this is a "normal" inode, etc */
+	if (!test_bit(GIF_USER, &ip->i_flags) ||
+	    (current->flags & PF_MEMALLOC))
+		return 0;
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (ret)
+		goto do_flush;
+	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (ret)
+		goto do_unlock;
+	ret = gfs2_meta_inode_buffer(ip, &bh);
+	if (ret == 0) {
+		di = (struct gfs2_dinode *)bh->b_data;
+		atime.tv_sec = be64_to_cpu(di->di_atime);
+		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
+		if (timespec_compare(&inode->i_atime, &atime) > 0) {
+			gfs2_trans_add_bh(ip->i_gl, bh, 1);
+			gfs2_dinode_out(ip, bh->b_data);
+		}
+		brelse(bh);
 	}
+	gfs2_trans_end(sdp);
+do_unlock:
+	gfs2_glock_dq_uninit(&gh);
+do_flush:
+	if (sync != 0)
+		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	return ret;
+}
 
-	return 0;
+/**
+ * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+{
+	struct gfs2_holder t_gh;
+	int error;
+
+	gfs2_quota_sync(sdp);
+	gfs2_statfs_sync(sdp);
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
+				   &t_gh);
+	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return error;
+
+	gfs2_meta_syncfs(sdp);
+	gfs2_log_shutdown(sdp);
+
+	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	if (t_gh.gh_gl)
+		gfs2_glock_dq_uninit(&t_gh);
+
+	gfs2_quota_cleanup(sdp);
+
+	return error;
 }
 
 /**
@@ -73,12 +133,6 @@ static void gfs2_put_super(struct super_block *sb)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	int error;
 
-	if (!sdp)
-		return;
-
-	if (!strncmp(sb->s_type->name, "gfs2meta", 8))
-		return; /* Nothing to do */
-
 	/*  Unfreeze the filesystem, if we need to  */
 
 	mutex_lock(&sdp->sd_freeze_lock);
@@ -101,7 +155,6 @@ static void gfs2_put_super(struct super_block *sb)
 
 	/*  Release stuff  */
 
-	iput(sdp->sd_master_dir);
 	iput(sdp->sd_jindex);
 	iput(sdp->sd_inum_inode);
 	iput(sdp->sd_statfs_inode);
@@ -152,6 +205,7 @@ static void gfs2_write_super(struct super_block *sb)
  *
  * Flushes the log to disk.
  */
+
 static int gfs2_sync_fs(struct super_block *sb, int wait)
 {
 	sb->s_dirt = 0;
@@ -270,14 +324,6 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
-	if (*flags & (MS_NOATIME | MS_NODIRATIME))
-		set_bit(SDF_NOATIME, &sdp->sd_flags);
-	else
-		clear_bit(SDF_NOATIME, &sdp->sd_flags);
-
-	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
-	*flags |= MS_NOATIME | MS_NODIRATIME;
-
 	return error;
 }
 
@@ -295,6 +341,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
  * inode's blocks, or alternatively pass the baton on to another
  * node for later deallocation.
  */
+
 static void gfs2_drop_inode(struct inode *inode)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
@@ -333,6 +380,16 @@ static void gfs2_clear_inode(struct inode *inode)
 	}
 }
 
+static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
+{
+	do {
+		if (d1 == d2)
+			return 1;
+		d1 = d1->d_parent;
+	} while (!IS_ROOT(d1));
+	return 0;
+}
+
 /**
  * gfs2_show_options - Show mount options for /proc/mounts
  * @s: seq_file structure
@@ -346,6 +403,8 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
 	struct gfs2_args *args = &sdp->sd_args;
 
+	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
+		seq_printf(s, ",meta");
 	if (args->ar_lockproto[0])
 		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
 	if (args->ar_locktable[0])
@@ -414,6 +473,7 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
  * conversion on the iopen lock, but we can change that later. This
  * is safe, just less efficient.
  */
+
 static void gfs2_delete_inode(struct inode *inode)
 {
 	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
@@ -478,8 +538,6 @@ out:
 	clear_inode(inode);
 }
 
-
-
 static struct inode *gfs2_alloc_inode(struct super_block *sb)
 {
 	struct gfs2_inode *ip;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index ca831991cbc2..c3ba3d9d0aac 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -33,313 +33,6 @@
 #include "trans.h"
 #include "util.h"
 
-static const u32 gfs2_old_fs_formats[] = {
-        0
-};
-
-static const u32 gfs2_old_multihost_formats[] = {
-        0
-};
-
-/**
- * gfs2_tune_init - Fill a gfs2_tune structure with default values
- * @gt: tune
- *
- */
-
-void gfs2_tune_init(struct gfs2_tune *gt)
-{
-	spin_lock_init(&gt->gt_spin);
-
-	gt->gt_demote_secs = 300;
-	gt->gt_incore_log_blocks = 1024;
-	gt->gt_log_flush_secs = 60;
-	gt->gt_recoverd_secs = 60;
-	gt->gt_logd_secs = 1;
-	gt->gt_quotad_secs = 5;
-	gt->gt_quota_simul_sync = 64;
-	gt->gt_quota_warn_period = 10;
-	gt->gt_quota_scale_num = 1;
-	gt->gt_quota_scale_den = 1;
-	gt->gt_quota_cache_secs = 300;
-	gt->gt_quota_quantum = 60;
-	gt->gt_atime_quantum = 3600;
-	gt->gt_new_files_jdata = 0;
-	gt->gt_max_readahead = 1 << 18;
-	gt->gt_stall_secs = 600;
-	gt->gt_complain_secs = 10;
-	gt->gt_statfs_quantum = 30;
-	gt->gt_statfs_slow = 0;
-}
-
-/**
- * gfs2_check_sb - Check superblock
- * @sdp: the filesystem
- * @sb: The superblock
- * @silent: Don't print a message if the check fails
- *
- * Checks the version code of the FS is one that we understand how to
- * read and that the sizes of the various on-disk structures have not
- * changed.
- */
-
-int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
-{
-	unsigned int x;
-
-	if (sb->sb_magic != GFS2_MAGIC ||
-	    sb->sb_type != GFS2_METATYPE_SB) {
-		if (!silent)
-			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
-		return -EINVAL;
-	}
-
-	/*  If format numbers match exactly, we're done.  */
-
-	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
-	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
-		return 0;
-
-	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
-		for (x = 0; gfs2_old_fs_formats[x]; x++)
-			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
-				break;
-
-		if (!gfs2_old_fs_formats[x]) {
-			printk(KERN_WARNING
-			       "GFS2: code version (%u, %u) is incompatible "
-			       "with ondisk format (%u, %u)\n",
-			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-			       sb->sb_fs_format, sb->sb_multihost_format);
-			printk(KERN_WARNING
-			       "GFS2: I don't know how to upgrade this FS\n");
-			return -EINVAL;
-		}
-	}
-
-	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
-		for (x = 0; gfs2_old_multihost_formats[x]; x++)
-			if (gfs2_old_multihost_formats[x] ==
-			    sb->sb_multihost_format)
-				break;
-
-		if (!gfs2_old_multihost_formats[x]) {
-			printk(KERN_WARNING
-			       "GFS2: code version (%u, %u) is incompatible "
-			       "with ondisk format (%u, %u)\n",
-			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-			       sb->sb_fs_format, sb->sb_multihost_format);
-			printk(KERN_WARNING
-			       "GFS2: I don't know how to upgrade this FS\n");
-			return -EINVAL;
-		}
-	}
-
-	if (!sdp->sd_args.ar_upgrade) {
-		printk(KERN_WARNING
-		       "GFS2: code version (%u, %u) is incompatible "
-		       "with ondisk format (%u, %u)\n",
-		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-		       sb->sb_fs_format, sb->sb_multihost_format);
-		printk(KERN_INFO
-		       "GFS2: Use the \"upgrade\" mount option to upgrade "
-		       "the FS\n");
-		printk(KERN_INFO "GFS2: See the manual for more details\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-
-static void end_bio_io_page(struct bio *bio, int error)
-{
-	struct page *page = bio->bi_private;
-
-	if (!error)
-		SetPageUptodate(page);
-	else
-		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
-	unlock_page(page);
-}
-
-static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
-{
-	const struct gfs2_sb *str = buf;
-
-	sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
-	sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
-	sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
-	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
-	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
-	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
-	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
-	sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
-	sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
-	sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
-	sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
-
-	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
-	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
-}
-
-/**
- * gfs2_read_super - Read the gfs2 super block from disk
- * @sdp: The GFS2 super block
- * @sector: The location of the super block
- * @error: The error code to return
- *
- * This uses the bio functions to read the super block from disk
- * because we want to be 100% sure that we never read cached data.
- * A super block is read twice only during each GFS2 mount and is
- * never written to by the filesystem. The first time its read no
- * locks are held, and the only details which are looked at are those
- * relating to the locking protocol. Once locking is up and working,
- * the sb is read again under the lock to establish the location of
- * the master directory (contains pointers to journals etc) and the
- * root directory.
- *
- * Returns: 0 on success or error
- */
-
-int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
-{
-	struct super_block *sb = sdp->sd_vfs;
-	struct gfs2_sb *p;
-	struct page *page;
-	struct bio *bio;
-
-	page = alloc_page(GFP_NOFS);
-	if (unlikely(!page))
-		return -ENOBUFS;
-
-	ClearPageUptodate(page);
-	ClearPageDirty(page);
-	lock_page(page);
-
-	bio = bio_alloc(GFP_NOFS, 1);
-	if (unlikely(!bio)) {
-		__free_page(page);
-		return -ENOBUFS;
-	}
-
-	bio->bi_sector = sector * (sb->s_blocksize >> 9);
-	bio->bi_bdev = sb->s_bdev;
-	bio_add_page(bio, page, PAGE_SIZE, 0);
-
-	bio->bi_end_io = end_bio_io_page;
-	bio->bi_private = page;
-	submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
-	wait_on_page_locked(page);
-	bio_put(bio);
-	if (!PageUptodate(page)) {
-		__free_page(page);
-		return -EIO;
-	}
-	p = kmap(page);
-	gfs2_sb_in(&sdp->sd_sb, p);
-	kunmap(page);
-	__free_page(page);
-	return 0;
-}
-
-/**
- * gfs2_read_sb - Read super block
- * @sdp: The GFS2 superblock
- * @gl: the glock for the superblock (assumed to be held)
- * @silent: Don't print message if mount fails
- *
- */
-
-int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
-{
-	u32 hash_blocks, ind_blocks, leaf_blocks;
-	u32 tmp_blocks;
-	unsigned int x;
-	int error;
-
-	error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
-	if (error) {
-		if (!silent)
-			fs_err(sdp, "can't read superblock\n");
-		return error;
-	}
-
-	error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
-	if (error)
-		return error;
-
-	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
-			       GFS2_BASIC_BLOCK_SHIFT;
-	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
-	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
-			  sizeof(struct gfs2_dinode)) / sizeof(u64);
-	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
-			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
-	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
-	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
-	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
-	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
-	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
-				sizeof(struct gfs2_meta_header)) /
-			        sizeof(struct gfs2_quota_change);
-
-	/* Compute maximum reservation required to add a entry to a directory */
-
-	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
-			     sdp->sd_jbsize);
-
-	ind_blocks = 0;
-	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
-		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
-		ind_blocks += tmp_blocks;
-	}
-
-	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
-
-	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
-
-	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
-				sizeof(struct gfs2_dinode);
-	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
-	for (x = 2;; x++) {
-		u64 space, d;
-		u32 m;
-
-		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
-		d = space;
-		m = do_div(d, sdp->sd_inptrs);
-
-		if (d != sdp->sd_heightsize[x - 1] || m)
-			break;
-		sdp->sd_heightsize[x] = space;
-	}
-	sdp->sd_max_height = x;
-	sdp->sd_heightsize[x] = ~0;
-	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
-
-	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
-				 sizeof(struct gfs2_dinode);
-	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
-	for (x = 2;; x++) {
-		u64 space, d;
-		u32 m;
-
-		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
-		d = space;
-		m = do_div(d, sdp->sd_inptrs);
-
-		if (d != sdp->sd_jheightsize[x - 1] || m)
-			break;
-		sdp->sd_jheightsize[x] = space;
-	}
-	sdp->sd_max_jheight = x;
-	sdp->sd_jheightsize[x] = ~0;
-	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
-
-	return 0;
-}
-
 /**
  * gfs2_jindex_hold - Grab a lock on the jindex
  * @sdp: The GFS2 superblock
@@ -581,39 +274,6 @@ fail:
 	return error;
 }
 
-/**
- * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
- * @sdp: the filesystem
- *
- * Returns: errno
- */
-
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
-{
-	struct gfs2_holder t_gh;
-	int error;
-
-	gfs2_quota_sync(sdp);
-	gfs2_statfs_sync(sdp);
-
-	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
-				   &t_gh);
-	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return error;
-
-	gfs2_meta_syncfs(sdp);
-	gfs2_log_shutdown(sdp);
-
-	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-
-	if (t_gh.gh_gl)
-		gfs2_glock_dq_uninit(&t_gh);
-
-	gfs2_quota_cleanup(sdp);
-
-	return error;
-}
-
 static void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
 {
 	const struct gfs2_statfs_change *str = buf;
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 44361ecc44f7..50a4c9b1215e 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -12,11 +12,6 @@
 
 #include "incore.h"
 
-void gfs2_tune_init(struct gfs2_tune *gt);
-
-int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent);
-int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent);
-int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector);
 void gfs2_lm_unmount(struct gfs2_sbd *sdp);
 
 static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
@@ -40,7 +35,6 @@ int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
 			      struct gfs2_inode **ipp);
 
 int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp);
 
 int gfs2_statfs_init(struct gfs2_sbd *sdp);
 void gfs2_statfs_change(struct gfs2_sbd *sdp,
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 74846559fc3f..7e1879f1a02c 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -269,14 +269,6 @@ ARGS_ATTR(quota,           "%u\n");
 ARGS_ATTR(suiddir,         "%d\n");
 ARGS_ATTR(data,            "%d\n");
 
-/* one oddball doesn't fit the macro mold */
-static ssize_t noatime_show(struct gfs2_sbd *sdp, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE, "%d\n",
-			!!test_bit(SDF_NOATIME, &sdp->sd_flags));
-}
-static struct args_attr args_attr_noatime = __ATTR_RO(noatime);
-
 static struct attribute *args_attrs[] = {
 	&args_attr_lockproto.attr,
 	&args_attr_locktable.attr,
@@ -292,7 +284,6 @@ static struct attribute *args_attrs[] = {
 	&args_attr_quota.attr,
 	&args_attr_suiddir.attr,
 	&args_attr_data.attr,
-	&args_attr_noatime.attr,
 	NULL,
 };
 
@@ -407,7 +398,6 @@ TUNE_ATTR(incore_log_blocks, 0);
 TUNE_ATTR(log_flush_secs, 0);
 TUNE_ATTR(quota_warn_period, 0);
 TUNE_ATTR(quota_quantum, 0);
-TUNE_ATTR(atime_quantum, 0);
 TUNE_ATTR(max_readahead, 0);
 TUNE_ATTR(complain_secs, 0);
 TUNE_ATTR(statfs_slow, 0);
@@ -427,7 +417,6 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_log_flush_secs.attr,
 	&tune_attr_quota_warn_period.attr,
 	&tune_attr_quota_quantum.attr,
-	&tune_attr_atime_quantum.attr,
 	&tune_attr_max_readahead.attr,
 	&tune_attr_complain_secs.attr,
 	&tune_attr_statfs_slow.attr,
diff --git a/fs/inotify_user.c b/fs/inotify_user.c
index 60249429a253..d85c7d931cdf 100644
--- a/fs/inotify_user.c
+++ b/fs/inotify_user.c
@@ -323,7 +323,7 @@ out:
 }
 
 /*
- * remove_kevent - cleans up and ultimately frees the given kevent
+ * remove_kevent - cleans up the given kevent
  *
  * Caller must hold dev->ev_mutex.
  */
@@ -334,7 +334,13 @@ static void remove_kevent(struct inotify_device *dev,
 
 	dev->event_count--;
 	dev->queue_size -= sizeof(struct inotify_event) + kevent->event.len;
+}
 
+/*
+ * free_kevent - frees the given kevent.
+ */
+static void free_kevent(struct inotify_kernel_event *kevent)
+{
 	kfree(kevent->name);
 	kmem_cache_free(event_cachep, kevent);
 }
@@ -350,6 +356,7 @@ static void inotify_dev_event_dequeue(struct inotify_device *dev)
 		struct inotify_kernel_event *kevent;
 		kevent = inotify_dev_get_event(dev);
 		remove_kevent(dev, kevent);
+		free_kevent(kevent);
 	}
 }
 
@@ -433,17 +440,15 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 	dev = file->private_data;
 
 	while (1) {
-		int events;
 
 		prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE);
 
 		mutex_lock(&dev->ev_mutex);
-		events = !list_empty(&dev->events);
-		mutex_unlock(&dev->ev_mutex);
-		if (events) {
+		if (!list_empty(&dev->events)) {
 			ret = 0;
 			break;
 		}
+		mutex_unlock(&dev->ev_mutex);
 
 		if (file->f_flags & O_NONBLOCK) {
 			ret = -EAGAIN;
@@ -462,7 +467,6 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 
-	mutex_lock(&dev->ev_mutex);
 	while (1) {
 		struct inotify_kernel_event *kevent;
 
@@ -481,6 +485,13 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 			}
 			break;
 		}
+		remove_kevent(dev, kevent);
+
+		/*
+		 * Must perform the copy_to_user outside the mutex in order
+		 * to avoid a lock order reversal with mmap_sem.
+		 */
+		mutex_unlock(&dev->ev_mutex);
 
 		if (copy_to_user(buf, &kevent->event, event_size)) {
 			ret = -EFAULT;
@@ -498,7 +509,9 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 			count -= kevent->event.len;
 		}
 
-		remove_kevent(dev, kevent);
+		free_kevent(kevent);
+
+		mutex_lock(&dev->ev_mutex);
 	}
 	mutex_unlock(&dev->ev_mutex);
 
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index ecc3330972e5..7408227c49c9 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -120,22 +120,21 @@ static int (*check_part[])(struct parsed_partitions *, struct block_device *) =
  * a pointer to that same buffer (for convenience).
  */
 
-char *disk_name(struct gendisk *hd, int part, char *buf)
+char *disk_name(struct gendisk *hd, int partno, char *buf)
 {
-	if (!part)
+	if (!partno)
 		snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
 	else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
-		snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, part);
+		snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
 	else
-		snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, part);
+		snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
 
 	return buf;
 }
 
 const char *bdevname(struct block_device *bdev, char *buf)
 {
-	int part = MINOR(bdev->bd_dev) - bdev->bd_disk->first_minor;
-	return disk_name(bdev->bd_disk, part, buf);
+	return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
 }
 
 EXPORT_SYMBOL(bdevname);
@@ -169,7 +168,7 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
 	if (isdigit(state->name[strlen(state->name)-1]))
 		sprintf(state->name, "p");
 
-	state->limit = hd->minors;
+	state->limit = disk_max_parts(hd);
 	i = res = err = 0;
 	while (!res && check_part[i]) {
 		memset(&state->parts, 0, sizeof(state->parts));
@@ -204,21 +203,22 @@ static ssize_t part_start_show(struct device *dev,
 	return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
 }
 
-static ssize_t part_size_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
+ssize_t part_size_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
 	return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
 }
 
-static ssize_t part_stat_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
+ssize_t part_stat_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	int cpu;
 
-	preempt_disable();
-	part_round_stats(p);
-	preempt_enable();
+	cpu = part_stat_lock();
+	part_round_stats(cpu, p);
+	part_stat_unlock();
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
@@ -238,17 +238,17 @@ static ssize_t part_stat_show(struct device *dev,
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
-static ssize_t part_fail_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
+ssize_t part_fail_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
 
 	return sprintf(buf, "%d\n", p->make_it_fail);
 }
 
-static ssize_t part_fail_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t count)
+ssize_t part_fail_store(struct device *dev,
+			struct device_attribute *attr,
+			const char *buf, size_t count)
 {
 	struct hd_struct *p = dev_to_part(dev);
 	int i;
@@ -300,40 +300,34 @@ struct device_type part_type = {
 	.release	= part_release,
 };
 
-static inline void partition_sysfs_add_subdir(struct hd_struct *p)
-{
-	struct kobject *k;
-
-	k = kobject_get(&p->dev.kobj);
-	p->holder_dir = kobject_create_and_add("holders", k);
-	kobject_put(k);
-}
-
-static inline void disk_sysfs_add_subdirs(struct gendisk *disk)
+static void delete_partition_rcu_cb(struct rcu_head *head)
 {
-	struct kobject *k;
+	struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
 
-	k = kobject_get(&disk->dev.kobj);
-	disk->holder_dir = kobject_create_and_add("holders", k);
-	disk->slave_dir = kobject_create_and_add("slaves", k);
-	kobject_put(k);
+	part->start_sect = 0;
+	part->nr_sects = 0;
+	part_stat_set_all(part, 0);
+	put_device(part_to_dev(part));
 }
 
-void delete_partition(struct gendisk *disk, int part)
+void delete_partition(struct gendisk *disk, int partno)
 {
-	struct hd_struct *p = disk->part[part-1];
+	struct disk_part_tbl *ptbl = disk->part_tbl;
+	struct hd_struct *part;
 
-	if (!p)
+	if (partno >= ptbl->len)
 		return;
-	if (!p->nr_sects)
+
+	part = ptbl->part[partno];
+	if (!part)
 		return;
-	disk->part[part-1] = NULL;
-	p->start_sect = 0;
-	p->nr_sects = 0;
-	part_stat_set_all(p, 0);
-	kobject_put(p->holder_dir);
-	device_del(&p->dev);
-	put_device(&p->dev);
+
+	blk_free_devt(part_devt(part));
+	rcu_assign_pointer(ptbl->part[partno], NULL);
+	kobject_put(part->holder_dir);
+	device_del(part_to_dev(part));
+
+	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -344,102 +338,132 @@ static ssize_t whole_disk_show(struct device *dev,
 static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
 		   whole_disk_show, NULL);
 
-int add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, int flags)
+int add_partition(struct gendisk *disk, int partno,
+		  sector_t start, sector_t len, int flags)
 {
 	struct hd_struct *p;
+	dev_t devt = MKDEV(0, 0);
+	struct device *ddev = disk_to_dev(disk);
+	struct device *pdev;
+	struct disk_part_tbl *ptbl;
+	const char *dname;
 	int err;
 
+	err = disk_expand_part_tbl(disk, partno);
+	if (err)
+		return err;
+	ptbl = disk->part_tbl;
+
+	if (ptbl->part[partno])
+		return -EBUSY;
+
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
 	if (!init_part_stats(p)) {
 		err = -ENOMEM;
-		goto out0;
+		goto out_free;
 	}
+	pdev = part_to_dev(p);
+
 	p->start_sect = start;
 	p->nr_sects = len;
-	p->partno = part;
-	p->policy = disk->policy;
+	p->partno = partno;
+	p->policy = get_disk_ro(disk);
 
-	if (isdigit(disk->dev.bus_id[strlen(disk->dev.bus_id)-1]))
-		snprintf(p->dev.bus_id, BUS_ID_SIZE,
-		"%sp%d", disk->dev.bus_id, part);
+	dname = dev_name(ddev);
+	if (isdigit(dname[strlen(dname) - 1]))
+		snprintf(pdev->bus_id, BUS_ID_SIZE, "%sp%d", dname, partno);
 	else
-		snprintf(p->dev.bus_id, BUS_ID_SIZE,
-			 "%s%d", disk->dev.bus_id, part);
+		snprintf(pdev->bus_id, BUS_ID_SIZE, "%s%d", dname, partno);
 
-	device_initialize(&p->dev);
-	p->dev.devt = MKDEV(disk->major, disk->first_minor + part);
-	p->dev.class = &block_class;
-	p->dev.type = &part_type;
-	p->dev.parent = &disk->dev;
-	disk->part[part-1] = p;
+	device_initialize(pdev);
+	pdev->class = &block_class;
+	pdev->type = &part_type;
+	pdev->parent = ddev;
+
+	err = blk_alloc_devt(p, &devt);
+	if (err)
+		goto out_free;
+	pdev->devt = devt;
 
 	/* delay uevent until 'holders' subdir is created */
-	p->dev.uevent_suppress = 1;
-	err = device_add(&p->dev);
+	pdev->uevent_suppress = 1;
+	err = device_add(pdev);
 	if (err)
-		goto out1;
-	partition_sysfs_add_subdir(p);
-	p->dev.uevent_suppress = 0;
+		goto out_put;
+
+	err = -ENOMEM;
+	p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
+	if (!p->holder_dir)
+		goto out_del;
+
+	pdev->uevent_suppress = 0;
 	if (flags & ADDPART_FLAG_WHOLEDISK) {
-		err = device_create_file(&p->dev, &dev_attr_whole_disk);
+		err = device_create_file(pdev, &dev_attr_whole_disk);
 		if (err)
-			goto out2;
+			goto out_del;
 	}
 
+	/* everything is up and running, commence */
+	INIT_RCU_HEAD(&p->rcu_head);
+	rcu_assign_pointer(ptbl->part[partno], p);
+
 	/* suppress uevent if the disk supresses it */
-	if (!disk->dev.uevent_suppress)
-		kobject_uevent(&p->dev.kobj, KOBJ_ADD);
+	if (!ddev->uevent_suppress)
+		kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
 	return 0;
 
-out2:
-	device_del(&p->dev);
-out1:
-	put_device(&p->dev);
-	free_part_stats(p);
-out0:
+out_free:
 	kfree(p);
 	return err;
+out_del:
+	kobject_put(p->holder_dir);
+	device_del(pdev);
+out_put:
+	put_device(pdev);
+	blk_free_devt(devt);
+	return err;
 }
 
 /* Not exported, helper to add_disk(). */
 void register_disk(struct gendisk *disk)
 {
+	struct device *ddev = disk_to_dev(disk);
 	struct block_device *bdev;
+	struct disk_part_iter piter;
+	struct hd_struct *part;
 	char *s;
-	int i;
-	struct hd_struct *p;
 	int err;
 
-	disk->dev.parent = disk->driverfs_dev;
-	disk->dev.devt = MKDEV(disk->major, disk->first_minor);
+	ddev->parent = disk->driverfs_dev;
 
-	strlcpy(disk->dev.bus_id, disk->disk_name, BUS_ID_SIZE);
+	strlcpy(ddev->bus_id, disk->disk_name, BUS_ID_SIZE);
 	/* ewww... some of these buggers have / in the name... */
-	s = strchr(disk->dev.bus_id, '/');
+	s = strchr(ddev->bus_id, '/');
 	if (s)
 		*s = '!';
 
 	/* delay uevents, until we scanned partition table */
-	disk->dev.uevent_suppress = 1;
+	ddev->uevent_suppress = 1;
 
-	if (device_add(&disk->dev))
+	if (device_add(ddev))
 		return;
 #ifndef CONFIG_SYSFS_DEPRECATED
-	err = sysfs_create_link(block_depr, &disk->dev.kobj,
-				kobject_name(&disk->dev.kobj));
+	err = sysfs_create_link(block_depr, &ddev->kobj,
+				kobject_name(&ddev->kobj));
 	if (err) {
-		device_del(&disk->dev);
+		device_del(ddev);
 		return;
 	}
 #endif
-	disk_sysfs_add_subdirs(disk);
+	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
+	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
 	/* No minors to use for partitions */
-	if (disk->minors == 1)
+	if (!disk_partitionable(disk))
 		goto exit;
 
 	/* No such device (e.g., media were just removed) */
@@ -458,41 +482,57 @@ void register_disk(struct gendisk *disk)
 
 exit:
 	/* announce disk after possible partitions are created */
-	disk->dev.uevent_suppress = 0;
-	kobject_uevent(&disk->dev.kobj, KOBJ_ADD);
+	ddev->uevent_suppress = 0;
+	kobject_uevent(&ddev->kobj, KOBJ_ADD);
 
 	/* announce possible partitions */
-	for (i = 1; i < disk->minors; i++) {
-		p = disk->part[i-1];
-		if (!p || !p->nr_sects)
-			continue;
-		kobject_uevent(&p->dev.kobj, KOBJ_ADD);
-	}
+	disk_part_iter_init(&piter, disk, 0);
+	while ((part = disk_part_iter_next(&piter)))
+		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
+	disk_part_iter_exit(&piter);
 }
 
 int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 {
+	struct disk_part_iter piter;
+	struct hd_struct *part;
 	struct parsed_partitions *state;
-	int p, res;
+	int p, highest, res;
 
 	if (bdev->bd_part_count)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
 	if (res)
 		return res;
-	bdev->bd_invalidated = 0;
-	for (p = 1; p < disk->minors; p++)
-		delete_partition(disk, p);
+
+	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
+	while ((part = disk_part_iter_next(&piter)))
+		delete_partition(disk, part->partno);
+	disk_part_iter_exit(&piter);
+
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
+	check_disk_size_change(disk, bdev);
+	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
 		return 0;
 	if (IS_ERR(state))	/* I/O error reading the partition table */
 		return -EIO;
 
 	/* tell userspace that the media / partition table may have changed */
-	kobject_uevent(&disk->dev.kobj, KOBJ_CHANGE);
+	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
 
+	/* Detect the highest partition number and preallocate
+	 * disk->part_tbl.  This is an optimization and not strictly
+	 * necessary.
+	 */
+	for (p = 1, highest = 0; p < state->limit; p++)
+		if (state->parts[p].size)
+			highest = p;
+
+	disk_expand_part_tbl(disk, highest);
+
+	/* add partitions */
 	for (p = 1; p < state->limit; p++) {
 		sector_t size = state->parts[p].size;
 		sector_t from = state->parts[p].from;
@@ -541,25 +581,31 @@ EXPORT_SYMBOL(read_dev_sector);
 
 void del_gendisk(struct gendisk *disk)
 {
-	int p;
+	struct disk_part_iter piter;
+	struct hd_struct *part;
 
 	/* invalidate stuff */
-	for (p = disk->minors - 1; p > 0; p--) {
-		invalidate_partition(disk, p);
-		delete_partition(disk, p);
+	disk_part_iter_init(&piter, disk,
+			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
+	while ((part = disk_part_iter_next(&piter))) {
+		invalidate_partition(disk, part->partno);
+		delete_partition(disk, part->partno);
 	}
+	disk_part_iter_exit(&piter);
+
 	invalidate_partition(disk, 0);
-	disk->capacity = 0;
+	blk_free_devt(disk_to_dev(disk)->devt);
+	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
 	unlink_gendisk(disk);
-	disk_stat_set_all(disk, 0);
-	disk->stamp = 0;
+	part_stat_set_all(&disk->part0, 0);
+	disk->part0.stamp = 0;
 
-	kobject_put(disk->holder_dir);
+	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
 	disk->driverfs_dev = NULL;
 #ifndef CONFIG_SYSFS_DEPRECATED
-	sysfs_remove_link(block_depr, disk->dev.bus_id);
+	sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 #endif
-	device_del(&disk->dev);
+	device_del(disk_to_dev(disk));
 }
diff --git a/fs/partitions/check.h b/fs/partitions/check.h
index 17ae8ecd9e8b..98dbe1a84528 100644
--- a/fs/partitions/check.h
+++ b/fs/partitions/check.h
@@ -5,15 +5,13 @@
  * add_gd_partition adds a partitions details to the devices partition
  * description.
  */
-enum { MAX_PART = 256 };
-
 struct parsed_partitions {
 	char name[BDEVNAME_SIZE];
 	struct {
 		sector_t from;
 		sector_t size;
 		int flags;
-	} parts[MAX_PART];
+	} parts[DISK_MAX_PARTS];
 	int next;
 	int limit;
 };
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 52312ec93ff4..5145cb9125af 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -58,7 +58,7 @@ const struct inode_operations ramfs_file_inode_operations = {
  * size 0 on the assumption that it's going to be used for an mmap of shared
  * memory
  */
-static int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
+int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 {
 	struct pagevec lru_pvec;
 	unsigned long npages, xpages, loop, limit;
diff --git a/fs/splice.c b/fs/splice.c
index 1bbc6f4bb09c..a1e701c27156 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -898,6 +898,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 	if (unlikely(!(out->f_mode & FMODE_WRITE)))
 		return -EBADF;
 
+	if (unlikely(out->f_flags & O_APPEND))
+		return -EINVAL;
+
 	ret = rw_verify_area(WRITE, out, ppos, len);
 	if (unlikely(ret < 0))
 		return ret;
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index b9cb77473758..d7f7645779f2 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -538,7 +538,7 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
 		printk(KERN_DEBUG "\t%d orphan inode numbers:\n", n);
 		for (i = 0; i < n; i++)
 			printk(KERN_DEBUG "\t  ino %llu\n",
-			       le64_to_cpu(orph->inos[i]));
+			       (unsigned long long)le64_to_cpu(orph->inos[i]));
 		break;
 	}
 	default:
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 2b267c9a1806..526c01ec8003 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -426,7 +426,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 
 	while (1) {
 		dbg_gen("feed '%s', ino %llu, new f_pos %#x",
-			dent->name, le64_to_cpu(dent->inum),
+			dent->name, (unsigned long long)le64_to_cpu(dent->inum),
 			key_hash_flash(c, &dent->key));
 		ubifs_assert(dent->ch.sqnum > ubifs_inode(dir)->creat_sqnum);
 
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index e045c8b55423..47814cde2407 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -507,7 +507,6 @@ int ubifs_find_free_space(struct ubifs_info *c, int min_space, int *free,
 		rsvd_idx_lebs = 0;
 	lebs = c->lst.empty_lebs + c->freeable_cnt + c->idx_gc_cnt -
 	       c->lst.taken_empty_lebs;
-	ubifs_assert(lebs + c->lst.idx_lebs >= c->min_idx_lebs);
 	if (rsvd_idx_lebs < lebs)
 		/*
 		 * OK to allocate an empty LEB, but we still don't want to go
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 13f1019c859f..02aba36fe3d4 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -334,15 +334,15 @@ int ubifs_garbage_collect_leb(struct ubifs_info *c, struct ubifs_lprops *lp)
 
 		err = move_nodes(c, sleb);
 		if (err)
-			goto out;
+			goto out_inc_seq;
 
 		err = gc_sync_wbufs(c);
 		if (err)
-			goto out;
+			goto out_inc_seq;
 
 		err = ubifs_change_one_lp(c, lnum, c->leb_size, 0, 0, 0, 0);
 		if (err)
-			goto out;
+			goto out_inc_seq;
 
 		/* Allow for races with TNC */
 		c->gced_lnum = lnum;
@@ -369,6 +369,14 @@ int ubifs_garbage_collect_leb(struct ubifs_info *c, struct ubifs_lprops *lp)
 out:
 	ubifs_scan_destroy(sleb);
 	return err;
+
+out_inc_seq:
+	/* We may have moved at least some nodes so allow for races with TNC */
+	c->gced_lnum = lnum;
+	smp_wmb();
+	c->gc_seq += 1;
+	smp_wmb();
+	goto out;
 }
 
 /**
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 7562464ac83f..3f4902060c7a 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1024,14 +1024,13 @@ static int mount_ubifs(struct ubifs_info *c)
 		goto out_dereg;
 	}
 
+	sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id);
 	if (!mounted_read_only) {
 		err = alloc_wbufs(c);
 		if (err)
 			goto out_cbuf;
 
 		/* Create background thread */
-		sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num,
-			c->vi.vol_id);
 		c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name);
 		if (!c->bgt)
 			c->bgt = ERR_PTR(-EINVAL);
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 7da209ab9378..7634c5970887 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -1476,7 +1476,7 @@ again:
 	}
 
 	err = fallible_read_node(c, key, &zbr, node);
-	if (maybe_leb_gced(c, zbr.lnum, gc_seq1)) {
+	if (err <= 0 || maybe_leb_gced(c, zbr.lnum, gc_seq1)) {
 		/*
 		 * The node may have been GC'ed out from under us so try again
 		 * while keeping the TNC mutex locked.
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index f42f80a3b1fa..a44d68eb50b5 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1338,6 +1338,10 @@ __xfs_get_blocks(
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
 	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
 	size = bh_result->b_size;
+
+	if (!create && direct && offset >= i_size_read(inode))
+		return 0;
+
 	error = xfs_iomap(XFS_I(inode), offset, size,
 			     create ? flags : BMAPI_READ, &iomap, &niomap);
 	if (error)
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 986061ae1b9b..36d5fcd3f593 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1001,12 +1001,13 @@ xfs_buf_iodone_work(
 	 * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
 	 * ordered flag and reissue them.  Because we can't tell the higher
 	 * layers directly that they should not issue ordered I/O anymore, they
-	 * need to check if the ordered flag was cleared during I/O completion.
+	 * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion.
 	 */
 	if ((bp->b_error == EOPNOTSUPP) &&
 	    (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
 		XB_TRACE(bp, "ordered_retry", bp->b_iodone);
 		bp->b_flags &= ~XBF_ORDERED;
+		bp->b_flags |= _XFS_BARRIER_FAILED;
 		xfs_buf_iorequest(bp);
 	} else if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index fe0109956656..456519a088c7 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -85,6 +85,14 @@ typedef enum {
 	 * modifications being lost.
 	 */
 	_XBF_PAGE_LOCKED = (1 << 22),
+
+	/*
+	 * If we try a barrier write, but it fails we have to communicate
+	 * this to the upper layers.  Unfortunately b_error gets overwritten
+	 * when the buffer is re-issued so we have to add another flag to
+	 * keep this information.
+	 */
+	_XFS_BARRIER_FAILED = (1 << 23),
 } xfs_buf_flags_t;
 
 typedef enum {
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 73c65f19e549..18d3c8487835 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1302,9 +1302,29 @@ xfs_fs_remount(
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
 			break;
 		default:
+			/*
+			 * Logically we would return an error here to prevent
+			 * users from believing they might have changed
+			 * mount options using remount which can't be changed.
+			 *
+			 * But unfortunately mount(8) adds all options from
+			 * mtab and fstab to the mount arguments in some cases
+			 * so we can't blindly reject options, but have to
+			 * check for each specified option if it actually
+			 * differs from the currently set option and only
+			 * reject it if that's the case.
+			 *
+			 * Until that is implemented we return success for
+			 * every remount request, and silently ignore all
+			 * options that we can't actually change.
+			 */
+#if 0
 			printk(KERN_INFO
 	"XFS: mount option \"%s\" not supported for remount\n", p);
 			return -EINVAL;
+#else
+			return 0;
+#endif
 		}
 	}
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 608c30c3f76b..002fc2617c8e 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -732,6 +732,7 @@ xfs_buf_item_init(
 	bip->bli_item.li_ops = &xfs_buf_item_ops;
 	bip->bli_item.li_mountp = mp;
 	bip->bli_buf = bp;
+	xfs_buf_hold(bp);
 	bip->bli_format.blf_type = XFS_LI_BUF;
 	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
 	bip->bli_format.blf_len = (ushort)BTOBB(XFS_BUF_COUNT(bp));
@@ -867,6 +868,21 @@ xfs_buf_item_dirty(
 	return (bip->bli_flags & XFS_BLI_DIRTY);
 }
 
+STATIC void
+xfs_buf_item_free(
+	xfs_buf_log_item_t	*bip)
+{
+#ifdef XFS_TRANS_DEBUG
+	kmem_free(bip->bli_orig);
+	kmem_free(bip->bli_logged);
+#endif /* XFS_TRANS_DEBUG */
+
+#ifdef XFS_BLI_TRACE
+	ktrace_free(bip->bli_trace);
+#endif
+	kmem_zone_free(xfs_buf_item_zone, bip);
+}
+
 /*
  * This is called when the buf log item is no longer needed.  It should
  * free the buf log item associated with the given buffer and clear
@@ -887,18 +903,8 @@ xfs_buf_item_relse(
 	    (XFS_BUF_IODONE_FUNC(bp) != NULL)) {
 		XFS_BUF_CLR_IODONE_FUNC(bp);
 	}
-
-#ifdef XFS_TRANS_DEBUG
-	kmem_free(bip->bli_orig);
-	bip->bli_orig = NULL;
-	kmem_free(bip->bli_logged);
-	bip->bli_logged = NULL;
-#endif /* XFS_TRANS_DEBUG */
-
-#ifdef XFS_BLI_TRACE
-	ktrace_free(bip->bli_trace);
-#endif
-	kmem_zone_free(xfs_buf_item_zone, bip);
+	xfs_buf_rele(bp);
+	xfs_buf_item_free(bip);
 }
 
 
@@ -1120,6 +1126,7 @@ xfs_buf_iodone(
 
 	ASSERT(bip->bli_buf == bp);
 
+	xfs_buf_rele(bp);
 	mp = bip->bli_item.li_mountp;
 
 	/*
@@ -1136,18 +1143,7 @@ xfs_buf_iodone(
 	 * xfs_trans_delete_ail() drops the AIL lock.
 	 */
 	xfs_trans_delete_ail(mp, (xfs_log_item_t *)bip);
-
-#ifdef XFS_TRANS_DEBUG
-	kmem_free(bip->bli_orig);
-	bip->bli_orig = NULL;
-	kmem_free(bip->bli_logged);
-	bip->bli_logged = NULL;
-#endif /* XFS_TRANS_DEBUG */
-
-#ifdef XFS_BLI_TRACE
-	ktrace_free(bip->bli_trace);
-#endif
-	kmem_zone_free(xfs_buf_item_zone, bip);
+	xfs_buf_item_free(bip);
 }
 
 #if defined(XFS_BLI_TRACE)
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 760f4c5b5160..75b0cd4da0ea 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -149,7 +149,14 @@ xfs_swap_extents(
 
 	sbp = &sxp->sx_stat;
 
-	xfs_lock_two_inodes(ip, tip, lock_flags);
+	/*
+	 * we have to do two separate lock calls here to keep lockdep
+	 * happy. If we try to get all the locks in one call, lock will
+	 * report false positives when we drop the ILOCK and regain them
+	 * below.
+	 */
+	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
+	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
 	locked = 1;
 
 	/* Verify that both files have the same format */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 00e80df9dd9d..dbd9cef852ec 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -4118,7 +4118,7 @@ xfs_iext_indirect_to_direct(
 	ASSERT(nextents <= XFS_LINEAR_EXTS);
 	size = nextents * sizeof(xfs_bmbt_rec_t);
 
-	xfs_iext_irec_compact_full(ifp);
+	xfs_iext_irec_compact_pages(ifp);
 	ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ);
 
 	ep = ifp->if_u1.if_ext_irec->er_extbuf;
@@ -4449,8 +4449,7 @@ xfs_iext_irec_remove(
  * compaction policy is as follows:
  *
  *    Full Compaction: Extents fit into a single page (or inline buffer)
- *    Full Compaction: Extents occupy less than 10% of allocated space
- * Partial Compaction: Extents occupy > 10% and < 50% of allocated space
+ * Partial Compaction: Extents occupy less than 50% of allocated space
  *      No Compaction: Extents occupy at least 50% of allocated space
  */
 void
@@ -4471,8 +4470,6 @@ xfs_iext_irec_compact(
 		xfs_iext_direct_to_inline(ifp, nextents);
 	} else if (nextents <= XFS_LINEAR_EXTS) {
 		xfs_iext_indirect_to_direct(ifp);
-	} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 3) {
-		xfs_iext_irec_compact_full(ifp);
 	} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 1) {
 		xfs_iext_irec_compact_pages(ifp);
 	}
@@ -4496,7 +4493,7 @@ xfs_iext_irec_compact_pages(
 		erp_next = erp + 1;
 		if (erp_next->er_extcount <=
 		    (XFS_LINEAR_EXTS - erp->er_extcount)) {
-			memmove(&erp->er_extbuf[erp->er_extcount],
+			memcpy(&erp->er_extbuf[erp->er_extcount],
 				erp_next->er_extbuf, erp_next->er_extcount *
 				sizeof(xfs_bmbt_rec_t));
 			erp->er_extcount += erp_next->er_extcount;
@@ -4516,91 +4513,6 @@ xfs_iext_irec_compact_pages(
 }
 
 /*
- * Fully compact the extent records managed by the indirection array.
- */
-void
-xfs_iext_irec_compact_full(
-	xfs_ifork_t	*ifp)			/* inode fork pointer */
-{
-	xfs_bmbt_rec_host_t *ep, *ep_next;	/* extent record pointers */
-	xfs_ext_irec_t	*erp, *erp_next;	/* extent irec pointers */
-	int		erp_idx = 0;		/* extent irec index */
-	int		ext_avail;		/* empty entries in ex list */
-	int		ext_diff;		/* number of exts to add */
-	int		nlists;			/* number of irec's (ex lists) */
-
-	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
-
-	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-	erp = ifp->if_u1.if_ext_irec;
-	ep = &erp->er_extbuf[erp->er_extcount];
-	erp_next = erp + 1;
-	ep_next = erp_next->er_extbuf;
-
-	while (erp_idx < nlists - 1) {
-		/*
-		 * Check how many extent records are available in this irec.
-		 * If there is none skip the whole exercise.
-		 */
-		ext_avail = XFS_LINEAR_EXTS - erp->er_extcount;
-		if (ext_avail) {
-
-			/*
-			 * Copy over as many as possible extent records into
-			 * the previous page.
-			 */
-			ext_diff = MIN(ext_avail, erp_next->er_extcount);
-			memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t));
-			erp->er_extcount += ext_diff;
-			erp_next->er_extcount -= ext_diff;
-
-			/*
-			 * If the next irec is empty now we can simply
-			 * remove it.
-			 */
-			if (erp_next->er_extcount == 0) {
-				/*
-				 * Free page before removing extent record
-				 * so er_extoffs don't get modified in
-				 * xfs_iext_irec_remove.
-				 */
-				kmem_free(erp_next->er_extbuf);
-				erp_next->er_extbuf = NULL;
-				xfs_iext_irec_remove(ifp, erp_idx + 1);
-				erp = &ifp->if_u1.if_ext_irec[erp_idx];
-				nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-
-			/*
-			 * If the next irec is not empty move up the content
-			 * that has not been copied to the previous page to
-			 * the beggining of this one.
-			 */
-			} else {
-				memmove(erp_next->er_extbuf, &ep_next[ext_diff],
-					erp_next->er_extcount *
-					sizeof(xfs_bmbt_rec_t));
-				ep_next = erp_next->er_extbuf;
-				memset(&ep_next[erp_next->er_extcount], 0,
-					(XFS_LINEAR_EXTS -
-						erp_next->er_extcount) *
-					sizeof(xfs_bmbt_rec_t));
-			}
-		}
-
-		if (erp->er_extcount == XFS_LINEAR_EXTS) {
-			erp_idx++;
-			if (erp_idx < nlists)
-				erp = &ifp->if_u1.if_ext_irec[erp_idx];
-			else
-				break;
-		}
-		ep = &erp->er_extbuf[erp->er_extcount];
-		erp_next = erp + 1;
-		ep_next = erp_next->er_extbuf;
-	}
-}
-
-/*
  * This is called to update the er_extoff field in the indirection
  * array when extents have been added or removed from one of the
  * extent lists. erp_idx contains the irec index to begin updating
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ccba14eb9dbe..0b02c6443551 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -124,16 +124,27 @@ STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
 STATIC int	xlog_iclogs_empty(xlog_t *log);
 
 #if defined(XFS_LOG_TRACE)
+
+#define XLOG_TRACE_LOGGRANT_SIZE	2048
+#define XLOG_TRACE_ICLOG_SIZE		256
+
+void
+xlog_trace_loggrant_alloc(xlog_t *log)
+{
+	log->l_grant_trace = ktrace_alloc(XLOG_TRACE_LOGGRANT_SIZE, KM_NOFS);
+}
+
+void
+xlog_trace_loggrant_dealloc(xlog_t *log)
+{
+	ktrace_free(log->l_grant_trace);
+}
+
 void
 xlog_trace_loggrant(xlog_t *log, xlog_ticket_t *tic, xfs_caddr_t string)
 {
 	unsigned long cnts;
 
-	if (!log->l_grant_trace) {
-		log->l_grant_trace = ktrace_alloc(2048, KM_NOSLEEP);
-		if (!log->l_grant_trace)
-			return;
-	}
 	/* ticket counts are 1 byte each */
 	cnts = ((unsigned long)tic->t_ocnt) | ((unsigned long)tic->t_cnt) << 8;
 
@@ -157,10 +168,20 @@ xlog_trace_loggrant(xlog_t *log, xlog_ticket_t *tic, xfs_caddr_t string)
 }
 
 void
+xlog_trace_iclog_alloc(xlog_in_core_t *iclog)
+{
+	iclog->ic_trace = ktrace_alloc(XLOG_TRACE_ICLOG_SIZE, KM_NOFS);
+}
+
+void
+xlog_trace_iclog_dealloc(xlog_in_core_t *iclog)
+{
+	ktrace_free(iclog->ic_trace);
+}
+
+void
 xlog_trace_iclog(xlog_in_core_t *iclog, uint state)
 {
-	if (!iclog->ic_trace)
-		iclog->ic_trace = ktrace_alloc(256, KM_NOFS);
 	ktrace_enter(iclog->ic_trace,
 		     (void *)((unsigned long)state),
 		     (void *)((unsigned long)current_pid()),
@@ -170,8 +191,15 @@ xlog_trace_iclog(xlog_in_core_t *iclog, uint state)
 		     (void *)NULL, (void *)NULL);
 }
 #else
+
+#define	xlog_trace_loggrant_alloc(log)
+#define	xlog_trace_loggrant_dealloc(log)
 #define	xlog_trace_loggrant(log,tic,string)
+
+#define	xlog_trace_iclog_alloc(iclog)
+#define	xlog_trace_iclog_dealloc(iclog)
 #define	xlog_trace_iclog(iclog,state)
+
 #endif /* XFS_LOG_TRACE */
 
 
@@ -1005,11 +1033,12 @@ xlog_iodone(xfs_buf_t *bp)
 	l = iclog->ic_log;
 
 	/*
-	 * If the ordered flag has been removed by a lower
-	 * layer, it means the underlyin device no longer supports
+	 * If the _XFS_BARRIER_FAILED flag was set by a lower
+	 * layer, it means the underlying device no longer supports
 	 * barrier I/O. Warn loudly and turn off barriers.
 	 */
-	if ((l->l_mp->m_flags & XFS_MOUNT_BARRIER) && !XFS_BUF_ORDERED(bp)) {
+	if (bp->b_flags & _XFS_BARRIER_FAILED) {
+		bp->b_flags &= ~_XFS_BARRIER_FAILED;
 		l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
 		xfs_fs_cmn_err(CE_WARN, l->l_mp,
 				"xlog_iodone: Barriers are no longer supported"
@@ -1231,6 +1260,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	spin_lock_init(&log->l_grant_lock);
 	sv_init(&log->l_flush_wait, 0, "flush_wait");
 
+	xlog_trace_loggrant_alloc(log);
 	/* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
 	ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);
 
@@ -1285,6 +1315,8 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		sv_init(&iclog->ic_force_wait, SV_DEFAULT, "iclog-force");
 		sv_init(&iclog->ic_write_wait, SV_DEFAULT, "iclog-write");
 
+		xlog_trace_iclog_alloc(iclog);
+
 		iclogp = &iclog->ic_next;
 	}
 	*iclogp = log->l_iclog;			/* complete ring */
@@ -1565,11 +1597,7 @@ xlog_dealloc_log(xlog_t *log)
 		sv_destroy(&iclog->ic_force_wait);
 		sv_destroy(&iclog->ic_write_wait);
 		xfs_buf_free(iclog->ic_bp);
-#ifdef XFS_LOG_TRACE
-		if (iclog->ic_trace != NULL) {
-			ktrace_free(iclog->ic_trace);
-		}
-#endif
+		xlog_trace_iclog_dealloc(iclog);
 		next_iclog = iclog->ic_next;
 		kmem_free(iclog);
 		iclog = next_iclog;
@@ -1578,14 +1606,7 @@ xlog_dealloc_log(xlog_t *log)
 	spinlock_destroy(&log->l_grant_lock);
 
 	xfs_buf_free(log->l_xbuf);
-#ifdef XFS_LOG_TRACE
-	if (log->l_trace != NULL) {
-		ktrace_free(log->l_trace);
-	}
-	if (log->l_grant_trace != NULL) {
-		ktrace_free(log->l_grant_trace);
-	}
-#endif
+	xlog_trace_loggrant_dealloc(log);
 	log->l_mp->m_log = NULL;
 	kmem_free(log);
 }	/* xlog_dealloc_log */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index c8a5b22ee3e3..e7d8f84443fa 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -448,7 +448,6 @@ typedef struct log {
 	int			l_grant_write_bytes;
 
 #ifdef XFS_LOG_TRACE
-	struct ktrace		*l_trace;
 	struct ktrace		*l_grant_trace;
 #endif
 
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index aa238c8fbd7a..8b6812f66a15 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -1838,6 +1838,12 @@ again:
 #endif
 }
 
+/*
+ * xfs_lock_two_inodes() can only be used to lock one type of lock
+ * at a time - the iolock or the ilock, but not both at once. If
+ * we lock both at once, lockdep will report false positives saying
+ * we have violated locking orders.
+ */
 void
 xfs_lock_two_inodes(
 	xfs_inode_t		*ip0,
@@ -1848,6 +1854,8 @@ xfs_lock_two_inodes(
 	int			attempts = 0;
 	xfs_log_item_t		*lp;
 
+	if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
+		ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0);
 	ASSERT(ip0->i_ino != ip1->i_ino);
 
 	if (ip0->i_ino > ip1->i_ino) {
@@ -3152,6 +3160,13 @@ error1:	/* Just cancel transaction */
 /*
  * Zero file bytes between startoff and endoff inclusive.
  * The iolock is held exclusive and no blocks are buffered.
+ *
+ * This function is used by xfs_free_file_space() to zero
+ * partial blocks when the range to free is not block aligned.
+ * When unreserving space with boundaries that are not block
+ * aligned we round up the start and round down the end
+ * boundaries and then use this function to zero the parts of
+ * the blocks that got dropped during the rounding.
  */
 STATIC int
 xfs_zero_remaining_bytes(
@@ -3168,6 +3183,17 @@ xfs_zero_remaining_bytes(
 	int			nimap;
 	int			error = 0;
 
+	/*
+	 * Avoid doing I/O beyond eof - it's not necessary
+	 * since nothing can read beyond eof.  The space will
+	 * be zeroed when the file is extended anyway.
+	 */
+	if (startoff >= ip->i_size)
+		return 0;
+
+	if (endoff > ip->i_size)
+		endoff = ip->i_size;
+
 	bp = xfs_buf_get_noaddr(mp->m_sb.sb_blocksize,
 				XFS_IS_REALTIME_INODE(ip) ?
 				mp->m_rtdev_targp : mp->m_ddev_targp);