1 files changed, 225 insertions, 86 deletions

diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 671085512e0f..232dd7b6cca1 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 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/uio.h>
+#include <linux/fiemap.h>
 #include "nilfs.h"
 #include "btnode.h"
 #include "segment.h"
@@ -28,12 +29,16 @@
  * @cno: checkpoint number
  * @root: pointer on NILFS root object (mounted checkpoint)
  * @for_gc: inode for GC flag
+ * @for_btnc: inode for B-tree node cache flag
+ * @for_shadow: inode for shadowed page cache flag
  */
 struct nilfs_iget_args {
 	u64 ino;
 	__u64 cno;
 	struct nilfs_root *root;
-	int for_gc;
+	bool for_gc;
+	bool for_btnc;
+	bool for_shadow;
 };
 
 static int nilfs_iget_test(struct inode *inode, void *opaque);
@@ -58,10 +63,10 @@ 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
@@ -103,10 +108,10 @@ 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);
+				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 = 0;
 			}
 			nilfs_transaction_abort(inode->i_sb);
@@ -135,28 +140,19 @@ 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
  */
-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,
@@ -207,23 +203,22 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 	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->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 +227,13 @@ 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->private_lock);
 
+	if (nr_dirty)
 		nilfs_set_file_dirty(inode, nr_dirty);
-	}
 	return ret;
 }
 
@@ -254,7 +248,7 @@ 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,
+			     loff_t pos, unsigned len,
 			     struct page **pagep, void **fsdata)
 
 {
@@ -264,8 +258,7 @@ 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, pagep, nilfs_get_block);
 	if (unlikely(err)) {
 		nilfs_write_failed(mapping, pos + len);
 		nilfs_transaction_abort(inode->i_sb);
@@ -305,14 +298,13 @@ 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,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
@@ -322,7 +314,8 @@ static int nilfs_insert_inode_locked(struct inode *inode,
 				     unsigned long ino)
 {
 	struct nilfs_iget_args args = {
-		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+		.ino = ino, .root = root, .cno = 0, .for_gc = false,
+		.for_btnc = false, .for_shadow = false
 	};
 
 	return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
@@ -335,6 +328,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	struct inode *inode;
 	struct nilfs_inode_info *ii;
 	struct nilfs_root *root;
+	struct buffer_head *bh;
 	int err = -ENOMEM;
 	ino_t ino;
 
@@ -350,13 +344,27 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	ii->i_state = BIT(NILFS_I_NEW);
 	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() */
 
+	if (unlikely(ino < NILFS_USER_INO)) {
+		nilfs_warn(sb,
+			   "inode bitmap is inconsistent for reserved inodes");
+		do {
+			brelse(bh);
+			err = nilfs_ifile_create_inode(root->ifile, &ino, &bh);
+			if (unlikely(err))
+				goto failed_ifile_create_inode;
+		} while (ino < NILFS_USER_INO);
+
+		nilfs_info(sb, "repaired inode bitmap for reserved inodes");
+	}
+	ii->i_bh = bh;
+
 	atomic64_inc(&root->inodes_count);
-	inode_init_owner(inode, dir, mode);
+	inode_init_owner(&init_user_ns, inode, dir, mode);
 	inode->i_ino = ino;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 
@@ -396,7 +404,8 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 
  failed_after_creation:
 	clear_nlink(inode);
-	unlock_new_inode(inode);
+	if (inode->i_state & I_NEW)
+		unlock_new_inode(inode);
 	iput(inode);  /*
 		       * raw_inode will be deleted through
 		       * nilfs_evict_inode().
@@ -446,6 +455,8 @@ int nilfs_read_inode_common(struct inode *inode,
 	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);
+	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 */
 
@@ -534,6 +545,19 @@ static int nilfs_iget_test(struct inode *inode, void *opaque)
 		return 0;
 
 	ii = NILFS_I(inode);
+	if (test_bit(NILFS_I_BTNC, &ii->i_state)) {
+		if (!args->for_btnc)
+			return 0;
+	} else if (args->for_btnc) {
+		return 0;
+	}
+	if (test_bit(NILFS_I_SHADOW, &ii->i_state)) {
+		if (!args->for_shadow)
+			return 0;
+	} else if (args->for_shadow) {
+		return 0;
+	}
+
 	if (!test_bit(NILFS_I_GCINODE, &ii->i_state))
 		return !args->for_gc;
 
@@ -545,15 +569,17 @@ 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_cno = args->cno;
+	NILFS_I(inode)->i_root = args->root;
+	if (args->root && args->ino == NILFS_ROOT_INO)
+		nilfs_get_root(args->root);
+
+	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;
-	}
+	if (args->for_btnc)
+		NILFS_I(inode)->i_state |= BIT(NILFS_I_BTNC);
+	if (args->for_shadow)
+		NILFS_I(inode)->i_state |= BIT(NILFS_I_SHADOW);
 	return 0;
 }
 
@@ -561,7 +587,8 @@ 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, .for_gc = false,
+		.for_btnc = false, .for_shadow = false
 	};
 
 	return ilookup5(sb, ino, nilfs_iget_test, &args);
@@ -571,7 +598,8 @@ 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, .for_gc = false,
+		.for_btnc = false, .for_shadow = false
 	};
 
 	return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
@@ -602,7 +630,8 @@ 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, .for_gc = true,
+		.for_btnc = false, .for_shadow = false
 	};
 	struct inode *inode;
 	int err;
@@ -622,6 +651,113 @@ 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 Value: On success, 0 is returned. On errors, one of the following
+ * negative error code is returned.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ */
+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.for_gc = test_bit(NILFS_I_GCINODE, &ii->i_state) != 0;
+	args.for_btnc = true;
+	args.for_shadow = test_bit(NILFS_I_SHADOW, &ii->i_state) != 0;
+
+	btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test,
+				  nilfs_iget_set, &args);
+	if (unlikely(!btnc_inode))
+		return -ENOMEM;
+	if (btnc_inode->i_state & 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 Value: On success, a pointer to the inode for data pages is
+ * returned. On errors, one of the following negative error code is returned
+ * in a pointer type.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ */
+struct inode *nilfs_iget_for_shadow(struct inode *inode)
+{
+	struct nilfs_iget_args args = {
+		.ino = inode->i_ino, .root = NULL, .cno = 0, .for_gc = false,
+		.for_btnc = false, .for_shadow = true
+	};
+	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 (!(s_inode->i_state & 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);
+
+	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;
+}
+
 void nilfs_write_inode_common(struct inode *inode,
 			      struct nilfs_inode *raw_inode, int has_bmap)
 {
@@ -714,9 +850,8 @@ 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)
@@ -770,7 +905,8 @@ 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 (!test_bit(NILFS_I_BTNC, &ii->i_state))
+		nilfs_detach_btree_node_cache(inode);
 
 	if (ii->i_root && inode->i_ino == NILFS_ROOT_INO)
 		nilfs_put_root(ii->i_root);
@@ -813,14 +949,15 @@ void nilfs_evict_inode(struct inode *inode)
 	 */
 }
 
-int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
+int nilfs_setattr(struct user_namespace *mnt_userns, 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(&init_user_ns, dentry, iattr);
 	if (err)
 		return err;
 
@@ -835,7 +972,7 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
 		nilfs_truncate(inode);
 	}
 
-	setattr_copy(inode, iattr);
+	setattr_copy(&init_user_ns, inode, iattr);
 	mark_inode_dirty(inode);
 
 	if (iattr->ia_valid & ATTR_MODE) {
@@ -851,7 +988,8 @@ out_err:
 	return err;
 }
 
-int nilfs_permission(struct inode *inode, int mask)
+int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+		     int mask)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
@@ -859,7 +997,7 @@ 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(&init_user_ns, inode, mask);
 }
 
 int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
@@ -927,9 +1065,9 @@ 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
@@ -950,9 +1088,9 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 
 	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 +1103,7 @@ 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 +1117,8 @@ 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 +1144,7 @@ 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;