1 files changed, 69 insertions, 66 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9d9f414f99fe..bf0b7dea4900 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -786,11 +786,10 @@ static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
 	 * once we get rid of using bh as a container for mapping information
 	 * to pass to / from get_block functions, this can go away.
 	 */
+	old_state = READ_ONCE(bh->b_state);
 	do {
-		old_state = READ_ONCE(bh->b_state);
 		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
-	} while (unlikely(
-		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+	} while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state)));
 }
 
 static int _ext4_get_block(struct inode *inode, sector_t iblock,
@@ -1136,7 +1135,8 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 		for (i = 0; i < nr_wait; i++) {
 			int err2;
 
-			err2 = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+			err2 = fscrypt_decrypt_pagecache_blocks(page_folio(page),
+								blocksize,
 								bh_offset(wait[i]));
 			if (err2) {
 				clear_buffer_uptodate(wait[i]);
@@ -2595,8 +2595,8 @@ static bool ext4_page_nomap_can_writeout(struct page *page)
 static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 {
 	struct address_space *mapping = mpd->inode->i_mapping;
-	struct pagevec pvec;
-	unsigned int nr_pages;
+	struct folio_batch fbatch;
+	unsigned int nr_folios;
 	long left = mpd->wbc->nr_to_write;
 	pgoff_t index = mpd->first_page;
 	pgoff_t end = mpd->last_page;
@@ -2610,18 +2610,17 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
-
-	pagevec_init(&pvec);
+	folio_batch_init(&fbatch);
 	mpd->map.m_len = 0;
 	mpd->next_page = index;
 	while (index <= end) {
-		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
-				tag);
-		if (nr_pages == 0)
+		nr_folios = filemap_get_folios_tag(mapping, &index, end,
+				tag, &fbatch);
+		if (nr_folios == 0)
 			break;
 
-		for (i = 0; i < nr_pages; i++) {
-			struct page *page = pvec.pages[i];
+		for (i = 0; i < nr_folios; i++) {
+			struct folio *folio = fbatch.folios[i];
 
 			/*
 			 * Accumulated enough dirty pages? This doesn't apply
@@ -2635,10 +2634,10 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 				goto out;
 
 			/* If we can't merge this page, we are done. */
-			if (mpd->map.m_len > 0 && mpd->next_page != page->index)
+			if (mpd->map.m_len > 0 && mpd->next_page != folio->index)
 				goto out;
 
-			lock_page(page);
+			folio_lock(folio);
 			/*
 			 * If the page is no longer dirty, or its mapping no
 			 * longer corresponds to inode we are writing (which
@@ -2646,16 +2645,16 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			 * page is already under writeback and we are not doing
 			 * a data integrity writeback, skip the page
 			 */
-			if (!PageDirty(page) ||
-			    (PageWriteback(page) &&
+			if (!folio_test_dirty(folio) ||
+			    (folio_test_writeback(folio) &&
 			     (mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
-			    unlikely(page->mapping != mapping)) {
-				unlock_page(page);
+			    unlikely(folio->mapping != mapping)) {
+				folio_unlock(folio);
 				continue;
 			}
 
-			wait_on_page_writeback(page);
-			BUG_ON(PageWriteback(page));
+			folio_wait_writeback(folio);
+			BUG_ON(folio_test_writeback(folio));
 
 			/*
 			 * Should never happen but for buggy code in
@@ -2666,56 +2665,56 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			 *
 			 * [1] https://lore.kernel.org/linux-mm/[email protected]
 			 */
-			if (!page_has_buffers(page)) {
-				ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index);
-				ClearPageDirty(page);
-				unlock_page(page);
+			if (!folio_buffers(folio)) {
+				ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", folio->index);
+				folio_clear_dirty(folio);
+				folio_unlock(folio);
 				continue;
 			}
 
 			if (mpd->map.m_len == 0)
-				mpd->first_page = page->index;
-			mpd->next_page = page->index + 1;
+				mpd->first_page = folio->index;
+			mpd->next_page = folio->index + folio_nr_pages(folio);
 			/*
 			 * Writeout for transaction commit where we cannot
 			 * modify metadata is simple. Just submit the page.
 			 */
 			if (!mpd->can_map) {
-				if (ext4_page_nomap_can_writeout(page)) {
-					err = mpage_submit_page(mpd, page);
+				if (ext4_page_nomap_can_writeout(&folio->page)) {
+					err = mpage_submit_page(mpd, &folio->page);
 					if (err < 0)
 						goto out;
 				} else {
-					unlock_page(page);
-					mpd->first_page++;
+					folio_unlock(folio);
+					mpd->first_page += folio_nr_pages(folio);
 				}
 			} else {
 				/* Add all dirty buffers to mpd */
-				lblk = ((ext4_lblk_t)page->index) <<
+				lblk = ((ext4_lblk_t)folio->index) <<
 					(PAGE_SHIFT - blkbits);
-				head = page_buffers(page);
+				head = folio_buffers(folio);
 				err = mpage_process_page_bufs(mpd, head, head,
-							      lblk);
+						lblk);
 				if (err <= 0)
 					goto out;
 				err = 0;
 			}
-			left--;
+			left -= folio_nr_pages(folio);
 		}
-		pagevec_release(&pvec);
+		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 	mpd->scanned_until_end = 1;
 	return 0;
 out:
-	pagevec_release(&pvec);
+	folio_batch_release(&fbatch);
 	return err;
 }
 
-static int ext4_writepage_cb(struct page *page, struct writeback_control *wbc,
+static int ext4_writepage_cb(struct folio *folio, struct writeback_control *wbc,
 			     void *data)
 {
-	return ext4_writepage(page, wbc);
+	return ext4_writepage(&folio->page, wbc);
 }
 
 static int ext4_do_writepages(struct mpage_da_data *mpd)
@@ -3858,7 +3857,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
 			/* We expect the key to be set. */
 			BUG_ON(!fscrypt_has_encryption_key(inode));
-			err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+			err = fscrypt_decrypt_pagecache_blocks(page_folio(page),
+							       blocksize,
 							       bh_offset(bh));
 			if (err) {
 				clear_buffer_uptodate(bh);
@@ -4797,8 +4797,13 @@ static inline int ext4_iget_extra_inode(struct inode *inode,
 
 	if (EXT4_INODE_HAS_XATTR_SPACE(inode)  &&
 	    *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
+		int err;
+
 		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
-		return ext4_find_inline_data_nolock(inode);
+		err = ext4_find_inline_data_nolock(inode);
+		if (!err && ext4_has_inline_data(inode))
+			ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+		return err;
 	} else
 		EXT4_I(inode)->i_inline_off = 0;
 	return 0;
@@ -4872,13 +4877,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
 
-	if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) {
-		ext4_error_inode(inode, function, line, 0,
-				 "iget: root inode unallocated");
-		ret = -EFSCORRUPTED;
-		goto bad_inode;
-	}
-
 	if ((flags & EXT4_IGET_HANDLE) &&
 	    (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) {
 		ret = -ESTALE;
@@ -4951,11 +4949,16 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	 * NeilBrown 1999oct15
 	 */
 	if (inode->i_nlink == 0) {
-		if ((inode->i_mode == 0 ||
+		if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL ||
 		     !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
 		    ino != EXT4_BOOT_LOADER_INO) {
-			/* this inode is deleted */
-			ret = -ESTALE;
+			/* this inode is deleted or unallocated */
+			if (flags & EXT4_IGET_SPECIAL) {
+				ext4_error_inode(inode, function, line, 0,
+						 "iget: special inode unallocated");
+				ret = -EFSCORRUPTED;
+			} else
+				ret = -ESTALE;
 			goto bad_inode;
 		}
 		/* The only unlinked inodes we let through here have
@@ -5434,7 +5437,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
  *
  * Called with inode->i_rwsem down.
  */
-int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -5454,7 +5457,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				  ATTR_GID | ATTR_TIMES_SET))))
 		return -EPERM;
 
-	error = setattr_prepare(mnt_userns, dentry, attr);
+	error = setattr_prepare(idmap, dentry, attr);
 	if (error)
 		return error;
 
@@ -5466,14 +5469,14 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (error)
 		return error;
 
-	if (is_quota_modification(mnt_userns, inode, attr)) {
+	if (is_quota_modification(idmap, inode, attr)) {
 		error = dquot_initialize(inode);
 		if (error)
 			return error;
 	}
 
-	if (i_uid_needs_update(mnt_userns, attr, inode) ||
-	    i_gid_needs_update(mnt_userns, attr, inode)) {
+	if (i_uid_needs_update(idmap, attr, inode) ||
+	    i_gid_needs_update(idmap, attr, inode)) {
 		handle_t *handle;
 
 		/* (user+group)*(old+new) structure, inode write (sb,
@@ -5490,7 +5493,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		 * counts xattr inode references.
 		 */
 		down_read(&EXT4_I(inode)->xattr_sem);
-		error = dquot_transfer(mnt_userns, inode, attr);
+		error = dquot_transfer(idmap, inode, attr);
 		up_read(&EXT4_I(inode)->xattr_sem);
 
 		if (error) {
@@ -5499,8 +5502,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		}
 		/* Update corresponding info in inode so that everything is in
 		 * one transaction */
-		i_uid_update(mnt_userns, attr, inode);
-		i_gid_update(mnt_userns, attr, inode);
+		i_uid_update(idmap, attr, inode);
+		i_gid_update(idmap, attr, inode);
 		error = ext4_mark_inode_dirty(handle, inode);
 		ext4_journal_stop(handle);
 		if (unlikely(error)) {
@@ -5630,7 +5633,7 @@ out_mmap_sem:
 	if (!error) {
 		if (inc_ivers)
 			inode_inc_iversion(inode);
-		setattr_copy(mnt_userns, inode, attr);
+		setattr_copy(idmap, inode, attr);
 		mark_inode_dirty(inode);
 	}
 
@@ -5642,7 +5645,7 @@ out_mmap_sem:
 		ext4_orphan_del(NULL, inode);
 
 	if (!error && (ia_valid & ATTR_MODE))
-		rc = posix_acl_chmod(mnt_userns, dentry, inode->i_mode);
+		rc = posix_acl_chmod(idmap, dentry, inode->i_mode);
 
 err_out:
 	if  (error)
@@ -5668,7 +5671,7 @@ u32 ext4_dio_alignment(struct inode *inode)
 	return 1; /* use the iomap defaults */
 }
 
-int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
+int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
@@ -5725,18 +5728,18 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 				  STATX_ATTR_NODUMP |
 				  STATX_ATTR_VERITY);
 
-	generic_fillattr(mnt_userns, inode, stat);
+	generic_fillattr(idmap, inode, stat);
 	return 0;
 }
 
-int ext4_file_getattr(struct user_namespace *mnt_userns,
+int ext4_file_getattr(struct mnt_idmap *idmap,
 		      const struct path *path, struct kstat *stat,
 		      u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
 	u64 delalloc_blocks;
 
-	ext4_getattr(mnt_userns, path, stat, request_mask, query_flags);
+	ext4_getattr(idmap, path, stat, request_mask, query_flags);
 
 	/*
 	 * If there is inline data in the inode, the inode will normally not
@@ -5788,7 +5791,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
 	ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
 	int gdpblocks;
 	int idxblocks;
-	int ret = 0;
+	int ret;
 
 	/*
 	 * How many index blocks need to touch to map @lblocks logical blocks