Merge tag 'v3.13-rc6' into for-3.14/core

Needed to bring blk-mq uptodate, since changes have been going in since for-3.14/core was established. Fixup merge issues related to the immutable biovec changes. Signed-off-by: Jens Axboe <axboe@kernel.dk> Conflicts: block/blk-flush.c fs/btrfs/check-integrity.c fs/btrfs/extent_io.c fs/btrfs/scrub.c fs/logfs/dev_bdev.c
author: Jens Axboe <axboe@kernel.dk> 2013-12-31 09:51:02 -0700
committer: Jens Axboe <axboe@kernel.dk> 2013-12-31 09:51:02 -0700
commit: b28bc9b38c52f63f43e3fd875af982f2240a2859 (patch)
tree: 76cdb7b52b58f5685993cc15ed81d1c903023358 /fs
parent: 8d30726912cb39c3a3ebde06214d54861f8fdde2 (diff)
parent: 802eee95bde72fd0cd0f3a5b2098375a487d1eda (diff)
download: linux-b28bc9b38c52f63f43e3fd875af982f2240a2859.tar.bz2
62 files changed, 909 insertions, 425 deletions
diff --git a/fs/affs/Changes b/fs/affs/Changes
index a29409c1ffe0..b41c2c9792ff 100644
--- a/fs/affs/Changes
+++ b/fs/affs/Changes
@@ -91,7 +91,7 @@ more 2.4 fixes: [Roman Zippel]
 Version 3.11
 ------------
 
-- Converted to use 2.3.x page cache [Dave Jones <dave@powertweak.com>]
+- Converted to use 2.3.x page cache [Dave Jones]
 - Corruption in truncate() bugfix [Ken Tyler <kent@werple.net.au>]
 
 Version 3.10
diff --git a/fs/aio.c b/fs/aio.c
index 08159ed13649..062a5f6a1448 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -244,9 +244,14 @@ static void aio_free_ring(struct kioctx *ctx)
 	int i;
 
 	for (i = 0; i < ctx->nr_pages; i++) {
+		struct page *page;
 		pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
 				page_count(ctx->ring_pages[i]));
-		put_page(ctx->ring_pages[i]);
+		page = ctx->ring_pages[i];
+		if (!page)
+			continue;
+		ctx->ring_pages[i] = NULL;
+		put_page(page);
 	}
 
 	put_aio_ring_file(ctx);
@@ -280,18 +285,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 	unsigned long flags;
 	int rc;
 
+	rc = 0;
+
+	/* Make sure the old page hasn't already been changed */
+	spin_lock(&mapping->private_lock);
+	ctx = mapping->private_data;
+	if (ctx) {
+		pgoff_t idx;
+		spin_lock_irqsave(&ctx->completion_lock, flags);
+		idx = old->index;
+		if (idx < (pgoff_t)ctx->nr_pages) {
+			if (ctx->ring_pages[idx] != old)
+				rc = -EAGAIN;
+		} else
+			rc = -EINVAL;
+		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	} else
+		rc = -EINVAL;
+	spin_unlock(&mapping->private_lock);
+
+	if (rc != 0)
+		return rc;
+
 	/* Writeback must be complete */
 	BUG_ON(PageWriteback(old));
-	put_page(old);
+	get_page(new);
 
-	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode);
+	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
 	if (rc != MIGRATEPAGE_SUCCESS) {
-		get_page(old);
+		put_page(new);
 		return rc;
 	}
 
-	get_page(new);
-
 	/* We can potentially race against kioctx teardown here.  Use the
 	 * address_space's private data lock to protect the mapping's
 	 * private_data.
@@ -303,13 +328,24 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 		spin_lock_irqsave(&ctx->completion_lock, flags);
 		migrate_page_copy(new, old);
 		idx = old->index;
-		if (idx < (pgoff_t)ctx->nr_pages)
-			ctx->ring_pages[idx] = new;
+		if (idx < (pgoff_t)ctx->nr_pages) {
+			/* And only do the move if things haven't changed */
+			if (ctx->ring_pages[idx] == old)
+				ctx->ring_pages[idx] = new;
+			else
+				rc = -EAGAIN;
+		} else
+			rc = -EINVAL;
 		spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	} else
 		rc = -EBUSY;
 	spin_unlock(&mapping->private_lock);
 
+	if (rc == MIGRATEPAGE_SUCCESS)
+		put_page(old);
+	else
+		put_page(new);
+
 	return rc;
 }
 #endif
@@ -326,7 +362,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	struct aio_ring *ring;
 	unsigned nr_events = ctx->max_reqs;
 	struct mm_struct *mm = current->mm;
-	unsigned long size, populate;
+	unsigned long size, unused;
 	int nr_pages;
 	int i;
 	struct file *file;
@@ -347,6 +383,20 @@ static int aio_setup_ring(struct kioctx *ctx)
 		return -EAGAIN;
 	}
 
+	ctx->aio_ring_file = file;
+	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
+			/ sizeof(struct io_event);
+
+	ctx->ring_pages = ctx->internal_pages;
+	if (nr_pages > AIO_RING_PAGES) {
+		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+					  GFP_KERNEL);
+		if (!ctx->ring_pages) {
+			put_aio_ring_file(ctx);
+			return -ENOMEM;
+		}
+	}
+
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
 		page = find_or_create_page(file->f_inode->i_mapping,
@@ -358,17 +408,14 @@ static int aio_setup_ring(struct kioctx *ctx)
 		SetPageUptodate(page);
 		SetPageDirty(page);
 		unlock_page(page);
+
+		ctx->ring_pages[i] = page;
 	}
-	ctx->aio_ring_file = file;
-	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
-			/ sizeof(struct io_event);
+	ctx->nr_pages = i;
 
-	ctx->ring_pages = ctx->internal_pages;
-	if (nr_pages > AIO_RING_PAGES) {
-		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
-					  GFP_KERNEL);
-		if (!ctx->ring_pages)
-			return -ENOMEM;
+	if (unlikely(i != nr_pages)) {
+		aio_free_ring(ctx);
+		return -EAGAIN;
 	}
 
 	ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -377,9 +424,9 @@ static int aio_setup_ring(struct kioctx *ctx)
 	down_write(&mm->mmap_sem);
 	ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
 				       PROT_READ | PROT_WRITE,
-				       MAP_SHARED | MAP_POPULATE, 0, &populate);
+				       MAP_SHARED, 0, &unused);
+	up_write(&mm->mmap_sem);
 	if (IS_ERR((void *)ctx->mmap_base)) {
-		up_write(&mm->mmap_sem);
 		ctx->mmap_size = 0;
 		aio_free_ring(ctx);
 		return -EAGAIN;
@@ -387,27 +434,6 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
 
-	/* We must do this while still holding mmap_sem for write, as we
-	 * need to be protected against userspace attempting to mremap()
-	 * or munmap() the ring buffer.
-	 */
-	ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
-				       1, 0, ctx->ring_pages, NULL);
-
-	/* Dropping the reference here is safe as the page cache will hold
-	 * onto the pages for us.  It is also required so that page migration
-	 * can unmap the pages and get the right reference count.
-	 */
-	for (i = 0; i < ctx->nr_pages; i++)
-		put_page(ctx->ring_pages[i]);
-
-	up_write(&mm->mmap_sem);
-
-	if (unlikely(ctx->nr_pages != nr_pages)) {
-		aio_free_ring(ctx);
-		return -EAGAIN;
-	}
-
 	ctx->user_id = ctx->mmap_base;
 	ctx->nr_events = nr_events; /* trusted copy */
 
@@ -645,12 +671,13 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	    aio_nr + nr_events < aio_nr) {
 		spin_unlock(&aio_nr_lock);
 		err = -EAGAIN;
-		goto err;
+		goto err_ctx;
 	}
 	aio_nr += ctx->max_reqs;
 	spin_unlock(&aio_nr_lock);
 
-	percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+	percpu_ref_get(&ctx->users);	/* io_setup() will drop this ref */
+	percpu_ref_get(&ctx->reqs);	/* free_ioctx_users() will drop this */
 
 	err = ioctx_add_table(ctx, mm);
 	if (err)
@@ -662,6 +689,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 err_cleanup:
 	aio_nr_sub(ctx->max_reqs);
+err_ctx:
+	aio_free_ring(ctx);
 err:
 	free_percpu(ctx->cpu);
 	free_percpu(ctx->reqs.pcpu_count);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 45d98d01028f..9c01509dd8ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -767,20 +767,19 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	if (metadata) {
-		key.objectid = bytenr;
-		key.type = BTRFS_METADATA_ITEM_KEY;
-		key.offset = offset;
-	} else {
-		key.objectid = bytenr;
-		key.type = BTRFS_EXTENT_ITEM_KEY;
-		key.offset = offset;
-	}
-
 	if (!trans) {
 		path->skip_locking = 1;
 		path->search_commit_root = 1;
 	}
+
+search_again:
+	key.objectid = bytenr;
+	key.offset = offset;
+	if (metadata)
+		key.type = BTRFS_METADATA_ITEM_KEY;
+	else
+		key.type = BTRFS_EXTENT_ITEM_KEY;
+
 again:
 	ret = btrfs_search_slot(trans, root->fs_info->extent_root,
 				&key, path, 0, 0);
@@ -788,7 +787,6 @@ again:
 		goto out_free;
 
 	if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) {
-		metadata = 0;
 		if (path->slots[0]) {
 			path->slots[0]--;
 			btrfs_item_key_to_cpu(path->nodes[0], &key,
@@ -855,7 +853,7 @@ again:
 			mutex_lock(&head->mutex);
 			mutex_unlock(&head->mutex);
 			btrfs_put_delayed_ref(&head->node);
-			goto again;
+			goto search_again;
 		}
 		if (head->extent_op && head->extent_op->update_flags)
 			extent_flags |= head->extent_op->flags_to_set;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a111622598b0..21da5762b0b1 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2121,7 +2121,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 
 	err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	if (err == -EINTR)
-		goto out;
+		goto out_drop_write;
 	dentry = lookup_one_len(vol_args->name, parent, namelen);
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
@@ -2284,6 +2284,7 @@ out_dput:
 	dput(dentry);
 out_unlock_dir:
 	mutex_unlock(&dir->i_mutex);
+out_drop_write:
 	mnt_drop_write_file(file);
 out:
 	kfree(vol_args);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ce459a7cb16d..429c73c374b8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -571,7 +571,9 @@ static int is_cowonly_root(u64 root_objectid)
 	    root_objectid == BTRFS_CHUNK_TREE_OBJECTID ||
 	    root_objectid == BTRFS_DEV_TREE_OBJECTID ||
 	    root_objectid == BTRFS_TREE_LOG_OBJECTID ||
-	    root_objectid == BTRFS_CSUM_TREE_OBJECTID)
+	    root_objectid == BTRFS_CSUM_TREE_OBJECTID ||
+	    root_objectid == BTRFS_UUID_TREE_OBJECTID ||
+	    root_objectid == BTRFS_QUOTA_TREE_OBJECTID)
 		return 1;
 	return 0;
 }
@@ -1264,10 +1266,10 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
 }
 
 /*
- * helper to update/delete the 'address of tree root -> reloc tree'
+ * helper to delete the 'address of tree root -> reloc tree'
  * mapping
  */
-static int __update_reloc_root(struct btrfs_root *root, int del)
+static void __del_reloc_root(struct btrfs_root *root)
 {
 	struct rb_node *rb_node;
 	struct mapping_node *node = NULL;
@@ -1275,7 +1277,7 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
 
 	spin_lock(&rc->reloc_root_tree.lock);
 	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-			      root->commit_root->start);
+			      root->node->start);
 	if (rb_node) {
 		node = rb_entry(rb_node, struct mapping_node, rb_node);
 		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
@@ -1283,23 +1285,45 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
 	spin_unlock(&rc->reloc_root_tree.lock);
 
 	if (!node)
-		return 0;
+		return;
 	BUG_ON((struct btrfs_root *)node->data != root);
 
-	if (!del) {
-		spin_lock(&rc->reloc_root_tree.lock);
-		node->bytenr = root->node->start;
-		rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
-				      node->bytenr, &node->rb_node);
-		spin_unlock(&rc->reloc_root_tree.lock);
-		if (rb_node)
-			backref_tree_panic(rb_node, -EEXIST, node->bytenr);
-	} else {
-		spin_lock(&root->fs_info->trans_lock);
-		list_del_init(&root->root_list);
-		spin_unlock(&root->fs_info->trans_lock);
-		kfree(node);
+	spin_lock(&root->fs_info->trans_lock);
+	list_del_init(&root->root_list);
+	spin_unlock(&root->fs_info->trans_lock);
+	kfree(node);
+}
+
+/*
+ * helper to update the 'address of tree root -> reloc tree'
+ * mapping
+ */
+static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr)
+{
+	struct rb_node *rb_node;
+	struct mapping_node *node = NULL;
+	struct reloc_control *rc = root->fs_info->reloc_ctl;
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+			      root->node->start);
+	if (rb_node) {
+		node = rb_entry(rb_node, struct mapping_node, rb_node);
+		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
 	}
+	spin_unlock(&rc->reloc_root_tree.lock);
+
+	if (!node)
+		return 0;
+	BUG_ON((struct btrfs_root *)node->data != root);
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	node->bytenr = new_bytenr;
+	rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
+			      node->bytenr, &node->rb_node);
+	spin_unlock(&rc->reloc_root_tree.lock);
+	if (rb_node)
+		backref_tree_panic(rb_node, -EEXIST, node->bytenr);
 	return 0;
 }
 
@@ -1420,7 +1444,6 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_root *reloc_root;
 	struct btrfs_root_item *root_item;
-	int del = 0;
 	int ret;
 
 	if (!root->reloc_root)
@@ -1432,11 +1455,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 	if (root->fs_info->reloc_ctl->merge_reloc_tree &&
 	    btrfs_root_refs(root_item) == 0) {
 		root->reloc_root = NULL;
-		del = 1;
+		__del_reloc_root(reloc_root);
 	}
 
-	__update_reloc_root(reloc_root, del);
-
 	if (reloc_root->commit_root != reloc_root->node) {
 		btrfs_set_root_node(root_item, reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
@@ -2287,7 +2308,7 @@ void free_reloc_roots(struct list_head *list)
 	while (!list_empty(list)) {
 		reloc_root = list_entry(list->next, struct btrfs_root,
 					root_list);
-		__update_reloc_root(reloc_root, 1);
+		__del_reloc_root(reloc_root);
 		free_extent_buffer(reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
 		kfree(reloc_root);
@@ -2332,7 +2353,7 @@ again:
 
 			ret = merge_reloc_root(rc, root);
 			if (ret) {
-				__update_reloc_root(reloc_root, 1);
+				__del_reloc_root(reloc_root);
 				free_extent_buffer(reloc_root->node);
 				free_extent_buffer(reloc_root->commit_root);
 				kfree(reloc_root);
@@ -2388,6 +2409,13 @@ out:
 		btrfs_std_error(root->fs_info, ret);
 		if (!list_empty(&reloc_roots))
 			free_reloc_roots(&reloc_roots);
+
+		/* new reloc root may be added */
+		mutex_lock(&root->fs_info->reloc_mutex);
+		list_splice_init(&rc->reloc_roots, &reloc_roots);
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		if (!list_empty(&reloc_roots))
+			free_reloc_roots(&reloc_roots);
 	}
 
 	BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
@@ -4522,6 +4550,11 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 	BUG_ON(rc->stage == UPDATE_DATA_PTRS &&
 	       root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID);
 
+	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+		if (buf == root->node)
+			__update_reloc_root(root, cow->start);
+	}
+
 	level = btrfs_header_level(buf);
 	if (btrfs_header_generation(buf) <=
 	    btrfs_root_last_snapshot(&root->root_item))
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 6837fe87f3a6..945d1db98f26 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4723,8 +4723,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	}
 
 	if (!access_ok(VERIFY_READ, arg->clone_sources,
-			sizeof(*arg->clone_sources *
-			arg->clone_sources_count))) {
+			sizeof(*arg->clone_sources) *
+			arg->clone_sources_count)) {
 		ret = -EFAULT;
 		goto out;
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2d8ac1bf0cf9..d71a11d13dfa 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -432,7 +432,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			} else {
 				printk(KERN_INFO "btrfs: setting nodatacow\n");
 			}
-			info->compress_type = BTRFS_COMPRESS_NONE;
 			btrfs_clear_opt(info->mount_opt, COMPRESS);
 			btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			btrfs_set_opt(info->mount_opt, NODATACOW);
@@ -461,7 +460,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_fs_incompat(info, COMPRESS_LZO);
 			} else if (strncmp(args[0].from, "no", 2) == 0) {
 				compress_type = "no";
-				info->compress_type = BTRFS_COMPRESS_NONE;
 				btrfs_clear_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 				compress_force = false;
@@ -474,9 +472,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
 				pr_info("btrfs: force %s compression\n",
 					compress_type);
-			} else
+			} else if (btrfs_test_opt(root, COMPRESS)) {
 				pr_info("btrfs: use %s compression\n",
 					compress_type);
+			}
 			break;
 		case Opt_ssd:
 			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 6df8bd481425..ec3ba43b9faa 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,13 +210,17 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	if (err < 0) {
 		SetPageError(page);
 		goto out;
-	} else if (err < PAGE_CACHE_SIZE) {
+	} else {
+		if (err < PAGE_CACHE_SIZE) {
 		/* zero fill remainder of page */
-		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+			zero_user_segment(page, err, PAGE_CACHE_SIZE);
+		} else {
+			flush_dcache_page(page);
+		}
 	}
 	SetPageUptodate(page);
 
-	if (err == 0)
+	if (err >= 0)
 		ceph_readpage_to_fscache(inode, page);
 
 out:
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 7db2e6ca4b8f..8c44fdd4e1c3 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -324,6 +324,9 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	if (!PageFsCache(page))
+		return;
+
 	fscache_wait_on_page_write(ci->fscache, page);
 	fscache_uncache_page(ci->fscache, page);
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 13976c33332e..3c0a4bd74996 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -897,7 +897,7 @@ static int __ceph_is_any_caps(struct ceph_inode_info *ci)
  * caller should hold i_ceph_lock.
  * caller will not hold session s_mutex if called from destroy_inode.
  */
-void __ceph_remove_cap(struct ceph_cap *cap)
+void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 {
 	struct ceph_mds_session *session = cap->session;
 	struct ceph_inode_info *ci = cap->ci;
@@ -909,6 +909,16 @@ void __ceph_remove_cap(struct ceph_cap *cap)
 
 	/* remove from session list */
 	spin_lock(&session->s_cap_lock);
+	/*
+	 * s_cap_reconnect is protected by s_cap_lock. no one changes
+	 * s_cap_gen while session is in the reconnect state.
+	 */
+	if (queue_release &&
+	    (!session->s_cap_reconnect ||
+	     cap->cap_gen == session->s_cap_gen))
+		__queue_cap_release(session, ci->i_vino.ino, cap->cap_id,
+				    cap->mseq, cap->issue_seq);
+
 	if (session->s_cap_iterator == cap) {
 		/* not yet, we are iterating over this very cap */
 		dout("__ceph_remove_cap  delaying %p removal from session %p\n",
@@ -1023,7 +1033,6 @@ void __queue_cap_release(struct ceph_mds_session *session,
 	struct ceph_mds_cap_release *head;
 	struct ceph_mds_cap_item *item;
 
-	spin_lock(&session->s_cap_lock);
 	BUG_ON(!session->s_num_cap_releases);
 	msg = list_first_entry(&session->s_cap_releases,
 			       struct ceph_msg, list_head);
@@ -1052,7 +1061,6 @@ void __queue_cap_release(struct ceph_mds_session *session,
 		     (int)CEPH_CAPS_PER_RELEASE,
 		     (int)msg->front.iov_len);
 	}
-	spin_unlock(&session->s_cap_lock);
 }
 
 /*
@@ -1067,12 +1075,8 @@ void ceph_queue_caps_release(struct inode *inode)
 	p = rb_first(&ci->i_caps);
 	while (p) {
 		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
-		struct ceph_mds_session *session = cap->session;
-
-		__queue_cap_release(session, ceph_ino(inode), cap->cap_id,
-				    cap->mseq, cap->issue_seq);
 		p = rb_next(p);
-		__ceph_remove_cap(cap);
+		__ceph_remove_cap(cap, true);
 	}
 }
 
@@ -2791,7 +2795,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
 			}
 			spin_unlock(&mdsc->cap_dirty_lock);
 		}
-		__ceph_remove_cap(cap);
+		__ceph_remove_cap(cap, false);
 	}
 	/* else, we already released it */
 
@@ -2931,9 +2935,12 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	if (!inode) {
 		dout(" i don't have ino %llx\n", vino.ino);
 
-		if (op == CEPH_CAP_OP_IMPORT)
+		if (op == CEPH_CAP_OP_IMPORT) {
+			spin_lock(&session->s_cap_lock);
 			__queue_cap_release(session, vino.ino, cap_id,
 					    mseq, seq);
+			spin_unlock(&session->s_cap_lock);
+		}
 		goto flush_cap_releases;
 	}
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 868b61d56cac..2a0bcaeb189a 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -352,8 +352,18 @@ more:
 		}
 
 		/* note next offset and last dentry name */
+		rinfo = &req->r_reply_info;
+		if (le32_to_cpu(rinfo->dir_dir->frag) != frag) {
+			frag = le32_to_cpu(rinfo->dir_dir->frag);
+			if (ceph_frag_is_leftmost(frag))
+				fi->next_offset = 2;
+			else
+				fi->next_offset = 0;
+			off = fi->next_offset;
+		}
 		fi->offset = fi->next_offset;
 		fi->last_readdir = req;
+		fi->frag = frag;
 
 		if (req->r_reply_info.dir_end) {
 			kfree(fi->last_name);
@@ -363,7 +373,6 @@ more:
 			else
 				fi->next_offset = 0;
 		} else {
-			rinfo = &req->r_reply_info;
 			err = note_last_dentry(fi,
 				       rinfo->dir_dname[rinfo->dir_nr-1],
 				       rinfo->dir_dname_len[rinfo->dir_nr-1]);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8549a48115f7..278fd2891288 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -577,6 +577,8 @@ static int fill_inode(struct inode *inode,
 	int issued = 0, implemented;
 	struct timespec mtime, atime, ctime;
 	u32 nsplits;
+	struct ceph_inode_frag *frag;
+	struct rb_node *rb_node;
 	struct ceph_buffer *xattr_blob = NULL;
 	int err = 0;
 	int queue_trunc = 0;
@@ -751,15 +753,38 @@ no_change:
 	/* FIXME: move me up, if/when version reflects fragtree changes */
 	nsplits = le32_to_cpu(info->fragtree.nsplits);
 	mutex_lock(&ci->i_fragtree_mutex);
+	rb_node = rb_first(&ci->i_fragtree);
 	for (i = 0; i < nsplits; i++) {
 		u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
-		struct ceph_inode_frag *frag = __get_or_create_frag(ci, id);
-
-		if (IS_ERR(frag))
-			continue;
+		frag = NULL;
+		while (rb_node) {
+			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+			if (ceph_frag_compare(frag->frag, id) >= 0) {
+				if (frag->frag != id)
+					frag = NULL;
+				else
+					rb_node = rb_next(rb_node);
+				break;
+			}
+			rb_node = rb_next(rb_node);
+			rb_erase(&frag->node, &ci->i_fragtree);
+			kfree(frag);
+			frag = NULL;
+		}
+		if (!frag) {
+			frag = __get_or_create_frag(ci, id);
+			if (IS_ERR(frag))
+				continue;
+		}
 		frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
 		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
 	}
+	while (rb_node) {
+		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+		rb_node = rb_next(rb_node);
+		rb_erase(&frag->node, &ci->i_fragtree);
+		kfree(frag);
+	}
 	mutex_unlock(&ci->i_fragtree_mutex);
 
 	/* were we issued a capability? */
@@ -953,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
-	int i = 0;
 	int err = 0;
 
 	dout("fill_trace %p is_dentry %d is_target %d\n", req,
@@ -1014,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		}
 	}
 
+	if (rinfo->head->is_target) {
+		vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+		vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+
+		in = ceph_get_inode(sb, vino);
+		if (IS_ERR(in)) {
+			err = PTR_ERR(in);
+			goto done;
+		}
+		req->r_target_inode = in;
+
+		err = fill_inode(in, &rinfo->targeti, NULL,
+				session, req->r_request_started,
+				(le32_to_cpu(rinfo->head->result) == 0) ?
+				req->r_fmode : -1,
+				&req->r_caps_reservation);
+		if (err < 0) {
+			pr_err("fill_inode badness %p %llx.%llx\n",
+				in, ceph_vinop(in));
+			goto done;
+		}
+	}
+
 	/*
 	 * ignore null lease/binding on snapdir ENOENT, or else we
 	 * will have trouble splicing in the virtual snapdir later
@@ -1083,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			     ceph_dentry(req->r_old_dentry)->offset);
 
 			dn = req->r_old_dentry;  /* use old_dentry */
-			in = dn->d_inode;
 		}
 
 		/* null dentry? */
@@ -1105,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		}
 
 		/* attach proper inode */
-		ininfo = rinfo->targeti.in;
-		vino.ino = le64_to_cpu(ininfo->ino);
-		vino.snap = le64_to_cpu(ininfo->snapid);
-		in = dn->d_inode;
-		if (!in) {
-			in = ceph_get_inode(sb, vino);
-			if (IS_ERR(in)) {
-				pr_err("fill_trace bad get_inode "
-				       "%llx.%llx\n", vino.ino, vino.snap);
-				err = PTR_ERR(in);
-				d_drop(dn);
-				goto done;
-			}
+		if (!dn->d_inode) {
+			ihold(in);
 			dn = splice_dentry(dn, in, &have_lease, true);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
 			}
 			req->r_dentry = dn;  /* may have spliced */
-			ihold(in);
-		} else if (ceph_ino(in) == vino.ino &&
-			   ceph_snap(in) == vino.snap) {
-			ihold(in);
-		} else {
+		} else if (dn->d_inode && dn->d_inode != in) {
 			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
-			     dn, in, ceph_ino(in), ceph_snap(in),
-			     vino.ino, vino.snap);
+			     dn, dn->d_inode, ceph_vinop(dn->d_inode),
+			     ceph_vinop(in));
 			have_lease = false;
-			in = NULL;
 		}
 
 		if (have_lease)
 			update_dentry_lease(dn, rinfo->dlease, session,
 					    req->r_request_started);
 		dout(" final dn %p\n", dn);
-		i++;
-	} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
-		   req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
+	} else if (!req->r_aborted &&
+		   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+		    req->r_op == CEPH_MDS_OP_MKSNAP)) {
 		struct dentry *dn = req->r_dentry;
 
 		/* fill out a snapdir LOOKUPSNAP dentry */
@@ -1152,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		ininfo = rinfo->targeti.in;
 		vino.ino = le64_to_cpu(ininfo->ino);
 		vino.snap = le64_to_cpu(ininfo->snapid);
-		in = ceph_get_inode(sb, vino);
-		if (IS_ERR(in)) {
-			pr_err("fill_inode get_inode badness %llx.%llx\n",
-			       vino.ino, vino.snap);
-			err = PTR_ERR(in);
-			d_delete(dn);
-			goto done;
-		}
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
+		ihold(in);
 		dn = splice_dentry(dn, in, NULL, true);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
 		}
 		req->r_dentry = dn;  /* may have spliced */
-		ihold(in);
-		rinfo->head->is_dentry = 1;  /* fool notrace handlers */
-	}
-
-	if (rinfo->head->is_target) {
-		vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-		vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
-		if (in == NULL || ceph_ino(in) != vino.ino ||
-		    ceph_snap(in) != vino.snap) {
-			in = ceph_get_inode(sb, vino);
-			if (IS_ERR(in)) {
-				err = PTR_ERR(in);
-				goto done;
-			}
-		}
-		req->r_target_inode = in;
-
-		err = fill_inode(in,
-				 &rinfo->targeti, NULL,
-				 session, req->r_request_started,
-				 (le32_to_cpu(rinfo->head->result) == 0) ?
-				 req->r_fmode : -1,
-				 &req->r_caps_reservation);
-		if (err < 0) {
-			pr_err("fill_inode badness %p %llx.%llx\n",
-			       in, ceph_vinop(in));
-			goto done;
-		}
 	}
-
 done:
 	dout("fill_trace done err=%d\n", err);
 	return err;
@@ -1247,11 +1240,23 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	struct qstr dname;
 	struct dentry *dn;
 	struct inode *in;
-	int err = 0, i;
+	int err = 0, ret, i;
 	struct inode *snapdir = NULL;
 	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
-	u64 frag = le32_to_cpu(rhead->args.readdir.frag);
 	struct ceph_dentry_info *di;
+	u64 r_readdir_offset = req->r_readdir_offset;
+	u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+
+	if (rinfo->dir_dir &&
+	    le32_to_cpu(rinfo->dir_dir->frag) != frag) {
+		dout("readdir_prepopulate got new frag %x -> %x\n",
+		     frag, le32_to_cpu(rinfo->dir_dir->frag));
+		frag = le32_to_cpu(rinfo->dir_dir->frag);
+		if (ceph_frag_is_leftmost(frag))
+			r_readdir_offset = 2;
+		else
+			r_readdir_offset = 0;
+	}
 
 	if (req->r_aborted)
 		return readdir_prepopulate_inodes_only(req, session);
@@ -1268,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 			ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
 	}
 
+	/* FIXME: release caps/leases if error occurs */
 	for (i = 0; i < rinfo->dir_nr; i++) {
 		struct ceph_vino vino;
 
@@ -1292,9 +1298,10 @@ retry_lookup:
 				err = -ENOMEM;
 				goto out;
 			}
-			err = ceph_init_dentry(dn);
-			if (err < 0) {
+			ret = ceph_init_dentry(dn);
+			if (ret < 0) {
 				dput(dn);
+				err = ret;
 				goto out;
 			}
 		} else if (dn->d_inode &&
@@ -1314,9 +1321,6 @@ retry_lookup:
 			spin_unlock(&parent->d_lock);
 		}
 
-		di = dn->d_fsdata;
-		di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset);
-
 		/* inode */
 		if (dn->d_inode) {
 			in = dn->d_inode;
@@ -1329,26 +1333,39 @@ retry_lookup:
 				err = PTR_ERR(in);
 				goto out;
 			}
-			dn = splice_dentry(dn, in, NULL, false);
-			if (IS_ERR(dn))
-				dn = NULL;
 		}
 
 		if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
 			       req->r_request_started, -1,
 			       &req->r_caps_reservation) < 0) {
 			pr_err("fill_inode badness on %p\n", in);
+			if (!dn->d_inode)
+				iput(in);
+			d_drop(dn);
 			goto next_item;
 		}
-		if (dn)
-			update_dentry_lease(dn, rinfo->dir_dlease[i],
-					    req->r_session,
-					    req->r_request_started);
+
+		if (!dn->d_inode) {
+			dn = splice_dentry(dn, in, NULL, false);
+			if (IS_ERR(dn)) {
+				err = PTR_ERR(dn);
+				dn = NULL;
+				goto next_item;
+			}
+		}
+
+		di = dn->d_fsdata;
+		di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+
+		update_dentry_lease(dn, rinfo->dir_dlease[i],
+				    req->r_session,
+				    req->r_request_started);
 next_item:
 		if (dn)
 			dput(dn);
 	}
-	req->r_did_prepopulate = true;
+	if (err == 0)
+		req->r_did_prepopulate = true;
 
 out:
 	if (snapdir) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index b7bda5d9611d..d90861f45210 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -43,6 +43,7 @@
  */
 
 struct ceph_reconnect_state {
+	int nr_caps;
 	struct ceph_pagelist *pagelist;
 	bool flock;
 };
@@ -443,6 +444,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	INIT_LIST_HEAD(&s->s_waiting);
 	INIT_LIST_HEAD(&s->s_unsafe);
 	s->s_num_cap_releases = 0;
+	s->s_cap_reconnect = 0;
 	s->s_cap_iterator = NULL;
 	INIT_LIST_HEAD(&s->s_cap_releases);
 	INIT_LIST_HEAD(&s->s_cap_releases_done);
@@ -642,6 +644,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 		req->r_unsafe_dir = NULL;
 	}
 
+	complete_all(&req->r_safe_completion);
+
 	ceph_mdsc_put_request(req);
 }
 
@@ -986,7 +990,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	dout("removing cap %p, ci is %p, inode is %p\n",
 	     cap, ci, &ci->vfs_inode);
 	spin_lock(&ci->i_ceph_lock);
-	__ceph_remove_cap(cap);
+	__ceph_remove_cap(cap, false);
 	if (!__ceph_is_any_real_caps(ci)) {
 		struct ceph_mds_client *mdsc =
 			ceph_sb_to_client(inode->i_sb)->mdsc;
@@ -1231,9 +1235,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg)
 	session->s_trim_caps--;
 	if (oissued) {
 		/* we aren't the only cap.. just remove us */
-		__queue_cap_release(session, ceph_ino(inode), cap->cap_id,
-				    cap->mseq, cap->issue_seq);
-		__ceph_remove_cap(cap);
+		__ceph_remove_cap(cap, true);
 	} else {
 		/* try to drop referring dentries */
 		spin_unlock(&ci->i_ceph_lock);
@@ -1416,7 +1418,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
 	unsigned num;
 
 	dout("discard_cap_releases mds%d\n", session->s_mds);
-	spin_lock(&session->s_cap_lock);
 
 	/* zero out the in-progress message */
 	msg = list_first_entry(&session->s_cap_releases,
@@ -1443,8 +1444,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
 		msg->front.iov_len = sizeof(*head);
 		list_add(&msg->list_head, &session->s_cap_releases);
 	}
-
-	spin_unlock(&session->s_cap_lock);
 }
 
 /*
@@ -1875,8 +1874,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	int mds = -1;
 	int err = -EAGAIN;
 
-	if (req->r_err || req->r_got_result)
+	if (req->r_err || req->r_got_result) {
+		if (req->r_aborted)
+			__unregister_request(mdsc, req);
 		goto out;
+	}
 
 	if (req->r_timeout &&
 	    time_after_eq(jiffies, req->r_started + req->r_timeout)) {
@@ -2186,7 +2188,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	if (head->safe) {
 		req->r_got_safe = true;
 		__unregister_request(mdsc, req);
-		complete_all(&req->r_safe_completion);
 
 		if (req->r_got_unsafe) {
 			/*
@@ -2238,8 +2239,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
 	if (err == 0) {
 		if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
-				    req->r_op == CEPH_MDS_OP_LSSNAP) &&
-		    rinfo->dir_nr)
+				    req->r_op == CEPH_MDS_OP_LSSNAP))
 			ceph_readdir_prepopulate(req, req->r_session);
 		ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
 	}
@@ -2490,6 +2490,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	cap->seq = 0;        /* reset cap seq */
 	cap->issue_seq = 0;  /* and issue_seq */
 	cap->mseq = 0;       /* and migrate_seq */
+	cap->cap_gen = cap->session->s_cap_gen;
 
 	if (recon_state->flock) {
 		rec.v2.cap_id = cpu_to_le64(cap->cap_id);
@@ -2552,6 +2553,8 @@ encode_again:
 	} else {
 		err = ceph_pagelist_append(pagelist, &rec, reclen);
 	}
+
+	recon_state->nr_caps++;
 out_free:
 	kfree(path);
 out_dput:
@@ -2579,6 +2582,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	struct rb_node *p;
 	int mds = session->s_mds;
 	int err = -ENOMEM;
+	int s_nr_caps;
 	struct ceph_pagelist *pagelist;
 	struct ceph_reconnect_state recon_state;
 
@@ -2610,20 +2614,38 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	dout("session %p state %s\n", session,
 	     session_state_name(session->s_state));
 
+	spin_lock(&session->s_gen_ttl_lock);
+	session->s_cap_gen++;
+	spin_unlock(&session->s_gen_ttl_lock);
+
+	spin_lock(&session->s_cap_lock);
+	/*
+	 * notify __ceph_remove_cap() that we are composing cap reconnect.
+	 * If a cap get released before being added to the cap reconnect,
+	 * __ceph_remove_cap() should skip queuing cap release.
+	 */
+	session->s_cap_reconnect = 1;
 	/* drop old cap expires; we're about to reestablish that state */
 	discard_cap_releases(mdsc, session);
+	spin_unlock(&session->s_cap_lock);
 
 	/* traverse this session's caps */
-	err = ceph_pagelist_encode_32(pagelist, session->s_nr_caps);
+	s_nr_caps = session->s_nr_caps;
+	err = ceph_pagelist_encode_32(pagelist, s_nr_caps);
 	if (err)
 		goto fail;
 
+	recon_state.nr_caps = 0;
 	recon_state.pagelist = pagelist;
 	recon_state.flock = session->s_con.peer_features & CEPH_FEATURE_FLOCK;
 	err = iterate_session_caps(session, encode_caps_cb, &recon_state);
 	if (err < 0)
 		goto fail;
 
+	spin_lock(&session->s_cap_lock);
+	session->s_cap_reconnect = 0;
+	spin_unlock(&session->s_cap_lock);
+
 	/*
 	 * snaprealms.  we provide mds with the ino, seq (version), and
 	 * parent for all of our realms.  If the mds has any newer info,
@@ -2646,11 +2668,18 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 
 	if (recon_state.flock)
 		reply->hdr.version = cpu_to_le16(2);
-	if (pagelist->length) {
-		/* set up outbound data if we have any */
-		reply->hdr.data_len = cpu_to_le32(pagelist->length);
-		ceph_msg_data_add_pagelist(reply, pagelist);
+
+	/* raced with cap release? */
+	if (s_nr_caps != recon_state.nr_caps) {
+		struct page *page = list_first_entry(&pagelist->head,
+						     struct page, lru);
+		__le32 *addr = kmap_atomic(page);
+		*addr = cpu_to_le32(recon_state.nr_caps);
+		kunmap_atomic(addr);
 	}
+
+	reply->hdr.data_len = cpu_to_le32(pagelist->length);
+	ceph_msg_data_add_pagelist(reply, pagelist);
 	ceph_con_send(&session->s_con, reply);
 
 	mutex_unlock(&session->s_mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index c2a19fbbe517..4c053d099ae4 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -132,6 +132,7 @@ struct ceph_mds_session {
 	struct list_head  s_caps;     /* all caps issued by this session */
 	int               s_nr_caps, s_trim_caps;
 	int               s_num_cap_releases;
+	int		  s_cap_reconnect;
 	struct list_head  s_cap_releases; /* waiting cap_release messages */
 	struct list_head  s_cap_releases_done; /* ready to send */
 	struct ceph_cap  *s_cap_iterator;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 6014b0a3c405..ef4ac38bb614 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -741,13 +741,7 @@ extern int ceph_add_cap(struct inode *inode,
 			int fmode, unsigned issued, unsigned wanted,
 			unsigned cap, unsigned seq, u64 realmino, int flags,
 			struct ceph_cap_reservation *caps_reservation);
-extern void __ceph_remove_cap(struct ceph_cap *cap);
-static inline void ceph_remove_cap(struct ceph_cap *cap)
-{
-	spin_lock(&cap->ci->i_ceph_lock);
-	__ceph_remove_cap(cap);
-	spin_unlock(&cap->ci->i_ceph_lock);
-}
+extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
 extern void ceph_put_cap(struct ceph_mds_client *mdsc,
 			 struct ceph_cap *cap);
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index d9ea7ada1378..f918a998a087 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -384,6 +384,7 @@ struct smb_version_operations {
 	int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
 			struct cifsFileInfo *target_file, u64 src_off, u64 len,
 			u64 dest_off);
+	int (*validate_negotiate)(const unsigned int, struct cifs_tcon *);
 };
 
 struct smb_version_values {
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 409b45eefe70..77492301cc2b 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -26,13 +26,15 @@
 #include <linux/mount.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
-#include <linux/btrfs.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "cifsfs.h"
 
+#define CIFS_IOCTL_MAGIC	0xCF
+#define CIFS_IOC_COPYCHUNK_FILE	_IOW(CIFS_IOCTL_MAGIC, 3, int)
+
 static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 			unsigned long srcfd, u64 off, u64 len, u64 destoff)
 {
@@ -213,7 +215,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				cifs_dbg(FYI, "set compress flag rc %d\n", rc);
 			}
 			break;
-		case BTRFS_IOC_CLONE:
+		case CIFS_IOC_COPYCHUNK_FILE:
 			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0);
 			break;
 		default:
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 11dde4b24f8a..757da3e54d3d 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -532,7 +532,10 @@ smb2_clone_range(const unsigned int xid,
 	int rc;
 	unsigned int ret_data_len;
 	struct copychunk_ioctl *pcchunk;
-	char *retbuf = NULL;
+	struct copychunk_ioctl_rsp *retbuf = NULL;
+	struct cifs_tcon *tcon;
+	int chunks_copied = 0;
+	bool chunk_sizes_updated = false;
 
 	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
 
@@ -547,27 +550,96 @@ smb2_clone_range(const unsigned int xid,
 
 	/* Note: request_res_key sets res_key null only if rc !=0 */
 	if (rc)
-		return rc;
+		goto cchunk_out;
 
 	/* For now array only one chunk long, will make more flexible later */
 	pcchunk->ChunkCount = __constant_cpu_to_le32(1);
 	pcchunk->Reserved = 0;
-	pcchunk->SourceOffset = cpu_to_le64(src_off);
-	pcchunk->TargetOffset = cpu_to_le64(dest_off);
-	pcchunk->Length = cpu_to_le32(len);
 	pcchunk->Reserved2 = 0;
 
-	/* Request that server copy to target from src file identified by key */
-	rc = SMB2_ioctl(xid, tlink_tcon(trgtfile->tlink),
-			trgtfile->fid.persistent_fid,
-			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
-			true /* is_fsctl */, (char *)pcchunk,
-			sizeof(struct copychunk_ioctl),	&retbuf, &ret_data_len);
+	tcon = tlink_tcon(trgtfile->tlink);
 
-	/* BB need to special case rc = EINVAL to alter chunk size */
+	while (len > 0) {
+		pcchunk->SourceOffset = cpu_to_le64(src_off);
+		pcchunk->TargetOffset = cpu_to_le64(dest_off);
+		pcchunk->Length =
+			cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk));
 
-	cifs_dbg(FYI, "rc %d data length out %d\n", rc, ret_data_len);
+		/* Request server copy to target from src identified by key */
+		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
+			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
+			true /* is_fsctl */, (char *)pcchunk,
+			sizeof(struct copychunk_ioctl),	(char **)&retbuf,
+			&ret_data_len);
+		if (rc == 0) {
+			if (ret_data_len !=
+					sizeof(struct copychunk_ioctl_rsp)) {
+				cifs_dbg(VFS, "invalid cchunk response size\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			if (retbuf->TotalBytesWritten == 0) {
+				cifs_dbg(FYI, "no bytes copied\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			/*
+			 * Check if server claimed to write more than we asked
+			 */
+			if (le32_to_cpu(retbuf->TotalBytesWritten) >
+			    le32_to_cpu(pcchunk->Length)) {
+				cifs_dbg(VFS, "invalid copy chunk response\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			if (le32_to_cpu(retbuf->ChunksWritten) != 1) {
+				cifs_dbg(VFS, "invalid num chunks written\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			chunks_copied++;
+
+			src_off += le32_to_cpu(retbuf->TotalBytesWritten);
+			dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
+			len -= le32_to_cpu(retbuf->TotalBytesWritten);
+
+			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+				le32_to_cpu(retbuf->ChunksWritten),
+				le32_to_cpu(retbuf->ChunkBytesWritten),
+				le32_to_cpu(retbuf->TotalBytesWritten));
+		} else if (rc == -EINVAL) {
+			if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
+				goto cchunk_out;
+
+			cifs_dbg(FYI, "MaxChunks %d BytesChunk %d MaxCopy %d\n",
+				le32_to_cpu(retbuf->ChunksWritten),
+				le32_to_cpu(retbuf->ChunkBytesWritten),
+				le32_to_cpu(retbuf->TotalBytesWritten));
+
+			/*
+			 * Check if this is the first request using these sizes,
+			 * (ie check if copy succeed once with original sizes
+			 * and check if the server gave us different sizes after
+			 * we already updated max sizes on previous request).
+			 * if not then why is the server returning an error now
+			 */
+			if ((chunks_copied != 0) || chunk_sizes_updated)
+				goto cchunk_out;
+
+			/* Check that server is not asking us to grow size */
+			if (le32_to_cpu(retbuf->ChunkBytesWritten) <
+					tcon->max_bytes_chunk)
+				tcon->max_bytes_chunk =
+					le32_to_cpu(retbuf->ChunkBytesWritten);
+			else
+				goto cchunk_out; /* server gave us bogus size */
+
+			/* No need to change MaxChunks since already set to 1 */
+			chunk_sizes_updated = true;
+		}
+	}
 
+cchunk_out:
 	kfree(pcchunk);
 	return rc;
 }
@@ -1247,6 +1319,7 @@ struct smb_version_operations smb30_operations = {
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
 	.clone_range = smb2_clone_range,
+	.validate_negotiate = smb3_validate_negotiate,
 };
 
 struct smb_version_values smb20_values = {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index d65270c290a1..2013234b73ad 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -454,6 +454,81 @@ neg_exit:
 	return rc;
 }
 
+int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
+{
+	int rc = 0;
+	struct validate_negotiate_info_req vneg_inbuf;
+	struct validate_negotiate_info_rsp *pneg_rsp;
+	u32 rsplen;
+
+	cifs_dbg(FYI, "validate negotiate\n");
+
+	/*
+	 * validation ioctl must be signed, so no point sending this if we
+	 * can not sign it.  We could eventually change this to selectively
+	 * sign just this, the first and only signed request on a connection.
+	 * This is good enough for now since a user who wants better security
+	 * would also enable signing on the mount. Having validation of
+	 * negotiate info for signed connections helps reduce attack vectors
+	 */
+	if (tcon->ses->server->sign == false)
+		return 0; /* validation requires signing */
+
+	vneg_inbuf.Capabilities =
+			cpu_to_le32(tcon->ses->server->vals->req_capabilities);
+	memcpy(vneg_inbuf.Guid, cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
+
+	if (tcon->ses->sign)
+		vneg_inbuf.SecurityMode =
+			cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED);
+	else if (global_secflags & CIFSSEC_MAY_SIGN)
+		vneg_inbuf.SecurityMode =
+			cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED);
+	else
+		vneg_inbuf.SecurityMode = 0;
+
+	vneg_inbuf.DialectCount = cpu_to_le16(1);
+	vneg_inbuf.Dialects[0] =
+		cpu_to_le16(tcon->ses->server->vals->protocol_id);
+
+	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
+		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
+		(char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
+		(char **)&pneg_rsp, &rsplen);
+
+	if (rc != 0) {
+		cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc);
+		return -EIO;
+	}
+
+	if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
+		cifs_dbg(VFS, "invalid size of protocol negotiate response\n");
+		return -EIO;
+	}
+
+	/* check validate negotiate info response matches what we got earlier */
+	if (pneg_rsp->Dialect !=
+			cpu_to_le16(tcon->ses->server->vals->protocol_id))
+		goto vneg_out;
+
+	if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode))
+		goto vneg_out;
+
+	/* do not validate server guid because not saved at negprot time yet */
+
+	if ((le32_to_cpu(pneg_rsp->Capabilities) | SMB2_NT_FIND |
+	      SMB2_LARGE_FILES) != tcon->ses->server->capabilities)
+		goto vneg_out;
+
+	/* validate negotiate successful */
+	cifs_dbg(FYI, "validate negotiate info successful\n");
+	return 0;
+
+vneg_out:
+	cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n");
+	return -EIO;
+}
+
 int
 SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 		const struct nls_table *nls_cp)
@@ -829,6 +904,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
 	init_copy_chunk_defaults(tcon);
+	if (tcon->ses->server->ops->validate_negotiate)
+		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(unc_path);
@@ -1214,10 +1291,17 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
 	rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base;
 
-	if (rc != 0) {
+	if ((rc != 0) && (rc != -EINVAL)) {
 		if (tcon)
 			cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
 		goto ioctl_exit;
+	} else if (rc == -EINVAL) {
+		if ((opcode != FSCTL_SRV_COPYCHUNK_WRITE) &&
+		    (opcode != FSCTL_SRV_COPYCHUNK)) {
+			if (tcon)
+				cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
+			goto ioctl_exit;
+		}
 	}
 
 	/* check if caller wants to look at return data or just return rc */
@@ -2154,11 +2238,9 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SendReceive2(xid, ses, iov, num, &resp_buftype, 0);
 	rsp = (struct smb2_set_info_rsp *)iov[0].iov_base;
 
-	if (rc != 0) {
+	if (rc != 0)
 		cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE);
-		goto out;
-	}
-out:
+
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(iov);
 	return rc;
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index f88320bbb477..2022c542ea3a 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -577,13 +577,19 @@ struct copychunk_ioctl_rsp {
 	__le32 TotalBytesWritten;
 } __packed;
 
-/* Response and Request are the same format */
-struct validate_negotiate_info {
+struct validate_negotiate_info_req {
 	__le32 Capabilities;
 	__u8   Guid[SMB2_CLIENT_GUID_SIZE];
 	__le16 SecurityMode;
 	__le16 DialectCount;
-	__le16 Dialect[1];
+	__le16 Dialects[1]; /* dialect (someday maybe list) client asked for */
+} __packed;
+
+struct validate_negotiate_info_rsp {
+	__le32 Capabilities;
+	__u8   Guid[SMB2_CLIENT_GUID_SIZE];
+	__le16 SecurityMode;
+	__le16 Dialect; /* Dialect in use for the connection */
 } __packed;
 
 #define RSS_CAPABLE	0x00000001
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index b4eea105b08c..93adc64666f3 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -162,5 +162,6 @@ extern int smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 		      struct smb2_lock_element *buf);
 extern int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 			    __u8 *lease_key, const __le32 lease_state);
+extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h
index a4b2391fe66e..0e538b5c9622 100644
--- a/fs/cifs/smbfsctl.h
+++ b/fs/cifs/smbfsctl.h
@@ -90,7 +90,7 @@
 #define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */
 #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */
 #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */
-#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 /* BB add struct */
+#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204
 /* Perform server-side data movement */
 #define FSCTL_SRV_COPYCHUNK 0x001440F2
 #define FSCTL_SRV_COPYCHUNK_WRITE 0x001480F2
diff --git a/fs/dcache.c b/fs/dcache.c
index 4bdb300b16e2..6055d61811d3 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -192,7 +192,7 @@ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char
 		if (!tcount)
 			return 0;
 	}
-	mask = ~(~0ul << tcount*8);
+	mask = bytemask_from_count(tcount);
 	return unlikely(!!((a ^ b) & mask));
 }
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 79b65c3b9e87..8b5e2584c840 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1852,8 +1852,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
-	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
-		epds.events &= ~EPOLLWAKEUP;
+	ep_take_care_of_epollwakeup(&epds);
 
 	/*
 	 * We have to check that the file structure underneath the file descriptor
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 288534920fe5..20d6697bd638 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1493,6 +1493,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
+		tmp_bh.b_size = sb->s_blocksize;
 		err = ext2_get_block(inode, blk, &tmp_bh, 1);
 		if (err < 0)
 			goto out;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e6185031c1cc..ece55565b9cd 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -268,6 +268,16 @@ struct ext4_io_submit {
 /* Translate # of blks to # of clusters */
 #define EXT4_NUM_B2C(sbi, blks)	(((blks) + (sbi)->s_cluster_ratio - 1) >> \
 				 (sbi)->s_cluster_bits)
+/* Mask out the low bits to get the starting block of the cluster */
+#define EXT4_PBLK_CMASK(s, pblk) ((pblk) &				\
+				  ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_CMASK(s, lblk) ((lblk) &				\
+				  ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
+/* Get the cluster offset */
+#define EXT4_PBLK_COFF(s, pblk) ((pblk) &				\
+				 ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_COFF(s, lblk) ((lblk) &				\
+				 ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
 
 /*
  * Structure of a blocks group descriptor
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 17ac112ab101..3fe29de832c8 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -259,6 +259,15 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 		if (WARN_ON_ONCE(err)) {
 			ext4_journal_abort_handle(where, line, __func__, bh,
 						  handle, err);
+			ext4_error_inode(inode, where, line,
+					 bh->b_blocknr,
+					 "journal_dirty_metadata failed: "
+					 "handle type %u started at line %u, "
+					 "credits %u/%u, errcode %d",
+					 handle->h_type,
+					 handle->h_line_no,
+					 handle->h_requested_credits,
+					 handle->h_buffer_credits, err);
 		}
 	} else {
 		if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 35f65cf4f318..4410cc3d6ee2 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -360,8 +360,10 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 {
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
+	ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
+	ext4_lblk_t last = lblock + len - 1;
 
-	if (len == 0)
+	if (lblock > last)
 		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
@@ -387,11 +389,26 @@ static int ext4_valid_extent_entries(struct inode *inode,
 	if (depth == 0) {
 		/* leaf entries */
 		struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
+		struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+		ext4_fsblk_t pblock = 0;
+		ext4_lblk_t lblock = 0;
+		ext4_lblk_t prev = 0;
+		int len = 0;
 		while (entries) {
 			if (!ext4_valid_extent(inode, ext))
 				return 0;
+
+			/* Check for overlapping extents */
+			lblock = le32_to_cpu(ext->ee_block);
+			len = ext4_ext_get_actual_len(ext);
+			if ((lblock <= prev) && prev) {
+				pblock = ext4_ext_pblock(ext);
+				es->s_last_error_block = cpu_to_le64(pblock);
+				return 0;
+			}
 			ext++;
 			entries--;
+			prev = lblock + len - 1;
 		}
 	} else {
 		struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
@@ -1834,8 +1851,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
 	depth = ext_depth(inode);
 	if (!path[depth].p_ext)
 		goto out;
-	b2 = le32_to_cpu(path[depth].p_ext->ee_block);
-	b2 &= ~(sbi->s_cluster_ratio - 1);
+	b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block));
 
 	/*
 	 * get the next allocated block if the extent in the path
@@ -1845,7 +1861,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
 		b2 = ext4_ext_next_allocated_block(path);
 		if (b2 == EXT_MAX_BLOCKS)
 			goto out;
-		b2 &= ~(sbi->s_cluster_ratio - 1);
+		b2 = EXT4_LBLK_CMASK(sbi, b2);
 	}
 
 	/* check for wrap through zero on extent logical start block*/
@@ -2504,7 +2520,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		 * extent, we have to mark the cluster as used (store negative
 		 * cluster number in partial_cluster).
 		 */
-		unaligned = pblk & (sbi->s_cluster_ratio - 1);
+		unaligned = EXT4_PBLK_COFF(sbi, pblk);
 		if (unaligned && (ee_len == num) &&
 		    (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
 			*partial_cluster = EXT4_B2C(sbi, pblk);
@@ -2598,7 +2614,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			 * accidentally freeing it later on
 			 */
 			pblk = ext4_ext_pblock(ex);
-			if (pblk & (sbi->s_cluster_ratio - 1))
+			if (EXT4_PBLK_COFF(sbi, pblk))
 				*partial_cluster =
 					-((long long)EXT4_B2C(sbi, pblk));
 			ex--;
@@ -3753,7 +3769,7 @@ int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_lblk_t lblk_start, lblk_end;
-	lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+	lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
 	lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
 
 	return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
@@ -3812,9 +3828,9 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 	trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
 
 	/* Check towards left side */
-	c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+	c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
 	if (c_offset) {
-		lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+		lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
 		lblk_to = lblk_from + c_offset - 1;
 
 		if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
@@ -3822,7 +3838,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 	}
 
 	/* Now check towards right. */
-	c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+	c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
 	if (allocated_clusters && c_offset) {
 		lblk_from = lblk_start + num_blks;
 		lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
@@ -4030,7 +4046,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 				     struct ext4_ext_path *path)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 	ext4_lblk_t ex_cluster_start, ex_cluster_end;
 	ext4_lblk_t rr_cluster_start;
 	ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
@@ -4048,8 +4064,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	    (rr_cluster_start == ex_cluster_start)) {
 		if (rr_cluster_start == ex_cluster_end)
 			ee_start += ee_len - 1;
-		map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
-			c_offset;
+		map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
 		map->m_len = min(map->m_len,
 				 (unsigned) sbi->s_cluster_ratio - c_offset);
 		/*
@@ -4203,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 */
 	map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
 	newex.ee_block = cpu_to_le32(map->m_lblk);
-	cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	cluster_offset = EXT4_LBLK_CMASK(sbi, map->m_lblk);
 
 	/*
 	 * If we are doing bigalloc, check to see if the extent returned
@@ -4271,7 +4286,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * needed so that future calls to get_implied_cluster_alloc()
 	 * work correctly.
 	 */
-	offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+	offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 	ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
 	ar.goal -= offset;
 	ar.logical -= offset;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 075763474118..61d49ff22c81 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1206,7 +1206,6 @@ static int ext4_journalled_write_end(struct file *file,
  */
 static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
 {
-	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
@@ -1218,7 +1217,6 @@ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
-repeat:
 	spin_lock(&ei->i_block_reservation_lock);
 	/*
 	 * ext4_calc_metadata_amount() has side effects, which we have
@@ -1238,10 +1236,6 @@ repeat:
 		ei->i_da_metadata_calc_len = save_len;
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
-		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			cond_resched();
-			goto repeat;
-		}
 		return -ENOSPC;
 	}
 	ei->i_reserved_meta_blocks += md_needed;
@@ -1255,7 +1249,6 @@ repeat:
  */
 static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 {
-	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
@@ -1277,7 +1270,6 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
-repeat:
 	spin_lock(&ei->i_block_reservation_lock);
 	/*
 	 * ext4_calc_metadata_amount() has side effects, which we have
@@ -1297,10 +1289,6 @@ repeat:
 		ei->i_da_metadata_calc_len = save_len;
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
-		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			cond_resched();
-			goto repeat;
-		}
 		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
 		return -ENOSPC;
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4d113efa024c..04a5c7504be9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3442,6 +3442,9 @@ static void ext4_mb_pa_callback(struct rcu_head *head)
 {
 	struct ext4_prealloc_space *pa;
 	pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+
+	BUG_ON(atomic_read(&pa->pa_count));
+	BUG_ON(pa->pa_deleted == 0);
 	kmem_cache_free(ext4_pspace_cachep, pa);
 }
 
@@ -3455,11 +3458,13 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 	ext4_group_t grp;
 	ext4_fsblk_t grp_blk;
 
-	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
-		return;
-
 	/* in this short window concurrent discard can set pa_deleted */
 	spin_lock(&pa->pa_lock);
+	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) {
+		spin_unlock(&pa->pa_lock);
+		return;
+	}
+
 	if (pa->pa_deleted == 1) {
 		spin_unlock(&pa->pa_lock);
 		return;
@@ -4121,7 +4126,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	ext4_get_group_no_and_offset(sb, goal, &group, &block);
 
 	/* set up allocation goals */
-	ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
+	ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical);
 	ac->ac_status = AC_STATUS_CONTINUE;
 	ac->ac_sb = sb;
 	ac->ac_inode = ar->inode;
@@ -4663,7 +4668,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	 * blocks at the beginning or the end unless we are explicitly
 	 * requested to avoid doing so.
 	 */
-	overflow = block & (sbi->s_cluster_ratio - 1);
+	overflow = EXT4_PBLK_COFF(sbi, block);
 	if (overflow) {
 		if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
 			overflow = sbi->s_cluster_ratio - overflow;
@@ -4677,7 +4682,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			count += overflow;
 		}
 	}
-	overflow = count & (sbi->s_cluster_ratio - 1);
+	overflow = EXT4_LBLK_COFF(sbi, count);
 	if (overflow) {
 		if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
 			if (count > overflow)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c977f4e4e63b..1f7784de05b6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -792,7 +792,7 @@ static void ext4_put_super(struct super_block *sb)
 	}
 
 	ext4_es_unregister_shrinker(sbi);
-	del_timer(&sbi->s_err_report);
+	del_timer_sync(&sbi->s_err_report);
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
@@ -3316,11 +3316,19 @@ int ext4_calculate_overhead(struct super_block *sb)
 }
 
 
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
 {
 	ext4_fsblk_t resv_clusters;
 
 	/*
+	 * There's no need to reserve anything when we aren't using extents.
+	 * The space estimates are exact, there are no unwritten extents,
+	 * hole punching doesn't need new metadata... This is needed especially
+	 * to keep ext2/3 backward compatibility.
+	 */
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+		return 0;
+	/*
 	 * By default we reserve 2% or 4096 clusters, whichever is smaller.
 	 * This should cover the situations where we can not afford to run
 	 * out of space like for example punch hole, or converting
@@ -3328,7 +3336,8 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
 	 * allocation would require 1, or 2 blocks, higher numbers are
 	 * very rare.
 	 */
-	resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+	resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
+			EXT4_SB(sb)->s_cluster_bits;
 
 	do_div(resv_clusters, 50);
 	resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
@@ -4071,10 +4080,10 @@ no_journal:
 			 "available");
 	}
 
-	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
-			 "reserved pool", ext4_calculate_resv_clusters(sbi));
+			 "reserved pool", ext4_calculate_resv_clusters(sb));
 		goto failed_mount4a;
 	}
 
@@ -4184,7 +4193,7 @@ failed_mount_wq:
 	}
 failed_mount3:
 	ext4_es_unregister_shrinker(sbi);
-	del_timer(&sbi->s_err_report);
+	del_timer_sync(&sbi->s_err_report);
 	if (sbi->s_flex_groups)
 		ext4_kvfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 52032647dd4a..5fa344afb49a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -702,7 +702,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	read_lock(&journal->j_state_lock);
 #ifdef CONFIG_JBD2_DEBUG
 	if (!tid_geq(journal->j_commit_request, tid)) {
-		printk(KERN_EMERG
+		printk(KERN_ERR
 		       "%s: error: j_commit_request=%d, tid=%d\n",
 		       __func__, journal->j_commit_request, tid);
 	}
@@ -718,10 +718,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	}
 	read_unlock(&journal->j_state_lock);
 
-	if (unlikely(is_journal_aborted(journal))) {
-		printk(KERN_EMERG "journal commit I/O error\n");
+	if (unlikely(is_journal_aborted(journal)))
 		err = -EIO;
-	}
 	return err;
 }
 
@@ -1527,13 +1525,13 @@ static int journal_get_superblock(journal_t *journal)
 	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
 	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
-		printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 "
+		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
 	if (!jbd2_verify_csum_type(journal, sb)) {
-		printk(KERN_ERR "JBD: Unknown checksum type\n");
+		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
@@ -1541,7 +1539,7 @@ static int journal_get_superblock(journal_t *journal)
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
-			printk(KERN_ERR "JBD: Cannot load crc32c driver.\n");
+			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
 			err = PTR_ERR(journal->j_chksum_driver);
 			journal->j_chksum_driver = NULL;
 			goto out;
@@ -1550,7 +1548,7 @@ static int journal_get_superblock(journal_t *journal)
 
 	/* Check superblock checksum */
 	if (!jbd2_superblock_csum_verify(journal, sb)) {
-		printk(KERN_ERR "JBD: journal checksum error\n");
+		printk(KERN_ERR "JBD2: journal checksum error\n");
 		goto out;
 	}
 
@@ -1836,7 +1834,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 			journal->j_chksum_driver = crypto_alloc_shash("crc32c",
 								      0, 0);
 			if (IS_ERR(journal->j_chksum_driver)) {
-				printk(KERN_ERR "JBD: Cannot load crc32c "
+				printk(KERN_ERR "JBD2: Cannot load crc32c "
 				       "driver.\n");
 				journal->j_chksum_driver = NULL;
 				return 0;
@@ -2645,7 +2643,7 @@ static void __exit journal_exit(void)
 #ifdef CONFIG_JBD2_DEBUG
 	int n = atomic_read(&nr_journal_heads);
 	if (n)
-		printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
+		printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n);
 #endif
 	jbd2_remove_jbd_stats_proc_entry();
 	jbd2_journal_destroy_caches();
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3929c50428b1..3b6bb19d60b1 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -594,7 +594,7 @@ static int do_one_pass(journal_t *journal,
 						be32_to_cpu(tmp->h_sequence))) {
 						brelse(obh);
 						success = -EIO;
-						printk(KERN_ERR "JBD: Invalid "
+						printk(KERN_ERR "JBD2: Invalid "
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 7aa9a32573bb..8360674c85bc 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -932,7 +932,7 @@ repeat:
 					jbd2_alloc(jh2bh(jh)->b_size,
 							 GFP_NOFS);
 				if (!frozen_buffer) {
-					printk(KERN_EMERG
+					printk(KERN_ERR
 					       "%s: OOM for frozen_buffer\n",
 					       __func__);
 					JBUFFER_TRACE(jh, "oom!");
@@ -1166,7 +1166,7 @@ repeat:
 	if (!jh->b_committed_data) {
 		committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
 		if (!committed_data) {
-			printk(KERN_EMERG "%s: No memory for committed data\n",
+			printk(KERN_ERR "%s: No memory for committed data\n",
 				__func__);
 			err = -ENOMEM;
 			goto out;
@@ -1290,7 +1290,10 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		 * once a transaction -bzzz
 		 */
 		jh->b_modified = 1;
-		J_ASSERT_JH(jh, handle->h_buffer_credits > 0);
+		if (handle->h_buffer_credits <= 0) {
+			ret = -ENOSPC;
+			goto out_unlock_bh;
+		}
 		handle->h_buffer_credits--;
 	}
 
@@ -1305,7 +1308,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		JBUFFER_TRACE(jh, "fastpath");
 		if (unlikely(jh->b_transaction !=
 			     journal->j_running_transaction)) {
-			printk(KERN_EMERG "JBD: %s: "
+			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_transaction (%llu, %p, %u) != "
 			       "journal->j_running_transaction (%p, %u)",
 			       journal->j_devname,
@@ -1332,7 +1335,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		JBUFFER_TRACE(jh, "already on other transaction");
 		if (unlikely(jh->b_transaction !=
 			     journal->j_committing_transaction)) {
-			printk(KERN_EMERG "JBD: %s: "
+			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_transaction (%llu, %p, %u) != "
 			       "journal->j_committing_transaction (%p, %u)",
 			       journal->j_devname,
@@ -1345,7 +1348,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 			ret = -EINVAL;
 		}
 		if (unlikely(jh->b_next_transaction != transaction)) {
-			printk(KERN_EMERG "JBD: %s: "
+			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_next_transaction (%llu, %p, %u) != "
 			       "transaction (%p, %u)",
 			       journal->j_devname,
@@ -1373,7 +1376,6 @@ out_unlock_bh:
 	jbd2_journal_put_journal_head(jh);
 out:
 	JBUFFER_TRACE(jh, "exit");
-	WARN_ON(ret);	/* All errors are bugs, so dump the stack */
 	return ret;
 }
 
diff --git a/fs/namei.c b/fs/namei.c
index 8f77a8cea289..3531deebad30 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -513,8 +513,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 
 	if (!lockref_get_not_dead(&parent->d_lockref)) {
 		nd->path.dentry = NULL;	
-		rcu_read_unlock();
-		return -ECHILD;
+		goto out;
 	}
 
 	/*
@@ -1599,11 +1598,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
  *   do a "get_unaligned()" if this helps and is sufficiently
  *   fast.
  *
- * - Little-endian machines (so that we can generate the mask
- *   of low bytes efficiently). Again, we *could* do a byte
- *   swapping load on big-endian architectures if that is not
- *   expensive enough to make the optimization worthless.
- *
  * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
  *   do not trap on the (extremely unlikely) case of a page
  *   crossing operation.
@@ -1647,7 +1641,7 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len)
 		if (!len)
 			goto done;
 	}
-	mask = ~(~0ul << len*8);
+	mask = bytemask_from_count(len);
 	hash += mask & a;
 done:
 	return fold_hash(hash);
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 8485978993e8..9838fb020473 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -36,6 +36,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 
+#include "../nfs4_fs.h"
 #include "../pnfs.h"
 #include "../netns.h"
 
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 9c3e117c3ed1..4d0161442565 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -44,7 +44,7 @@
 static inline sector_t normalize(sector_t s, int base)
 {
 	sector_t tmp = s; /* Since do_div modifies its argument */
-	return s - do_div(tmp, base);
+	return s - sector_div(tmp, base);
 }
 
 static inline sector_t normalize_up(sector_t s, int base)
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index fc0f95ec7358..d25f10fb4926 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -46,7 +46,9 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/svcauth.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/nfs_fs.h>
 
+#include "nfs4_fs.h"
 #include "dns_resolve.h"
 #include "cache_lib.h"
 #include "netns.h"
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 18ab2da4eeb6..00ad1c2b217d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -312,7 +312,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags)
 }
 EXPORT_SYMBOL_GPL(nfs4_label_alloc);
 #else
-void inline nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
+void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					struct nfs4_label *label)
 {
 }
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index bca6a3e3c49c..8b5cc04a8611 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -269,6 +269,21 @@ extern const u32 nfs41_maxgetdevinfo_overhead;
 extern struct rpc_procinfo nfs4_procedures[];
 #endif
 
+#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
+static inline void nfs4_label_free(struct nfs4_label *label)
+{
+	if (label) {
+		kfree(label->label);
+		kfree(label);
+	}
+	return;
+}
+#else
+static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
+static inline void nfs4_label_free(void *label) {}
+#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
+
 /* proc.c */
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 3ce79b04522e..5609edc742a0 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -9,6 +9,14 @@
 #ifndef __LINUX_FS_NFS_NFS4_FS_H
 #define __LINUX_FS_NFS_NFS4_FS_H
 
+#if defined(CONFIG_NFS_V4_2)
+#define NFS4_MAX_MINOR_VERSION 2
+#elif defined(CONFIG_NFS_V4_1)
+#define NFS4_MAX_MINOR_VERSION 1
+#else
+#define NFS4_MAX_MINOR_VERSION 0
+#endif
+
 #if IS_ENABLED(CONFIG_NFS_V4)
 
 #define NFS4_MAX_LOOP_ON_RECOVER (10)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 659990c0109e..15052b81df42 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2518,9 +2518,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 						     calldata->roc_barrier);
 			nfs_set_open_stateid(state, &calldata->res.stateid, 0);
 			renew_lease(server, calldata->timestamp);
-			nfs4_close_clear_stateid_flags(state,
-					calldata->arg.fmode);
 			break;
+		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_OLD_STATEID:
 		case -NFS4ERR_BAD_STATEID:
@@ -2528,9 +2527,13 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			if (calldata->arg.fmode == 0)
 				break;
 		default:
-			if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+			if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
 				rpc_restart_call_prepare(task);
+				goto out_release;
+			}
 	}
+	nfs4_close_clear_stateid_flags(state, calldata->arg.fmode);
+out_release:
 	nfs_release_seqid(calldata->arg.seqid);
 	nfs_refresh_inode(calldata->inode, calldata->res.fattr);
 	dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
@@ -4802,7 +4805,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			dprintk("%s ERROR %d, Reset session\n", __func__,
 				task->tk_status);
 			nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-			goto restart_call;
+			goto wait_on_recovery;
 #endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
@@ -4987,11 +4990,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 
 	trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
 	switch (task->tk_status) {
-	case -NFS4ERR_STALE_STATEID:
-	case -NFS4ERR_EXPIRED:
 	case 0:
 		renew_lease(data->res.server, data->timestamp);
 		break;
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_EXPIRED:
+		task->tk_status = 0;
+		break;
 	default:
 		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
 				-EAGAIN) {
@@ -7589,7 +7598,14 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		return;
 
 	server = NFS_SERVER(lrp->args.inode);
-	if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+	switch (task->tk_status) {
+	default:
+		task->tk_status = 0;
+	case 0:
+		break;
+	case -NFS4ERR_DELAY:
+		if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+			break;
 		rpc_restart_call_prepare(task);
 		return;
 	}
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 9186c7ce0b14..b6af150c96b8 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -132,6 +132,13 @@ nfsd_reply_cache_alloc(void)
 }
 
 static void
+nfsd_reply_cache_unhash(struct svc_cacherep *rp)
+{
+	hlist_del_init(&rp->c_hash);
+	list_del_init(&rp->c_lru);
+}
+
+static void
 nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
 {
 	if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) {
@@ -417,7 +424,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 		rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
 		if (nfsd_cache_entry_expired(rp) ||
 		    num_drc_entries >= max_drc_entries) {
-			lru_put_end(rp);
+			nfsd_reply_cache_unhash(rp);
 			prune_cache_entries();
 			goto search_cache;
 		}
diff --git a/fs/pipe.c b/fs/pipe.c
index d2c45e14e6d8..0e0752ef2715 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -726,11 +726,25 @@ pipe_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
+static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
+{
+	int kill = 0;
+
+	spin_lock(&inode->i_lock);
+	if (!--pipe->files) {
+		inode->i_pipe = NULL;
+		kill = 1;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (kill)
+		free_pipe_info(pipe);
+}
+
 static int
 pipe_release(struct inode *inode, struct file *file)
 {
-	struct pipe_inode_info *pipe = inode->i_pipe;
-	int kill = 0;
+	struct pipe_inode_info *pipe = file->private_data;
 
 	__pipe_lock(pipe);
 	if (file->f_mode & FMODE_READ)
@@ -743,17 +757,9 @@ pipe_release(struct inode *inode, struct file *file)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
 
-	if (kill)
-		free_pipe_info(pipe);
-
+	put_pipe_info(inode, pipe);
 	return 0;
 }
 
@@ -1014,7 +1020,6 @@ static int fifo_open(struct inode *inode, struct file *filp)
 {
 	struct pipe_inode_info *pipe;
 	bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
-	int kill = 0;
 	int ret;
 
 	filp->f_version = 0;
@@ -1130,15 +1135,9 @@ err_wr:
 	goto err;
 
 err:
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
-	if (kill)
-		free_pipe_info(pipe);
+
+	put_pipe_info(inode, pipe);
 	return ret;
 }
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 28955d4b7218..124fc43c7090 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -292,16 +292,20 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	unsigned long rv = -EIO;
-	unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
-				  unsigned long, unsigned long) = NULL;
+
 	if (use_pde(pde)) {
+		typeof(proc_reg_get_unmapped_area) *get_area;
+
+		get_area = pde->proc_fops->get_unmapped_area;
 #ifdef CONFIG_MMU
-		get_area = current->mm->get_unmapped_area;
+		if (!get_area)
+			get_area = current->mm->get_unmapped_area;
 #endif
-		if (pde->proc_fops->get_unmapped_area)
-			get_area = pde->proc_fops->get_unmapped_area;
+
 		if (get_area)
 			rv = get_area(file, orig_addr, len, pgoff, flags);
+		else
+			rv = orig_addr;
 		unuse_pde(pde);
 	}
 	return rv;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index b8e93a40a5d3..78c3c2097787 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -443,8 +443,11 @@ int pstore_register(struct pstore_info *psi)
 		pstore_get_records(0);
 
 	kmsg_dump_register(&pstore_dumper);
-	pstore_register_console();
-	pstore_register_ftrace();
+
+	if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
+		pstore_register_console();
+		pstore_register_ftrace();
+	}
 
 	if (pstore_update_ms >= 0) {
 		pstore_timer.expires = jiffies +
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index 2943b2bfae48..62a0de6632e1 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -84,6 +84,9 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 		 */
 		res = squashfs_read_cache(target_page, block, bsize, pages,
 								page);
+		if (res < 0)
+			goto mark_errored;
+
 		goto out;
 	}
 
@@ -119,7 +122,7 @@ mark_errored:
 	 * dealt with by the caller
 	 */
 	for (i = 0; i < pages; i++) {
-		if (page[i] == target_page)
+		if (page[i] == NULL || page[i] == target_page)
 			continue;
 		flush_dcache_page(page[i]);
 		SetPageError(page[i]);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 79b5da2acbe1..35e7d08fe629 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -649,7 +649,23 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	if (!of)
 		goto err_out;
 
-	mutex_init(&of->mutex);
+	/*
+	 * The following is done to give a different lockdep key to
+	 * @of->mutex for files which implement mmap.  This is a rather
+	 * crude way to avoid false positive lockdep warning around
+	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
+	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
+	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
+	 * open file has a separate mutex, it's okay as long as those don't
+	 * happen on the same file.  At this point, we can't easily give
+	 * each file a separate locking class.  Let's differentiate on
+	 * whether the file is bin or not for now.
+	 */
+	if (sysfs_is_bin(attr_sd))
+		mutex_init(&of->mutex);
+	else
+		mutex_init(&of->mutex);
+
 	of->sd = attr_sd;
 	of->file = file;
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 3ef11b22e750..3b2c14b6f0fb 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1635,7 +1635,7 @@ xfs_bmap_last_extent(
  * blocks at the end of the file which do not start at the previous data block,
  * we will try to align the new blocks at stripe unit boundaries.
  *
- * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be
+ * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be
  * at, or past the EOF.
  */
 STATIC int
@@ -1650,9 +1650,14 @@ xfs_bmap_isaeof(
 	bma->aeof = 0;
 	error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
 				     &is_empty);
-	if (error || is_empty)
+	if (error)
 		return error;
 
+	if (is_empty) {
+		bma->aeof = 1;
+		return 0;
+	}
+
 	/*
 	 * Check if we are allocation or past the last extent, or at least into
 	 * the last delayed allocated extent.
@@ -3643,10 +3648,19 @@ xfs_bmap_btalloc(
 	int		isaligned;
 	int		tryagain;
 	int		error;
+	int		stripe_align;
 
 	ASSERT(ap->length);
 
 	mp = ap->ip->i_mount;
+
+	/* stripe alignment for allocation is determined by mount parameters */
+	stripe_align = 0;
+	if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
+		stripe_align = mp->m_swidth;
+	else if (mp->m_dalign)
+		stripe_align = mp->m_dalign;
+
 	align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
 	if (unlikely(align)) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
@@ -3655,6 +3669,8 @@ xfs_bmap_btalloc(
 		ASSERT(!error);
 		ASSERT(ap->length);
 	}
+
+
 	nullfb = *ap->firstblock == NULLFSBLOCK;
 	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
 	if (nullfb) {
@@ -3730,7 +3746,7 @@ xfs_bmap_btalloc(
 	 */
 	if (!ap->flist->xbf_low && ap->aeof) {
 		if (!ap->offset) {
-			args.alignment = mp->m_dalign;
+			args.alignment = stripe_align;
 			atype = args.type;
 			isaligned = 1;
 			/*
@@ -3755,13 +3771,13 @@ xfs_bmap_btalloc(
 			 * of minlen+alignment+slop doesn't go up
 			 * between the calls.
 			 */
-			if (blen > mp->m_dalign && blen <= args.maxlen)
-				nextminlen = blen - mp->m_dalign;
+			if (blen > stripe_align && blen <= args.maxlen)
+				nextminlen = blen - stripe_align;
 			else
 				nextminlen = args.minlen;
-			if (nextminlen + mp->m_dalign > args.minlen + 1)
+			if (nextminlen + stripe_align > args.minlen + 1)
 				args.minalignslop =
-					nextminlen + mp->m_dalign -
+					nextminlen + stripe_align -
 					args.minlen - 1;
 			else
 				args.minalignslop = 0;
@@ -3783,7 +3799,7 @@ xfs_bmap_btalloc(
 		 */
 		args.type = atype;
 		args.fsbno = ap->blkno;
-		args.alignment = mp->m_dalign;
+		args.alignment = stripe_align;
 		args.minlen = nextminlen;
 		args.minalignslop = 0;
 		isaligned = 1;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5887e41c0323..1394106ed22d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1187,7 +1187,12 @@ xfs_zero_remaining_bytes(
 		XFS_BUF_UNWRITE(bp);
 		XFS_BUF_READ(bp);
 		XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
-		xfsbdstrat(mp, bp);
+
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			error = XFS_ERROR(EIO);
+			break;
+		}
+		xfs_buf_iorequest(bp);
 		error = xfs_buf_iowait(bp);
 		if (error) {
 			xfs_buf_ioerror_alert(bp,
@@ -1200,7 +1205,12 @@ xfs_zero_remaining_bytes(
 		XFS_BUF_UNDONE(bp);
 		XFS_BUF_UNREAD(bp);
 		XFS_BUF_WRITE(bp);
-		xfsbdstrat(mp, bp);
+
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			error = XFS_ERROR(EIO);
+			break;
+		}
+		xfs_buf_iorequest(bp);
 		error = xfs_buf_iowait(bp);
 		if (error) {
 			xfs_buf_ioerror_alert(bp,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 5f3ea443ebbe..2a941ab623cb 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -698,7 +698,11 @@ xfs_buf_read_uncached(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	xfsbdstrat(target->bt_mount, bp);
+	if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+		xfs_buf_relse(bp);
+		return NULL;
+	}
+	xfs_buf_iorequest(bp);
 	xfs_buf_iowait(bp);
 	return bp;
 }
@@ -1089,7 +1093,7 @@ xfs_bioerror(
  * This is meant for userdata errors; metadata bufs come with
  * iodone functions attached, so that we can track down errors.
  */
-STATIC int
+int
 xfs_bioerror_relse(
 	struct xfs_buf	*bp)
 {
@@ -1152,7 +1156,7 @@ xfs_bwrite(
 	ASSERT(xfs_buf_islocked(bp));
 
 	bp->b_flags |= XBF_WRITE;
-	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
 
 	xfs_bdstrat_cb(bp);
 
@@ -1164,25 +1168,6 @@ xfs_bwrite(
 	return error;
 }
 
-/*
- * Wrapper around bdstrat so that we can stop data from going to disk in case
- * we are shutting down the filesystem.  Typically user data goes thru this
- * path; one of the exceptions is the superblock.
- */
-void
-xfsbdstrat(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
-{
-	if (XFS_FORCED_SHUTDOWN(mp)) {
-		trace_xfs_bdstrat_shut(bp, _RET_IP_);
-		xfs_bioerror_relse(bp);
-		return;
-	}
-
-	xfs_buf_iorequest(bp);
-}
-
 STATIC void
 _xfs_buf_ioend(
 	xfs_buf_t		*bp,
@@ -1516,6 +1501,12 @@ xfs_wait_buftarg(
 			struct xfs_buf *bp;
 			bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
 			list_del_init(&bp->b_lru);
+			if (bp->b_flags & XBF_WRITE_FAIL) {
+				xfs_alert(btp->bt_mount,
+"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n"
+"Please run xfs_repair to determine the extent of the problem.",
+					(long long)bp->b_bn);
+			}
 			xfs_buf_rele(bp);
 		}
 		if (loop++ != 0)
@@ -1799,7 +1790,7 @@ __xfs_buf_delwri_submit(
 
 	blk_start_plug(&plug);
 	list_for_each_entry_safe(bp, n, io_list, b_list) {
-		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
 		bp->b_flags |= XBF_WRITE;
 
 		if (!wait) {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index e65683361017..1cf21a4a9f22 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -45,6 +45,7 @@ typedef enum {
 #define XBF_ASYNC	 (1 << 4) /* initiator will not wait for completion */
 #define XBF_DONE	 (1 << 5) /* all pages in the buffer uptodate */
 #define XBF_STALE	 (1 << 6) /* buffer has been staled, do not find it */
+#define XBF_WRITE_FAIL	 (1 << 24)/* async writes have failed on this buffer */
 
 /* I/O hints for the BIO layer */
 #define XBF_SYNCIO	 (1 << 10)/* treat this buffer as synchronous I/O */
@@ -70,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_STALE,		"STALE" }, \
+	{ XBF_WRITE_FAIL,	"WRITE_FAIL" }, \
 	{ XBF_SYNCIO,		"SYNCIO" }, \
 	{ XBF_FUA,		"FUA" }, \
 	{ XBF_FLUSH,		"FLUSH" }, \
@@ -80,6 +82,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
 	{ _XBF_COMPOUND,	"COMPOUND" }
 
+
 /*
  * Internal state flags.
  */
@@ -269,9 +272,6 @@ extern void xfs_buf_unlock(xfs_buf_t *);
 
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_buf *bp);
-
-extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
-
 extern void xfs_buf_ioend(xfs_buf_t *,	int);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
@@ -282,6 +282,8 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 #define xfs_buf_zero(bp, off, len) \
 	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
 
+extern int xfs_bioerror_relse(struct xfs_buf *);
+
 static inline int xfs_buf_geterror(xfs_buf_t *bp)
 {
 	return bp ? bp->b_error : ENOMEM;
@@ -301,7 +303,8 @@ extern void xfs_buf_terminate(void);
 
 #define XFS_BUF_ZEROFLAGS(bp) \
 	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
-			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
+			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
+			    XBF_WRITE_FAIL))
 
 void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XBF_STALE)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a64f67ba25d3..2227b9b050bb 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -496,6 +496,14 @@ xfs_buf_item_unpin(
 	}
 }
 
+/*
+ * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
+ * seconds so as to not spam logs too much on repeated detection of the same
+ * buffer being bad..
+ */
+
+DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
+
 STATIC uint
 xfs_buf_item_push(
 	struct xfs_log_item	*lip,
@@ -524,6 +532,14 @@ xfs_buf_item_push(
 
 	trace_xfs_buf_item_push(bip);
 
+	/* has a previous flush failed due to IO errors? */
+	if ((bp->b_flags & XBF_WRITE_FAIL) &&
+	    ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
+		xfs_warn(bp->b_target->bt_mount,
+"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+			 (long long)bp->b_bn);
+	}
+
 	if (!xfs_buf_delwri_queue(bp, buffer_list))
 		rval = XFS_ITEM_FLUSHING;
 	xfs_buf_unlock(bp);
@@ -1096,8 +1112,9 @@ xfs_buf_iodone_callbacks(
 
 		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
 
-		if (!XFS_BUF_ISSTALE(bp)) {
-			bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+		if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
+			bp->b_flags |= XBF_WRITE | XBF_ASYNC |
+				       XBF_DONE | XBF_WRITE_FAIL;
 			xfs_buf_iorequest(bp);
 		} else {
 			xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 56369d4509d5..48c7d18f68c3 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -2067,12 +2067,12 @@ xfs_dir2_node_lookup(
  */
 int						/* error */
 xfs_dir2_node_removename(
-	xfs_da_args_t		*args)		/* operation arguments */
+	struct xfs_da_args	*args)		/* operation arguments */
 {
-	xfs_da_state_blk_t	*blk;		/* leaf block */
+	struct xfs_da_state_blk	*blk;		/* leaf block */
 	int			error;		/* error return value */
 	int			rval;		/* operation return value */
-	xfs_da_state_t		*state;		/* btree cursor */
+	struct xfs_da_state	*state;		/* btree cursor */
 
 	trace_xfs_dir2_node_removename(args);
 
@@ -2084,19 +2084,18 @@ xfs_dir2_node_removename(
 	state->mp = args->dp->i_mount;
 	state->blocksize = state->mp->m_dirblksize;
 	state->node_ents = state->mp->m_dir_node_ents;
-	/*
-	 * Look up the entry we're deleting, set up the cursor.
-	 */
+
+	/* Look up the entry we're deleting, set up the cursor. */
 	error = xfs_da3_node_lookup_int(state, &rval);
 	if (error)
-		rval = error;
-	/*
-	 * Didn't find it, upper layer screwed up.
-	 */
+		goto out_free;
+
+	/* Didn't find it, upper layer screwed up. */
 	if (rval != EEXIST) {
-		xfs_da_state_free(state);
-		return rval;
+		error = rval;
+		goto out_free;
 	}
+
 	blk = &state->path.blk[state->path.active - 1];
 	ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
 	ASSERT(state->extravalid);
@@ -2107,7 +2106,7 @@ xfs_dir2_node_removename(
 	error = xfs_dir2_leafn_remove(args, blk->bp, blk->index,
 		&state->extrablk, &rval);
 	if (error)
-		return error;
+		goto out_free;
 	/*
 	 * Fix the hash values up the btree.
 	 */
@@ -2122,6 +2121,7 @@ xfs_dir2_node_removename(
 	 */
 	if (!error)
 		error = xfs_dir2_node_to_leaf(state);
+out_free:
 	xfs_da_state_free(state);
 	return error;
 }
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 8367d6dc18c9..4f11ef011139 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -157,7 +157,7 @@ xfs_ioc_trim(
 	struct xfs_mount		*mp,
 	struct fstrim_range __user	*urange)
 {
-	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
+	struct request_queue	*q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
 	unsigned int		granularity = q->limits.discard_granularity;
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
@@ -180,7 +180,8 @@ xfs_ioc_trim(
 	 * matter as trimming blocks is an advisory interface.
 	 */
 	if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
-	    range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)))
+	    range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) ||
+	    range.len < mp->m_sb.sb_blocksize)
 		return -XFS_ERROR(EINVAL);
 
 	start = BTOBB(range.start);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a6e54b3319bd..02fb943cbf22 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -220,6 +220,8 @@ xfs_growfs_data_private(
 	 */
 	nfree = 0;
 	for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
+		__be32	*agfl_bno;
+
 		/*
 		 * AG freespace header block
 		 */
@@ -279,8 +281,10 @@ xfs_growfs_data_private(
 			agfl->agfl_seqno = cpu_to_be32(agno);
 			uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_uuid);
 		}
+
+		agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
 		for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++)
-			agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+			agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
 
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 4d613401a5e0..33ad9a77791f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -442,7 +442,8 @@ xfs_attrlist_by_handle(
 		return -XFS_ERROR(EPERM);
 	if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
-	if (al_hreq.buflen > XATTR_LIST_MAX)
+	if (al_hreq.buflen < sizeof(struct attrlist) ||
+	    al_hreq.buflen > XATTR_LIST_MAX)
 		return -XFS_ERROR(EINVAL);
 
 	/*
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index e8fb1231db81..a7992f8de9d3 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -356,7 +356,8 @@ xfs_compat_attrlist_by_handle(
 	if (copy_from_user(&al_hreq, arg,
 			   sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
-	if (al_hreq.buflen > XATTR_LIST_MAX)
+	if (al_hreq.buflen < sizeof(struct attrlist) ||
+	    al_hreq.buflen > XATTR_LIST_MAX)
 		return -XFS_ERROR(EINVAL);
 
 	/*
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 27e0e544e963..104455b8046c 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -618,7 +618,8 @@ xfs_setattr_nonsize(
 		}
 		if (!gid_eq(igid, gid)) {
 			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
-				ASSERT(!XFS_IS_PQUOTA_ON(mp));
+				ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
+				       !XFS_IS_PQUOTA_ON(mp));
 				ASSERT(mask & ATTR_GID);
 				ASSERT(gdqp);
 				olddquot2 = xfs_qm_vop_chown(tp, ip,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b6b669df40f3..eae16920655b 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -193,7 +193,10 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	xfsbdstrat(log->l_mp, bp);
+	if (XFS_FORCED_SHUTDOWN(log->l_mp))
+		return XFS_ERROR(EIO);
+
+	xfs_buf_iorequest(bp);
 	error = xfs_buf_iowait(bp);
 	if (error)
 		xfs_buf_ioerror_alert(bp, __func__);
@@ -4397,7 +4400,13 @@ xlog_do_recover(
 	XFS_BUF_READ(bp);
 	XFS_BUF_UNASYNC(bp);
 	bp->b_ops = &xfs_sb_buf_ops;
-	xfsbdstrat(log->l_mp, bp);
+
+	if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+		xfs_buf_relse(bp);
+		return XFS_ERROR(EIO);
+	}
+
+	xfs_buf_iorequest(bp);
 	error = xfs_buf_iowait(bp);
 	if (error) {
 		xfs_buf_ioerror_alert(bp, __func__);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 14a4996cfec6..dd88f0e27bd8 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -134,8 +134,6 @@ xfs_qm_dqpurge(
 {
 	struct xfs_mount	*mp = dqp->q_mount;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
-	struct xfs_dquot	*gdqp = NULL;
-	struct xfs_dquot	*pdqp = NULL;
 
 	xfs_dqlock(dqp);
 	if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
@@ -143,21 +141,6 @@ xfs_qm_dqpurge(
 		return EAGAIN;
 	}
 
-	/*
-	 * If this quota has a hint attached, prepare for releasing it now.
-	 */
-	gdqp = dqp->q_gdquot;
-	if (gdqp) {
-		xfs_dqlock(gdqp);
-		dqp->q_gdquot = NULL;
-	}
-
-	pdqp = dqp->q_pdquot;
-	if (pdqp) {
-		xfs_dqlock(pdqp);
-		dqp->q_pdquot = NULL;
-	}
-
 	dqp->dq_flags |= XFS_DQ_FREEING;
 
 	xfs_dqflock(dqp);
@@ -206,11 +189,47 @@ xfs_qm_dqpurge(
 	XFS_STATS_DEC(xs_qm_dquot_unused);
 
 	xfs_qm_dqdestroy(dqp);
+	return 0;
+}
+
+/*
+ * Release the group or project dquot pointers the user dquots maybe carrying
+ * around as a hint, and proceed to purge the user dquot cache if requested.
+*/
+STATIC int
+xfs_qm_dqpurge_hints(
+	struct xfs_dquot	*dqp,
+	void			*data)
+{
+	struct xfs_dquot	*gdqp = NULL;
+	struct xfs_dquot	*pdqp = NULL;
+	uint			flags = *((uint *)data);
+
+	xfs_dqlock(dqp);
+	if (dqp->dq_flags & XFS_DQ_FREEING) {
+		xfs_dqunlock(dqp);
+		return EAGAIN;
+	}
+
+	/* If this quota has a hint attached, prepare for releasing it now */
+	gdqp = dqp->q_gdquot;
+	if (gdqp)
+		dqp->q_gdquot = NULL;
+
+	pdqp = dqp->q_pdquot;
+	if (pdqp)
+		dqp->q_pdquot = NULL;
+
+	xfs_dqunlock(dqp);
 
 	if (gdqp)
-		xfs_qm_dqput(gdqp);
+		xfs_qm_dqrele(gdqp);
 	if (pdqp)
-		xfs_qm_dqput(pdqp);
+		xfs_qm_dqrele(pdqp);
+
+	if (flags & XFS_QMOPT_UQUOTA)
+		return xfs_qm_dqpurge(dqp, NULL);
+
 	return 0;
 }
 
@@ -222,8 +241,18 @@ xfs_qm_dqpurge_all(
 	struct xfs_mount	*mp,
 	uint			flags)
 {
-	if (flags & XFS_QMOPT_UQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
+	/*
+	 * We have to release group/project dquot hint(s) from the user dquot
+	 * at first if they are there, otherwise we would run into an infinite
+	 * loop while walking through radix tree to purge other type of dquots
+	 * since their refcount is not zero if the user dquot refers to them
+	 * as hint.
+	 *
+	 * Call the special xfs_qm_dqpurge_hints() will end up go through the
+	 * general xfs_qm_dqpurge() against user dquot cache if requested.
+	 */
+	xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags);
+
 	if (flags & XFS_QMOPT_GQUOTA)
 		xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_PQUOTA)
@@ -2082,24 +2111,21 @@ xfs_qm_vop_create_dqattach(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
 
-	if (udqp) {
+	if (udqp && XFS_IS_UQUOTA_ON(mp)) {
 		ASSERT(ip->i_udquot == NULL);
-		ASSERT(XFS_IS_UQUOTA_ON(mp));
 		ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id));
 
 		ip->i_udquot = xfs_qm_dqhold(udqp);
 		xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
-	if (gdqp) {
+	if (gdqp && XFS_IS_GQUOTA_ON(mp)) {
 		ASSERT(ip->i_gdquot == NULL);
-		ASSERT(XFS_IS_GQUOTA_ON(mp));
 		ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id));
 		ip->i_gdquot = xfs_qm_dqhold(gdqp);
 		xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
-	if (pdqp) {
+	if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
 		ASSERT(ip->i_pdquot == NULL);
-		ASSERT(XFS_IS_PQUOTA_ON(mp));
 		ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id));
 
 		ip->i_pdquot = xfs_qm_dqhold(pdqp);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index c035d11b7734..647b6f1d8923 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -314,7 +314,18 @@ xfs_trans_read_buf_map(
 			ASSERT(bp->b_iodone == NULL);
 			XFS_BUF_READ(bp);
 			bp->b_ops = ops;
-			xfsbdstrat(tp->t_mountp, bp);
+
+			/*
+			 * XXX(hch): clean up the error handling here to be less
+			 * of a mess..
+			 */
+			if (XFS_FORCED_SHUTDOWN(mp)) {
+				trace_xfs_bdstrat_shut(bp, _RET_IP_);
+				xfs_bioerror_relse(bp);
+			} else {
+				xfs_buf_iorequest(bp);
+			}
+
 			error = xfs_buf_iowait(bp);
 			if (error) {
 				xfs_buf_ioerror_alert(bp, __func__);
author	Jens Axboe <axboe@kernel.dk>	2013-12-31 09:51:02 -0700
committer	Jens Axboe <axboe@kernel.dk>	2013-12-31 09:51:02 -0700
commit	b28bc9b38c52f63f43e3fd875af982f2240a2859 (patch)
tree	76cdb7b52b58f5685993cc15ed81d1c903023358 /fs
parent	8d30726912cb39c3a3ebde06214d54861f8fdde2 (diff)
parent	802eee95bde72fd0cd0f3a5b2098375a487d1eda (diff)
download	linux-b28bc9b38c52f63f43e3fd875af982f2240a2859.tar.bz2