1 files changed, 286 insertions, 179 deletions

diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 671085512e0f..51bde45d5865 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * inode.c - NILFS inode operations.
+ * NILFS inode operations.
  *
  * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
  *
@@ -14,6 +14,8 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/uio.h>
+#include <linux/fiemap.h>
+#include <linux/random.h>
 #include "nilfs.h"
 #include "btnode.h"
 #include "segment.h"
@@ -27,13 +29,13 @@
  * @ino: inode number
  * @cno: checkpoint number
  * @root: pointer on NILFS root object (mounted checkpoint)
- * @for_gc: inode for GC flag
+ * @type: inode type
  */
 struct nilfs_iget_args {
 	u64 ino;
 	__u64 cno;
 	struct nilfs_root *root;
-	int for_gc;
+	unsigned int type;
 };
 
 static int nilfs_iget_test(struct inode *inode, void *opaque);
@@ -58,14 +60,16 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
 
 /**
  * nilfs_get_block() - get a file block on the filesystem (callback function)
- * @inode - inode struct of the target file
- * @blkoff - file block number
- * @bh_result - buffer head to be mapped on
- * @create - indicate whether allocating the block or not when it has not
+ * @inode: inode struct of the target file
+ * @blkoff: file block number
+ * @bh_result: buffer head to be mapped on
+ * @create: indicate whether allocating the block or not when it has not
  *      been allocated yet.
  *
  * This function does not issue actual read request of the specified data
  * block. It is done by VFS.
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_get_block(struct inode *inode, sector_t blkoff,
 		    struct buffer_head *bh_result, int create)
@@ -103,11 +107,11 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
 				 * However, the page having this block must
 				 * be locked in this case.
 				 */
-				nilfs_msg(inode->i_sb, KERN_WARNING,
-					  "%s (ino=%lu): a race condition while inserting a data block at offset=%llu",
-					  __func__, inode->i_ino,
-					  (unsigned long long)blkoff);
-				err = 0;
+				nilfs_warn(inode->i_sb,
+					   "%s (ino=%lu): a race condition while inserting a data block at offset=%llu",
+					   __func__, inode->i_ino,
+					   (unsigned long long)blkoff);
+				err = -EAGAIN;
 			}
 			nilfs_transaction_abort(inode->i_sb);
 			goto out;
@@ -135,28 +139,21 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
 }
 
 /**
- * nilfs_readpage() - implement readpage() method of nilfs_aops {}
+ * nilfs_read_folio() - implement read_folio() method of nilfs_aops {}
  * address_space_operations.
- * @file - file struct of the file to be read
- * @page - the page to be read
+ * @file: file struct of the file to be read
+ * @folio: the folio to be read
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
-static int nilfs_readpage(struct file *file, struct page *page)
+static int nilfs_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, nilfs_get_block);
+	return mpage_read_folio(folio, nilfs_get_block);
 }
 
-/**
- * nilfs_readpages() - implement readpages() method of nilfs_aops {}
- * address_space_operations.
- * @file - file struct of the file to be read
- * @mapping - address_space struct used for reading multiple pages
- * @pages - the pages to be read
- * @nr_pages - number of pages to be read
- */
-static int nilfs_readpages(struct file *file, struct address_space *mapping,
-			   struct list_head *pages, unsigned int nr_pages)
+static void nilfs_readahead(struct readahead_control *rac)
 {
-	return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
+	mpage_readahead(rac, nilfs_get_block);
 }
 
 static int nilfs_writepages(struct address_space *mapping,
@@ -166,7 +163,7 @@ static int nilfs_writepages(struct address_space *mapping,
 	int err = 0;
 
 	if (sb_rdonly(inode->i_sb)) {
-		nilfs_clear_dirty_pages(mapping, false);
+		nilfs_clear_dirty_pages(mapping);
 		return -EROFS;
 	}
 
@@ -177,53 +174,22 @@ static int nilfs_writepages(struct address_space *mapping,
 	return err;
 }
 
-static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	int err;
-
-	if (sb_rdonly(inode->i_sb)) {
-		/*
-		 * It means that filesystem was remounted in read-only
-		 * mode because of error or metadata corruption. But we
-		 * have dirty pages that try to be flushed in background.
-		 * So, here we simply discard this dirty page.
-		 */
-		nilfs_clear_dirty_page(page, false);
-		unlock_page(page);
-		return -EROFS;
-	}
-
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-
-	if (wbc->sync_mode == WB_SYNC_ALL) {
-		err = nilfs_construct_segment(inode->i_sb);
-		if (unlikely(err))
-			return err;
-	} else if (wbc->for_reclaim)
-		nilfs_flush_segment(inode->i_sb, inode->i_ino);
-
-	return 0;
-}
-
-static int nilfs_set_page_dirty(struct page *page)
+static bool nilfs_dirty_folio(struct address_space *mapping,
+		struct folio *folio)
 {
-	struct inode *inode = page->mapping->host;
-	int ret = __set_page_dirty_nobuffers(page);
+	struct inode *inode = mapping->host;
+	struct buffer_head *head;
+	unsigned int nr_dirty = 0;
+	bool ret = filemap_dirty_folio(mapping, folio);
 
-	if (page_has_buffers(page)) {
-		unsigned int nr_dirty = 0;
-		struct buffer_head *bh, *head;
+	/*
+	 * The page may not be locked, eg if called from try_to_unmap_one()
+	 */
+	spin_lock(&mapping->i_private_lock);
+	head = folio_buffers(folio);
+	if (head) {
+		struct buffer_head *bh = head;
 
-		/*
-		 * This page is locked by callers, and no other thread
-		 * concurrently marks its buffers dirty since they are
-		 * only dirtied through routines in fs/buffer.c in
-		 * which call sites of mark_buffer_dirty are protected
-		 * by page lock.
-		 */
-		bh = head = page_buffers(page);
 		do {
 			/* Do not mark hole blocks dirty */
 			if (buffer_dirty(bh) || !buffer_mapped(bh))
@@ -232,14 +198,13 @@ static int nilfs_set_page_dirty(struct page *page)
 			set_buffer_dirty(bh);
 			nr_dirty++;
 		} while (bh = bh->b_this_page, bh != head);
-
-		if (nr_dirty)
-			nilfs_set_file_dirty(inode, nr_dirty);
 	} else if (ret) {
-		unsigned int nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
+		nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits);
+	}
+	spin_unlock(&mapping->i_private_lock);
 
+	if (nr_dirty)
 		nilfs_set_file_dirty(inode, nr_dirty);
-	}
 	return ret;
 }
 
@@ -253,9 +218,10 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int nilfs_write_begin(struct file *file, struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
-			     struct page **pagep, void **fsdata)
+static int nilfs_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata)
 
 {
 	struct inode *inode = mapping->host;
@@ -264,8 +230,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 	if (unlikely(err))
 		return err;
 
-	err = block_write_begin(mapping, pos, len, flags, pagep,
-				nilfs_get_block);
+	err = block_write_begin(mapping, pos, len, foliop, nilfs_get_block);
 	if (unlikely(err)) {
 		nilfs_write_failed(mapping, pos + len);
 		nilfs_transaction_abort(inode->i_sb);
@@ -273,18 +238,19 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 	return err;
 }
 
-static int nilfs_write_end(struct file *file, struct address_space *mapping,
+static int nilfs_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
-			   struct page *page, void *fsdata)
+			   struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	unsigned int start = pos & (PAGE_SIZE - 1);
 	unsigned int nr_dirty;
 	int err;
 
-	nr_dirty = nilfs_page_count_clean_buffers(page, start,
+	nr_dirty = nilfs_page_count_clean_buffers(folio, start,
 						  start + copied);
-	copied = generic_write_end(file, mapping, pos, len, copied, page,
+	copied = generic_write_end(iocb, mapping, pos, len, copied, folio,
 				   fsdata);
 	nilfs_set_file_dirty(inode, nr_dirty);
 	err = nilfs_transaction_commit(inode->i_sb);
@@ -304,25 +270,28 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 }
 
 const struct address_space_operations nilfs_aops = {
-	.writepage		= nilfs_writepage,
-	.readpage		= nilfs_readpage,
+	.read_folio		= nilfs_read_folio,
 	.writepages		= nilfs_writepages,
-	.set_page_dirty		= nilfs_set_page_dirty,
-	.readpages		= nilfs_readpages,
+	.dirty_folio		= nilfs_dirty_folio,
+	.readahead		= nilfs_readahead,
 	.write_begin		= nilfs_write_begin,
 	.write_end		= nilfs_write_end,
-	/* .releasepage		= nilfs_releasepage, */
-	.invalidatepage		= block_invalidatepage,
+	.invalidate_folio	= block_invalidate_folio,
 	.direct_IO		= nilfs_direct_IO,
+	.migrate_folio		= buffer_migrate_folio_norefs,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
 
+const struct address_space_operations nilfs_buffer_cache_aops = {
+	.invalidate_folio	= block_invalidate_folio,
+};
+
 static int nilfs_insert_inode_locked(struct inode *inode,
 				     struct nilfs_root *root,
 				     unsigned long ino)
 {
 	struct nilfs_iget_args args = {
-		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+		.ino = ino, .root = root, .cno = 0, .type = NILFS_I_TYPE_NORMAL
 	};
 
 	return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
@@ -331,10 +300,10 @@ static int nilfs_insert_inode_locked(struct inode *inode,
 struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
-	struct the_nilfs *nilfs = sb->s_fs_info;
 	struct inode *inode;
 	struct nilfs_inode_info *ii;
 	struct nilfs_root *root;
+	struct buffer_head *bh;
 	int err = -ENOMEM;
 	ino_t ino;
 
@@ -348,17 +317,19 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	root = NILFS_I(dir)->i_root;
 	ii = NILFS_I(inode);
 	ii->i_state = BIT(NILFS_I_NEW);
+	ii->i_type = NILFS_I_TYPE_NORMAL;
 	ii->i_root = root;
 
-	err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh);
+	err = nilfs_ifile_create_inode(root->ifile, &ino, &bh);
 	if (unlikely(err))
 		goto failed_ifile_create_inode;
 	/* reference count of i_bh inherits from nilfs_mdt_read_block() */
+	ii->i_bh = bh;
 
 	atomic64_inc(&root->inodes_count);
-	inode_init_owner(inode, dir, mode);
+	inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
 	inode->i_ino = ino;
-	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	simple_inode_init_ts(inode);
 
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		err = nilfs_bmap_read(ii->i_bmap, NULL);
@@ -376,9 +347,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	/* ii->i_dir_acl = 0; */
 	ii->i_dir_start_lookup = 0;
 	nilfs_set_inode_flags(inode);
-	spin_lock(&nilfs->ns_next_gen_lock);
-	inode->i_generation = nilfs->ns_next_generation++;
-	spin_unlock(&nilfs->ns_next_gen_lock);
+	inode->i_generation = get_random_u32();
 	if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
 		err = -EIO;
 		goto failed_after_creation;
@@ -396,7 +365,8 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 
  failed_after_creation:
 	clear_nlink(inode);
-	unlock_new_inode(inode);
+	if (inode_state_read_once(inode) & I_NEW)
+		unlock_new_inode(inode);
 	iput(inode);  /*
 		       * raw_inode will be deleted through
 		       * nilfs_evict_inode().
@@ -440,12 +410,14 @@ int nilfs_read_inode_common(struct inode *inode,
 	i_gid_write(inode, le32_to_cpu(raw_inode->i_gid));
 	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
 	inode->i_size = le64_to_cpu(raw_inode->i_size);
-	inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
-	inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
-	inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
-	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
-	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
+	inode_set_atime(inode, le64_to_cpu(raw_inode->i_mtime),
+			le32_to_cpu(raw_inode->i_mtime_nsec));
+	inode_set_ctime(inode, le64_to_cpu(raw_inode->i_ctime),
+			le32_to_cpu(raw_inode->i_ctime_nsec));
+	inode_set_mtime(inode, le64_to_cpu(raw_inode->i_mtime),
+			le32_to_cpu(raw_inode->i_mtime_nsec));
+	if (nilfs_is_metadata_file_inode(inode) && !S_ISREG(inode->i_mode))
+		return -EIO; /* this inode is for metadata and corrupted */
 	if (inode->i_nlink == 0)
 		return -ESTALE; /* this inode is deleted */
 
@@ -502,13 +474,20 @@ static int __nilfs_read_inode(struct super_block *sb,
 		inode->i_op = &nilfs_symlink_inode_operations;
 		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &nilfs_aops;
-	} else {
+	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
+		   S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
 		inode->i_op = &nilfs_special_inode_operations;
 		init_special_inode(
 			inode, inode->i_mode,
 			huge_decode_dev(le64_to_cpu(raw_inode->i_device_code)));
+	} else {
+		nilfs_error(sb,
+			    "invalid file type bits in mode 0%o for inode %lu",
+			    inode->i_mode, ino);
+		err = -EIO;
+		goto failed_unmap;
 	}
-	nilfs_ifile_unmap_inode(root->ifile, ino, bh);
+	nilfs_ifile_unmap_inode(raw_inode);
 	brelse(bh);
 	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
 	nilfs_set_inode_flags(inode);
@@ -517,7 +496,7 @@ static int __nilfs_read_inode(struct super_block *sb,
 	return 0;
 
  failed_unmap:
-	nilfs_ifile_unmap_inode(root->ifile, ino, bh);
+	nilfs_ifile_unmap_inode(raw_inode);
 	brelse(bh);
 
  bad_inode:
@@ -534,10 +513,10 @@ static int nilfs_iget_test(struct inode *inode, void *opaque)
 		return 0;
 
 	ii = NILFS_I(inode);
-	if (!test_bit(NILFS_I_GCINODE, &ii->i_state))
-		return !args->for_gc;
+	if (ii->i_type != args->type)
+		return 0;
 
-	return args->for_gc && args->cno == ii->i_cno;
+	return !(args->type & NILFS_I_TYPE_GC) || args->cno == ii->i_cno;
 }
 
 static int nilfs_iget_set(struct inode *inode, void *opaque)
@@ -545,15 +524,11 @@ static int nilfs_iget_set(struct inode *inode, void *opaque)
 	struct nilfs_iget_args *args = opaque;
 
 	inode->i_ino = args->ino;
-	if (args->for_gc) {
-		NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE);
-		NILFS_I(inode)->i_cno = args->cno;
-		NILFS_I(inode)->i_root = NULL;
-	} else {
-		if (args->root && args->ino == NILFS_ROOT_INO)
-			nilfs_get_root(args->root);
-		NILFS_I(inode)->i_root = args->root;
-	}
+	NILFS_I(inode)->i_cno = args->cno;
+	NILFS_I(inode)->i_root = args->root;
+	NILFS_I(inode)->i_type = args->type;
+	if (args->root && args->ino == NILFS_ROOT_INO)
+		nilfs_get_root(args->root);
 	return 0;
 }
 
@@ -561,7 +536,7 @@ struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
 			    unsigned long ino)
 {
 	struct nilfs_iget_args args = {
-		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+		.ino = ino, .root = root, .cno = 0, .type = NILFS_I_TYPE_NORMAL
 	};
 
 	return ilookup5(sb, ino, nilfs_iget_test, &args);
@@ -571,7 +546,7 @@ struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
 				unsigned long ino)
 {
 	struct nilfs_iget_args args = {
-		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+		.ino = ino, .root = root, .cno = 0, .type = NILFS_I_TYPE_NORMAL
 	};
 
 	return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
@@ -586,8 +561,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
 	inode = nilfs_iget_locked(sb, root, ino);
 	if (unlikely(!inode))
 		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW))
+
+	if (!(inode_state_read_once(inode) & I_NEW)) {
+		if (!inode->i_nlink) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
 		return inode;
+	}
 
 	err = __nilfs_read_inode(sb, root, ino, inode);
 	if (unlikely(err)) {
@@ -602,7 +583,7 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
 				__u64 cno)
 {
 	struct nilfs_iget_args args = {
-		.ino = ino, .root = NULL, .cno = cno, .for_gc = 1
+		.ino = ino, .root = NULL, .cno = cno, .type = NILFS_I_TYPE_GC
 	};
 	struct inode *inode;
 	int err;
@@ -610,7 +591,7 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
 	inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
 	if (unlikely(!inode))
 		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW))
+	if (!(inode_state_read_once(inode) & I_NEW))
 		return inode;
 
 	err = nilfs_init_gcinode(inode);
@@ -622,8 +603,118 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
 	return inode;
 }
 
+/**
+ * nilfs_attach_btree_node_cache - attach a B-tree node cache to the inode
+ * @inode: inode object
+ *
+ * nilfs_attach_btree_node_cache() attaches a B-tree node cache to @inode,
+ * or does nothing if the inode already has it.  This function allocates
+ * an additional inode to maintain page cache of B-tree nodes one-on-one.
+ *
+ * Return: 0 on success, or %-ENOMEM if memory is insufficient.
+ */
+int nilfs_attach_btree_node_cache(struct inode *inode)
+{
+	struct nilfs_inode_info *ii = NILFS_I(inode);
+	struct inode *btnc_inode;
+	struct nilfs_iget_args args;
+
+	if (ii->i_assoc_inode)
+		return 0;
+
+	args.ino = inode->i_ino;
+	args.root = ii->i_root;
+	args.cno = ii->i_cno;
+	args.type = ii->i_type | NILFS_I_TYPE_BTNC;
+
+	btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test,
+				  nilfs_iget_set, &args);
+	if (unlikely(!btnc_inode))
+		return -ENOMEM;
+	if (inode_state_read_once(btnc_inode) & I_NEW) {
+		nilfs_init_btnc_inode(btnc_inode);
+		unlock_new_inode(btnc_inode);
+	}
+	NILFS_I(btnc_inode)->i_assoc_inode = inode;
+	NILFS_I(btnc_inode)->i_bmap = ii->i_bmap;
+	ii->i_assoc_inode = btnc_inode;
+
+	return 0;
+}
+
+/**
+ * nilfs_detach_btree_node_cache - detach the B-tree node cache from the inode
+ * @inode: inode object
+ *
+ * nilfs_detach_btree_node_cache() detaches the B-tree node cache and its
+ * holder inode bound to @inode, or does nothing if @inode doesn't have it.
+ */
+void nilfs_detach_btree_node_cache(struct inode *inode)
+{
+	struct nilfs_inode_info *ii = NILFS_I(inode);
+	struct inode *btnc_inode = ii->i_assoc_inode;
+
+	if (btnc_inode) {
+		NILFS_I(btnc_inode)->i_assoc_inode = NULL;
+		ii->i_assoc_inode = NULL;
+		iput(btnc_inode);
+	}
+}
+
+/**
+ * nilfs_iget_for_shadow - obtain inode for shadow mapping
+ * @inode: inode object that uses shadow mapping
+ *
+ * nilfs_iget_for_shadow() allocates a pair of inodes that holds page
+ * caches for shadow mapping.  The page cache for data pages is set up
+ * in one inode and the one for b-tree node pages is set up in the
+ * other inode, which is attached to the former inode.
+ *
+ * Return: a pointer to the inode for data pages on success, or %-ENOMEM
+ * if memory is insufficient.
+ */
+struct inode *nilfs_iget_for_shadow(struct inode *inode)
+{
+	struct nilfs_iget_args args = {
+		.ino = inode->i_ino, .root = NULL, .cno = 0,
+		.type = NILFS_I_TYPE_SHADOW
+	};
+	struct inode *s_inode;
+	int err;
+
+	s_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test,
+			       nilfs_iget_set, &args);
+	if (unlikely(!s_inode))
+		return ERR_PTR(-ENOMEM);
+	if (!(inode_state_read_once(s_inode) & I_NEW))
+		return inode;
+
+	NILFS_I(s_inode)->i_flags = 0;
+	memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap));
+	mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS);
+	s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
+
+	err = nilfs_attach_btree_node_cache(s_inode);
+	if (unlikely(err)) {
+		iget_failed(s_inode);
+		return ERR_PTR(err);
+	}
+	unlock_new_inode(s_inode);
+	return s_inode;
+}
+
+/**
+ * nilfs_write_inode_common - export common inode information to on-disk inode
+ * @inode:     inode object
+ * @raw_inode: on-disk inode
+ *
+ * This function writes standard information from the on-memory inode @inode
+ * to @raw_inode on ifile, cpfile or a super root block.  Since inode bmap
+ * data is not exported, nilfs_bmap_write() must be called separately during
+ * log writing.
+ */
 void nilfs_write_inode_common(struct inode *inode,
-			      struct nilfs_inode *raw_inode, int has_bmap)
+			      struct nilfs_inode *raw_inode)
 {
 	struct nilfs_inode_info *ii = NILFS_I(inode);
 
@@ -632,30 +723,15 @@ void nilfs_write_inode_common(struct inode *inode,
 	raw_inode->i_gid = cpu_to_le32(i_gid_read(inode));
 	raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
 	raw_inode->i_size = cpu_to_le64(inode->i_size);
-	raw_inode->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
-	raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
-	raw_inode->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
-	raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+	raw_inode->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode));
+	raw_inode->i_mtime = cpu_to_le64(inode_get_mtime_sec(inode));
+	raw_inode->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
+	raw_inode->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode));
 	raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);
 
 	raw_inode->i_flags = cpu_to_le32(ii->i_flags);
 	raw_inode->i_generation = cpu_to_le32(inode->i_generation);
 
-	if (NILFS_ROOT_METADATA_FILE(inode->i_ino)) {
-		struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
-
-		/* zero-fill unused portion in the case of super root block */
-		raw_inode->i_xattr = 0;
-		raw_inode->i_pad = 0;
-		memset((void *)raw_inode + sizeof(*raw_inode), 0,
-		       nilfs->ns_inode_size - sizeof(*raw_inode));
-	}
-
-	if (has_bmap)
-		nilfs_bmap_write(ii->i_bmap, raw_inode);
-	else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
-		raw_inode->i_device_code =
-			cpu_to_le64(huge_encode_dev(inode->i_rdev));
 	/*
 	 * When extending inode, nilfs->ns_inode_size should be checked
 	 * for substitutions of appended fields.
@@ -676,14 +752,13 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags)
 	if (flags & I_DIRTY_DATASYNC)
 		set_bit(NILFS_I_INODE_SYNC, &ii->i_state);
 
-	nilfs_write_inode_common(inode, raw_inode, 0);
-		/*
-		 * XXX: call with has_bmap = 0 is a workaround to avoid
-		 * deadlock of bmap.  This delays update of i_bmap to just
-		 * before writing.
-		 */
+	nilfs_write_inode_common(inode, raw_inode);
+
+	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
+		raw_inode->i_device_code =
+			cpu_to_le64(huge_encode_dev(inode->i_rdev));
 
-	nilfs_ifile_unmap_inode(ifile, ino, ibh);
+	nilfs_ifile_unmap_inode(raw_inode);
 }
 
 #define NILFS_MAX_TRUNCATE_BLOCKS	16384  /* 64MB for 4KB block */
@@ -714,9 +789,8 @@ repeat:
 		goto repeat;
 
 failed:
-	nilfs_msg(ii->vfs_inode.i_sb, KERN_WARNING,
-		  "error %d truncating bmap (ino=%lu)", ret,
-		  ii->vfs_inode.i_ino);
+	nilfs_warn(ii->vfs_inode.i_sb, "error %d truncating bmap (ino=%lu)",
+		   ret, ii->vfs_inode.i_ino);
 }
 
 void nilfs_truncate(struct inode *inode)
@@ -740,7 +814,7 @@ void nilfs_truncate(struct inode *inode)
 
 	nilfs_truncate_bmap(ii, blkoff);
 
-	inode->i_mtime = inode->i_ctime = current_time(inode);
+	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	if (IS_SYNC(inode))
 		nilfs_set_transaction_flag(NILFS_TI_SYNC);
 
@@ -770,7 +844,8 @@ static void nilfs_clear_inode(struct inode *inode)
 	if (test_bit(NILFS_I_BMAP, &ii->i_state))
 		nilfs_bmap_clear(ii->i_bmap);
 
-	nilfs_btnode_cache_clear(&ii->i_btnode_cache);
+	if (!(ii->i_type & NILFS_I_TYPE_BTNC))
+		nilfs_detach_btree_node_cache(inode);
 
 	if (ii->i_root && inode->i_ino == NILFS_ROOT_INO)
 		nilfs_put_root(ii->i_root);
@@ -781,6 +856,7 @@ void nilfs_evict_inode(struct inode *inode)
 	struct nilfs_transaction_info ti;
 	struct super_block *sb = inode->i_sb;
 	struct nilfs_inode_info *ii = NILFS_I(inode);
+	struct the_nilfs *nilfs;
 	int ret;
 
 	if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
@@ -793,6 +869,23 @@ void nilfs_evict_inode(struct inode *inode)
 
 	truncate_inode_pages_final(&inode->i_data);
 
+	nilfs = sb->s_fs_info;
+	if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) {
+		/*
+		 * If this inode is about to be disposed after the file system
+		 * has been degraded to read-only due to file system corruption
+		 * or after the writer has been detached, do not make any
+		 * changes that cause writes, just clear it.
+		 * Do this check after read-locking ns_segctor_sem by
+		 * nilfs_transaction_begin() in order to avoid a race with
+		 * the writer detach operation.
+		 */
+		clear_inode(inode);
+		nilfs_clear_inode(inode);
+		nilfs_transaction_abort(sb);
+		return;
+	}
+
 	/* TODO: some of the following operations may fail.  */
 	nilfs_truncate_bmap(ii, 0);
 	nilfs_mark_inode_dirty(inode);
@@ -813,14 +906,15 @@ void nilfs_evict_inode(struct inode *inode)
 	 */
 }
 
-int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
+int nilfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		  struct iattr *iattr)
 {
 	struct nilfs_transaction_info ti;
 	struct inode *inode = d_inode(dentry);
 	struct super_block *sb = inode->i_sb;
 	int err;
 
-	err = setattr_prepare(dentry, iattr);
+	err = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
 	if (err)
 		return err;
 
@@ -835,7 +929,7 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
 		nilfs_truncate(inode);
 	}
 
-	setattr_copy(inode, iattr);
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
 	mark_inode_dirty(inode);
 
 	if (iattr->ia_valid & ATTR_MODE) {
@@ -851,7 +945,8 @@ out_err:
 	return err;
 }
 
-int nilfs_permission(struct inode *inode, int mask)
+int nilfs_permission(struct mnt_idmap *idmap, struct inode *inode,
+		     int mask)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
@@ -859,7 +954,7 @@ int nilfs_permission(struct inode *inode, int mask)
 	    root->cno != NILFS_CPTREE_CURRENT_CNO)
 		return -EROFS; /* snapshot is not writable */
 
-	return generic_permission(inode, mask);
+	return generic_permission(&nop_mnt_idmap, inode, mask);
 }
 
 int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
@@ -869,7 +964,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
 	int err;
 
 	spin_lock(&nilfs->ns_inode_lock);
-	if (ii->i_bh == NULL) {
+	if (ii->i_bh == NULL || unlikely(!buffer_uptodate(ii->i_bh))) {
 		spin_unlock(&nilfs->ns_inode_lock);
 		err = nilfs_ifile_get_inode_block(ii->i_root->ifile,
 						  inode->i_ino, pbh);
@@ -878,7 +973,10 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
 		spin_lock(&nilfs->ns_inode_lock);
 		if (ii->i_bh == NULL)
 			ii->i_bh = *pbh;
-		else {
+		else if (unlikely(!buffer_uptodate(ii->i_bh))) {
+			__brelse(ii->i_bh);
+			ii->i_bh = *pbh;
+		} else {
 			brelse(*pbh);
 			*pbh = ii->i_bh;
 		}
@@ -927,9 +1025,9 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
 			 * This will happen when somebody is freeing
 			 * this inode.
 			 */
-			nilfs_msg(inode->i_sb, KERN_WARNING,
-				  "cannot set file dirty (ino=%lu): the file is being freed",
-				  inode->i_ino);
+			nilfs_warn(inode->i_sb,
+				   "cannot set file dirty (ino=%lu): the file is being freed",
+				   inode->i_ino);
 			spin_unlock(&nilfs->ns_inode_lock);
 			return -EINVAL; /*
 					 * NILFS_I_DIRTY may remain for
@@ -945,14 +1043,22 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
 
 int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 {
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 	struct buffer_head *ibh;
 	int err;
 
+	/*
+	 * Do not dirty inodes after the log writer has been detached
+	 * and its nilfs_root struct has been freed.
+	 */
+	if (unlikely(nilfs_purging(nilfs)))
+		return 0;
+
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "cannot mark inode dirty (ino=%lu): error %d loading inode block",
-			  inode->i_ino, err);
+		nilfs_warn(inode->i_sb,
+			   "cannot mark inode dirty (ino=%lu): error %d loading inode block",
+			   inode->i_ino, err);
 		return err;
 	}
 	nilfs_update_inode(inode, ibh, flags);
@@ -965,6 +1071,7 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 /**
  * nilfs_dirty_inode - reflect changes on given inode to an inode block.
  * @inode: inode of the file to be registered.
+ * @flags: flags to determine the dirty state of the inode
  *
  * nilfs_dirty_inode() loads a inode block containing the specified
  * @inode and copies data from a nilfs_inode to a corresponding inode
@@ -978,8 +1085,8 @@ void nilfs_dirty_inode(struct inode *inode, int flags)
 	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
 
 	if (is_bad_inode(inode)) {
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "tried to mark bad_inode dirty. ignored.");
+		nilfs_warn(inode->i_sb,
+			   "tried to mark bad_inode dirty. ignored.");
 		dump_stack();
 		return;
 	}
@@ -1005,7 +1112,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	unsigned int blkbits = inode->i_blkbits;
 	int ret, n;
 
-	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
 	if (ret)
 		return ret;
 
@@ -1088,7 +1195,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			if (size) {
 				if (phys && blkphy << blkbits == phys + size) {
 					/* The current extent goes on */
-					size += n << blkbits;
+					size += (u64)n << blkbits;
 				} else {
 					/* Terminate the current extent */
 					ret = fiemap_fill_next_extent(
@@ -1101,14 +1208,14 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 					flags = FIEMAP_EXTENT_MERGED;
 					logical = blkoff << blkbits;
 					phys = blkphy << blkbits;
-					size = n << blkbits;
+					size = (u64)n << blkbits;
 				}
 			} else {
 				/* Start a new extent */
 				flags = FIEMAP_EXTENT_MERGED;
 				logical = blkoff << blkbits;
 				phys = blkphy << blkbits;
-				size = n << blkbits;
+				size = (u64)n << blkbits;
 			}
 			blkoff += n;
 		}