Merge tag 'nfs-rdma-4.4-2' of git://git.linux-nfs.org/projects/anna/nfs-rdma

NFS: NFSoRDMA Client Side Changes

In addition to a variety of bugfixes, these patches are mostly geared at
enabling both swap and backchannel support to the NFS over RDMA client.

Signed-off-by: Anna Schumake <Anna.Schumaker@Netapp.com>

19 files changed, 112 insertions, 119 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index ecbc63d..9a2ec79 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1828,7 +1828,6 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root,
 	int found = 0;
 	struct extent_buffer *eb;
 	struct btrfs_inode_extref *extref;
-	struct extent_buffer *leaf;
 	u32 item_size;
 	u32 cur_offset;
 	unsigned long ptr;
@@ -1856,9 +1855,8 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root,
 		btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 		btrfs_release_path(path);
 
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, slot);
-		ptr = btrfs_item_ptr_offset(leaf, slot);
+		item_size = btrfs_item_size_nr(eb, slot);
+		ptr = btrfs_item_ptr_offset(eb, slot);
 		cur_offset = 0;
 
 		while (cur_offset < item_size) {
@@ -1872,7 +1870,7 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root,
 			if (ret)
 				break;
 
-			cur_offset += btrfs_inode_extref_name_len(leaf, extref);
+			cur_offset += btrfs_inode_extref_name_len(eb, extref);
 			cur_offset += sizeof(*extref);
 		}
 		btrfs_tree_read_unlock_blocking(eb);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 295795a..1e60d00 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2847,6 +2847,8 @@ int open_ctree(struct super_block *sb,
 	    !extent_buffer_uptodate(chunk_root->node)) {
 		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
 		       sb->s_id);
+		if (!IS_ERR(chunk_root->node))
+			free_extent_buffer(chunk_root->node);
 		chunk_root->node = NULL;
 		goto fail_tree_roots;
 	}
@@ -2885,6 +2887,8 @@ retry_root_backup:
 	    !extent_buffer_uptodate(tree_root->node)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
 		       sb->s_id);
+		if (!IS_ERR(tree_root->node))
+			free_extent_buffer(tree_root->node);
 		tree_root->node = NULL;
 		goto recovery_tree_root;
 	}
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 8d05220..2513a7f 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -112,11 +112,11 @@ static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh,
 	u32 generation;
 
 	if (fh_type == FILEID_BTRFS_WITH_PARENT) {
-		if (fh_len !=  BTRFS_FID_SIZE_CONNECTABLE)
+		if (fh_len <  BTRFS_FID_SIZE_CONNECTABLE)
 			return NULL;
 		root_objectid = fid->root_objectid;
 	} else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) {
-		if (fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT)
+		if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT)
 			return NULL;
 		root_objectid = fid->parent_root_objectid;
 	} else
@@ -136,11 +136,11 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 	u32 generation;
 
 	if ((fh_type != FILEID_BTRFS_WITH_PARENT ||
-	     fh_len != BTRFS_FID_SIZE_CONNECTABLE) &&
+	     fh_len < BTRFS_FID_SIZE_CONNECTABLE) &&
 	    (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT ||
-	     fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) &&
+	     fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) &&
 	    (fh_type != FILEID_BTRFS_WITHOUT_PARENT ||
-	     fh_len != BTRFS_FID_SIZE_NON_CONNECTABLE))
+	     fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE))
 		return NULL;
 
 	objectid = fid->objectid;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9f96042..601d7d4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2828,6 +2828,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head;
 	int ret;
 	int run_all = count == (unsigned long)-1;
+	bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
 
 	/* We'll clean this up in btrfs_cleanup_transaction */
 	if (trans->aborted)
@@ -2844,6 +2845,7 @@ again:
 #ifdef SCRAMBLE_DELAYED_REFS
 	delayed_refs->run_delayed_start = find_middle(&delayed_refs->root);
 #endif
+	trans->can_flush_pending_bgs = false;
 	ret = __btrfs_run_delayed_refs(trans, root, count);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, root, ret);
@@ -2893,6 +2895,7 @@ again:
 	}
 out:
 	assert_qgroups_uptodate(trans);
+	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 	return 0;
 }
 
@@ -4306,7 +4309,8 @@ out:
 	 * the block groups that were made dirty during the lifetime of the
 	 * transaction.
 	 */
-	if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
+	if (trans->can_flush_pending_bgs &&
+	    trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
 		btrfs_create_pending_block_groups(trans, trans->root);
 		btrfs_trans_release_chunk_metadata(trans);
 	}
@@ -9560,7 +9564,9 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 	struct btrfs_block_group_item item;
 	struct btrfs_key key;
 	int ret = 0;
+	bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
 
+	trans->can_flush_pending_bgs = false;
 	list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
 		if (ret)
 			goto next;
@@ -9581,6 +9587,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 next:
 		list_del_init(&block_group->bg_list);
 	}
+	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 }
 
 int btrfs_make_block_group(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e2357e3..3915c94 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3132,12 +3132,12 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 					     get_extent_t *get_extent,
 					     struct extent_map **em_cached,
 					     struct bio **bio, int mirror_num,
-					     unsigned long *bio_flags, int rw)
+					     unsigned long *bio_flags, int rw,
+					     u64 *prev_em_start)
 {
 	struct inode *inode;
 	struct btrfs_ordered_extent *ordered;
 	int index;
-	u64 prev_em_start = (u64)-1;
 
 	inode = pages[0]->mapping->host;
 	while (1) {
@@ -3153,7 +3153,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, rw, &prev_em_start);
+			      mirror_num, bio_flags, rw, prev_em_start);
 		page_cache_release(pages[index]);
 	}
 }
@@ -3163,7 +3163,8 @@ static void __extent_readpages(struct extent_io_tree *tree,
 			       int nr_pages, get_extent_t *get_extent,
 			       struct extent_map **em_cached,
 			       struct bio **bio, int mirror_num,
-			       unsigned long *bio_flags, int rw)
+			       unsigned long *bio_flags, int rw,
+			       u64 *prev_em_start)
 {
 	u64 start = 0;
 	u64 end = 0;
@@ -3184,7 +3185,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 						  index - first_index, start,
 						  end, get_extent, em_cached,
 						  bio, mirror_num, bio_flags,
-						  rw);
+						  rw, prev_em_start);
 			start = page_start;
 			end = start + PAGE_CACHE_SIZE - 1;
 			first_index = index;
@@ -3195,7 +3196,8 @@ static void __extent_readpages(struct extent_io_tree *tree,
 		__do_contiguous_readpages(tree, &pages[first_index],
 					  index - first_index, start,
 					  end, get_extent, em_cached, bio,
-					  mirror_num, bio_flags, rw);
+					  mirror_num, bio_flags, rw,
+					  prev_em_start);
 }
 
 static int __extent_read_full_page(struct extent_io_tree *tree,
@@ -4207,6 +4209,7 @@ int extent_readpages(struct extent_io_tree *tree,
 	struct page *page;
 	struct extent_map *em_cached = NULL;
 	int nr = 0;
+	u64 prev_em_start = (u64)-1;
 
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		page = list_entry(pages->prev, struct page, lru);
@@ -4223,12 +4226,12 @@ int extent_readpages(struct extent_io_tree *tree,
 		if (nr < ARRAY_SIZE(pagepool))
 			continue;
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ);
+				   &bio, 0, &bio_flags, READ, &prev_em_start);
 		nr = 0;
 	}
 	if (nr)
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ);
+				   &bio, 0, &bio_flags, READ, &prev_em_start);
 
 	if (em_cached)
 		free_extent_map(em_cached);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0adf542..3e3e613 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4639,6 +4639,11 @@ locked:
 		bctl->flags |= BTRFS_BALANCE_TYPE_MASK;
 	}
 
+	if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) {
+		ret = -EINVAL;
+		goto out_bargs;
+	}
+
 do_balance:
 	/*
 	 * Ownership of bctl and mutually_exclusive_operation_running
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index aa72bfd..a739b82 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1920,10 +1920,12 @@ static int did_overwrite_ref(struct send_ctx *sctx,
 	/*
 	 * We know that it is or will be overwritten. Check this now.
 	 * The current inode being processed might have been the one that caused
-	 * inode 'ino' to be orphanized, therefore ow_inode can actually be the
-	 * same as sctx->send_progress.
+	 * inode 'ino' to be orphanized, therefore check if ow_inode matches
+	 * the current inode being processed.
 	 */
-	if (ow_inode <= sctx->send_progress)
+	if ((ow_inode < sctx->send_progress) ||
+	    (ino != sctx->cur_ino && ow_inode == sctx->cur_ino &&
+	     gen == sctx->cur_inode_gen))
 		ret = 1;
 	else
 		ret = 0;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 74bc333..a5b0644 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -557,6 +557,7 @@ again:
 	h->delayed_ref_elem.seq = 0;
 	h->type = type;
 	h->allocating_chunk = false;
+	h->can_flush_pending_bgs = true;
 	h->reloc_reserved = false;
 	h->sync = false;
 	INIT_LIST_HEAD(&h->qgroup_ref_list);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 87964bf..a994bb0 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -118,6 +118,7 @@ struct btrfs_trans_handle {
 	short aborted;
 	short adding_csums;
 	bool allocating_chunk;
+	bool can_flush_pending_bgs;
 	bool reloc_reserved;
 	bool sync;
 	unsigned int type;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2ca784a..595279a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -376,6 +376,14 @@ struct map_lookup {
 #define BTRFS_BALANCE_ARGS_VRANGE	(1ULL << 4)
 #define BTRFS_BALANCE_ARGS_LIMIT	(1ULL << 5)
 
+#define BTRFS_BALANCE_ARGS_MASK			\
+	(BTRFS_BALANCE_ARGS_PROFILES |		\
+	 BTRFS_BALANCE_ARGS_USAGE |		\
+	 BTRFS_BALANCE_ARGS_DEVID | 		\
+	 BTRFS_BALANCE_ARGS_DRANGE |		\
+	 BTRFS_BALANCE_ARGS_VRANGE |		\
+	 BTRFS_BALANCE_ARGS_LIMIT)
+
 /*
  * Profile changing flags.  When SOFT is set we won't relocate chunk if
  * it already has the target profile (even though it may be
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index e2a6af1..62203c3 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3380,6 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	struct page *page, *tpage;
 	unsigned int expected_index;
 	int rc;
+	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping);
 
 	INIT_LIST_HEAD(tmplist);
 
@@ -3392,7 +3393,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	 */
 	__set_page_locked(page);
 	rc = add_to_page_cache_locked(page, mapping,
-				      page->index, GFP_KERNEL);
+				      page->index, gfp);
 
 	/* give up if we can't stick it in the cache */
 	if (rc) {
@@ -3418,8 +3419,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 			break;
 
 		__set_page_locked(page);
-		if (add_to_page_cache_locked(page, mapping, page->index,
-								GFP_KERNEL)) {
+		if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
 			__clear_page_locked(page);
 			break;
 		}
diff --git a/fs/dax.c b/fs/dax.c
index bcfb14b..a86d3cc 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -285,6 +285,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh,
 static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 			struct vm_area_struct *vma, struct vm_fault *vmf)
 {
+	struct address_space *mapping = inode->i_mapping;
 	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
 	void __pmem *addr;
@@ -292,6 +293,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	pgoff_t size;
 	int error;
 
+	i_mmap_lock_read(mapping);
+
 	/*
 	 * Check truncate didn't happen while we were allocating a block.
 	 * If it did, this block may or may not be still allocated to the
@@ -321,6 +324,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	error = vm_insert_mixed(vma, vaddr, pfn);
 
  out:
+	i_mmap_unlock_read(mapping);
+
 	return error;
 }
 
@@ -382,17 +387,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			 * from a read fault and we've raced with a truncate
 			 */
 			error = -EIO;
-			goto unlock;
+			goto unlock_page;
 		}
-	} else {
-		i_mmap_lock_write(mapping);
 	}
 
 	error = get_block(inode, block, &bh, 0);
 	if (!error && (bh.b_size < PAGE_SIZE))
 		error = -EIO;		/* fs corruption? */
 	if (error)
-		goto unlock;
+		goto unlock_page;
 
 	if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
 		if (vmf->flags & FAULT_FLAG_WRITE) {
@@ -403,9 +406,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			if (!error && (bh.b_size < PAGE_SIZE))
 				error = -EIO;
 			if (error)
-				goto unlock;
+				goto unlock_page;
 		} else {
-			i_mmap_unlock_write(mapping);
 			return dax_load_hole(mapping, page, vmf);
 		}
 	}
@@ -417,15 +419,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		else
 			clear_user_highpage(new_page, vaddr);
 		if (error)
-			goto unlock;
+			goto unlock_page;
 		vmf->page = page;
 		if (!page) {
+			i_mmap_lock_read(mapping);
 			/* Check we didn't race with truncate */
 			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
 								PAGE_SHIFT;
 			if (vmf->pgoff >= size) {
+				i_mmap_unlock_read(mapping);
 				error = -EIO;
-				goto unlock;
+				goto out;
 			}
 		}
 		return VM_FAULT_LOCKED;
@@ -461,8 +465,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
 	}
 
-	if (!page)
-		i_mmap_unlock_write(mapping);
  out:
 	if (error == -ENOMEM)
 		return VM_FAULT_OOM | major;
@@ -471,14 +473,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		return VM_FAULT_SIGBUS | major;
 	return VM_FAULT_NOPAGE | major;
 
- unlock:
+ unlock_page:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
-	} else {
-		i_mmap_unlock_write(mapping);
 	}
-
 	goto out;
 }
 EXPORT_SYMBOL(__dax_fault);
@@ -556,10 +555,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
 
 	bh.b_size = PMD_SIZE;
-	i_mmap_lock_write(mapping);
 	length = get_block(inode, block, &bh, write);
 	if (length)
 		return VM_FAULT_SIGBUS;
+	i_mmap_lock_read(mapping);
 
 	/*
 	 * If the filesystem isn't willing to tell us the length of a hole,
@@ -569,36 +568,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
-	sector = bh.b_blocknr << (blkbits - 9);
-
-	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-		int i;
-
-		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
-						bh.b_size);
-		if (length < 0) {
-			result = VM_FAULT_SIGBUS;
-			goto out;
-		}
-		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
-			goto fallback;
-
-		for (i = 0; i < PTRS_PER_PMD; i++)
-			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
-		wmb_pmem();
-		count_vm_event(PGMAJFAULT);
-		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
-		result |= VM_FAULT_MAJOR;
-	}
-
 	/*
 	 * If we allocated new storage, make sure no process has any
 	 * zero pages covering this hole
 	 */
 	if (buffer_new(&bh)) {
-		i_mmap_unlock_write(mapping);
+		i_mmap_unlock_read(mapping);
 		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
-		i_mmap_lock_write(mapping);
+		i_mmap_lock_read(mapping);
 	}
 
 	/*
@@ -635,6 +612,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		result = VM_FAULT_NOPAGE;
 		spin_unlock(ptl);
 	} else {
+		sector = bh.b_blocknr << (blkbits - 9);
 		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
 						bh.b_size);
 		if (length < 0) {
@@ -644,15 +622,25 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
 			goto fallback;
 
+		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+			int i;
+			for (i = 0; i < PTRS_PER_PMD; i++)
+				clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
+			wmb_pmem();
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			result |= VM_FAULT_MAJOR;
+		}
+
 		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
 	}
 
  out:
+	i_mmap_unlock_read(mapping);
+
 	if (buffer_unwritten(&bh))
 		complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
 
-	i_mmap_unlock_write(mapping);
-
 	return result;
 
  fallback:
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 47728da..b46e9fc 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -63,7 +63,7 @@ config EXT4_FS
 	  If unsure, say N.
 
 config EXT4_USE_FOR_EXT2
-	bool "Use ext4 for ext2/ext3 file systems"
+	bool "Use ext4 for ext2 file systems"
 	depends on EXT4_FS
 	depends on EXT2_FS=n
 	default y
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index e26803f..560af04 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -165,8 +165,8 @@ int ext4_mpage_readpages(struct address_space *mapping,
 		if (pages) {
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
-			if (add_to_page_cache_lru(page, mapping,
-						  page->index, GFP_KERNEL))
+			if (add_to_page_cache_lru(page, mapping, page->index,
+					GFP_KERNEL & mapping_gfp_mask(mapping)))
 				goto next_page;
 		}
 
diff --git a/fs/mpage.c b/fs/mpage.c
index 778a4dd..a7c3427 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -139,7 +139,8 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
 static struct bio *
 do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
 		sector_t *last_block_in_bio, struct buffer_head *map_bh,
-		unsigned long *first_logical_block, get_block_t get_block)
+		unsigned long *first_logical_block, get_block_t get_block,
+		gfp_t gfp)
 {
 	struct inode *inode = page->mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
@@ -277,8 +278,7 @@ alloc_new:
 				goto out;
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-				min_t(int, nr_pages, BIO_MAX_PAGES),
-				GFP_KERNEL);
+				min_t(int, nr_pages, BIO_MAX_PAGES), gfp);
 		if (bio == NULL)
 			goto confused;
 	}
@@ -361,6 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
+	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
@@ -370,12 +371,13 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 		prefetchw(&page->flags);
 		list_del(&page->lru);
 		if (!add_to_page_cache_lru(page, mapping,
-					page->index, GFP_KERNEL)) {
+					page->index,
+					gfp)) {
 			bio = do_mpage_readpage(bio, page,
 					nr_pages - page_idx,
 					&last_block_in_bio, &map_bh,
 					&first_logical_block,
-					get_block);
+					get_block, gfp);
 		}
 		page_cache_release(page);
 	}
@@ -395,11 +397,12 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
+	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
 	bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
-			&map_bh, &first_logical_block, get_block);
+			&map_bh, &first_logical_block, get_block, gfp);
 	if (bio)
 		mpage_bio_submit(READ, bio);
 	return 0;
diff --git a/fs/namei.c b/fs/namei.c
index 726d211..33e9495 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1558,8 +1558,6 @@ static int lookup_fast(struct nameidata *nd,
 		negative = d_is_negative(dentry);
 		if (read_seqcount_retry(&dentry->d_seq, seq))
 			return -ECHILD;
-		if (negative)
-			return -ENOENT;
 
 		/*
 		 * This sequence count validates that the parent had no
@@ -1580,6 +1578,12 @@ static int lookup_fast(struct nameidata *nd,
 				goto unlazy;
 			}
 		}
+		/*
+		 * Note: do negative dentry check after revalidation in
+		 * case that drops it.
+		 */
+		if (negative)
+			return -ENOENT;
 		path->mnt = mnt;
 		path->dentry = dentry;
 		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 75f7c0a..a7f2e6e 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -99,17 +99,6 @@ nfs4_callback_up(struct svc_serv *serv)
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
-{
-	/*
-	 * Create an svc_sock for the back channel service that shares the
-	 * fore channel connection.
-	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
-	 */
-	return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0,
-			      SVC_SOCK_ANONYMOUS);
-}
-
 /*
  * The callback service for NFSv4.1 callbacks
  */
@@ -184,11 +173,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
 		xprt->bc_serv = serv;
 }
 #else
-static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
-{
-	return 0;
-}
-
 static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv,
 		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
 {
@@ -259,7 +243,8 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc
 	svc_shutdown_net(serv, net);
 }
 
-static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net)
+static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
+			       struct net *net, struct rpc_xprt *xprt)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	int ret;
@@ -275,20 +260,11 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct n
 		goto err_bind;
 	}
 
-	switch (minorversion) {
-		case 0:
-			ret = nfs4_callback_up_net(serv, net);
-			break;
-		case 1:
-		case 2:
-			ret = nfs41_callback_up_net(serv, net);
-			break;
-		default:
-			printk(KERN_ERR "NFS: unknown callback version: %d\n",
-					minorversion);
-			ret = -EINVAL;
-			break;
-	}
+	ret = -EPROTONOSUPPORT;
+	if (minorversion == 0)
+		ret = nfs4_callback_up_net(serv, net);
+	else if (xprt->ops->bc_up)
+		ret = xprt->ops->bc_up(serv, net);
 
 	if (ret < 0) {
 		printk(KERN_ERR "NFS: callback service start failed\n");
@@ -364,7 +340,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		goto err_create;
 	}
 
-	ret = nfs_callback_up_net(minorversion, serv, net);
+	ret = nfs_callback_up_net(minorversion, serv, net, xprt);
 	if (ret < 0)
 		goto err_net;
 
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index cdefaa3..c29d942 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -56,14 +56,6 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 	u32 device_generation = 0;
 	int error;
 
-	/*
-	 * We do not attempt to support I/O smaller than the fs block size,
-	 * or not aligned to it.
-	 */
-	if (args->lg_minlength < block_size) {
-		dprintk("pnfsd: I/O too small\n");
-		goto out_layoutunavailable;
-	}
 	if (seg->offset & (block_size - 1)) {
 		dprintk("pnfsd: I/O misaligned\n");
 		goto out_layoutunavailable;
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index ba1323a..a586467 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -70,6 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 	unsigned order;
 	void *data;
 	int ret;
+	gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
 
 	/* make various checks */
 	order = get_order(newsize);
@@ -84,7 +85,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 
 	/* allocate enough contiguous pages to be able to satisfy the
 	 * request */
-	pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order);
+	pages = alloc_pages(gfp, order);
 	if (!pages)
 		return -ENOMEM;
 
@@ -108,7 +109,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 		struct page *page = pages + loop;
 
 		ret = add_to_page_cache_lru(page, inode->i_mapping, loop,
-					GFP_KERNEL);
+					gfp);
 		if (ret < 0)
 			goto add_error;