Merge tag 'fs_for_v6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull misc filesystem updates from Jan Kara:

 - Rewrite kmap_local() handling in ext2

 - Convert ext2 direct IO path to iomap (with some infrastructure tweaks
   associated with that)

 - Convert two boilerplate licenses in udf to SPDX identifiers

 - Other small udf, ext2, and quota fixes and cleanups

* tag 'fs_for_v6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  udf: Fix uninitialized array access for some pathnames
  ext2: Drop fragment support
  quota: fix warning in dqgrab()
  quota: Properly disable quotas when add_dquot_ref() fails
  fs: udf: udftime: Replace LGPL boilerplate with SPDX identifier
  fs: udf: Replace GPL 2.0 boilerplate license notice with SPDX identifier
  fs: Drop wait_unfrozen wait queue
  ext2_find_entry()/ext2_dotdot(): callers don't need page_addr anymore
  ext2_{set_link,delete_entry}(): don't bother with page_addr
  ext2_put_page(): accept any pointer within the page
  ext2_get_page(): saner type
  ext2: use offset_in_page() instead of open-coding it as subtraction
  ext2_rename(): set_link and delete_entry may fail
  ext2: Add direct-io trace points
  ext2: Move direct-io to use iomap
  ext2: Use generic_buffers_fsync() implementation
  ext4: Use generic_buffers_fsync_noflush() implementation
  fs/buffer.c: Add generic_buffers_fsync*() implementation
  ext2/dax: Fix ext2_setsize when len is page aligned

9 files changed, 356 insertions, 178 deletions

diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
index 311479d864a7..8860948ef9ca 100644
--- a/fs/ext2/Makefile
+++ b/fs/ext2/Makefile
@@ -6,7 +6,10 @@
 obj-$(CONFIG_EXT2_FS) += ext2.o
 
 ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
-	  ioctl.o namei.o super.o symlink.o
+	  ioctl.o namei.o super.o symlink.o trace.o
+
+# For tracepoints to include our trace.h from tracepoint infrastructure
+CFLAGS_trace.o := -I$(src)
 
 ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
 ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 4a6955a0a116..42db804794bd 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -186,23 +186,25 @@ fail:
  * NOTE: ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page()
  * and should be treated as a call to ext2_get_page() for nesting purposes.
  */
-static struct page * ext2_get_page(struct inode *dir, unsigned long n,
-				   int quiet, void **page_addr)
+static void *ext2_get_page(struct inode *dir, unsigned long n,
+				   int quiet, struct page **page)
 {
 	struct address_space *mapping = dir->i_mapping;
 	struct folio *folio = read_mapping_folio(mapping, n, NULL);
+	void *page_addr;
 
 	if (IS_ERR(folio))
-		return &folio->page;
-	*page_addr = kmap_local_folio(folio, n & (folio_nr_pages(folio) - 1));
+		return ERR_CAST(folio);
+	page_addr = kmap_local_folio(folio, n & (folio_nr_pages(folio) - 1));
 	if (unlikely(!folio_test_checked(folio))) {
-		if (!ext2_check_page(&folio->page, quiet, *page_addr))
+		if (!ext2_check_page(&folio->page, quiet, page_addr))
 			goto fail;
 	}
-	return &folio->page;
+	*page = &folio->page;
+	return page_addr;
 
 fail:
-	ext2_put_page(&folio->page, *page_addr);
+	ext2_put_page(&folio->page, page_addr);
 	return ERR_PTR(-EIO);
 }
 
@@ -240,7 +242,7 @@ ext2_validate_entry(char *base, unsigned offset, unsigned mask)
 			break;
 		p = ext2_next_entry(p);
 	}
-	return (char *)p - base;
+	return offset_in_page(p);
 }
 
 static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
@@ -271,16 +273,17 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 		EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE);
 
 	for ( ; n < npages; n++, offset = 0) {
-		char *kaddr, *limit;
 		ext2_dirent *de;
-		struct page *page = ext2_get_page(inode, n, 0, (void **)&kaddr);
+		struct page *page;
+		char *kaddr = ext2_get_page(inode, n, 0, &page);
+		char *limit;
 
-		if (IS_ERR(page)) {
+		if (IS_ERR(kaddr)) {
 			ext2_error(sb, __func__,
 				   "bad page in #%lu",
 				   inode->i_ino);
 			ctx->pos += PAGE_SIZE - offset;
-			return PTR_ERR(page);
+			return PTR_ERR(kaddr);
 		}
 		if (unlikely(need_revalidate)) {
 			if (offset) {
@@ -296,7 +299,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 			if (de->rec_len == 0) {
 				ext2_error(sb, __func__,
 					"zero-length directory entry");
-				ext2_put_page(page, kaddr);
+				ext2_put_page(page, de);
 				return -EIO;
 			}
 			if (de->inode) {
@@ -308,7 +311,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 				if (!dir_emit(ctx, de->name, de->name_len,
 						le32_to_cpu(de->inode),
 						d_type)) {
-					ext2_put_page(page, kaddr);
+					ext2_put_page(page, de);
 					return 0;
 				}
 			}
@@ -336,8 +339,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
  * should be treated as a call to ext2_get_page() for nesting purposes.
  */
 struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir,
-			const struct qstr *child, struct page **res_page,
-			void **res_page_addr)
+			const struct qstr *child, struct page **res_page)
 {
 	const char *name = child->name;
 	int namelen = child->len;
@@ -347,40 +349,36 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir,
 	struct page *page = NULL;
 	struct ext2_inode_info *ei = EXT2_I(dir);
 	ext2_dirent * de;
-	void *page_addr;
 
 	if (npages == 0)
 		goto out;
 
 	/* OFFSET_CACHE */
 	*res_page = NULL;
-	*res_page_addr = NULL;
 
 	start = ei->i_dir_start_lookup;
 	if (start >= npages)
 		start = 0;
 	n = start;
 	do {
-		char *kaddr;
-		page = ext2_get_page(dir, n, 0, &page_addr);
-		if (IS_ERR(page))
-			return ERR_CAST(page);
+		char *kaddr = ext2_get_page(dir, n, 0, &page);
+		if (IS_ERR(kaddr))
+			return ERR_CAST(kaddr);
 
-		kaddr = page_addr;
 		de = (ext2_dirent *) kaddr;
 		kaddr += ext2_last_byte(dir, n) - reclen;
 		while ((char *) de <= kaddr) {
 			if (de->rec_len == 0) {
 				ext2_error(dir->i_sb, __func__,
 					"zero-length directory entry");
-				ext2_put_page(page, page_addr);
+				ext2_put_page(page, de);
 				goto out;
 			}
 			if (ext2_match(namelen, name, de))
 				goto found;
 			de = ext2_next_entry(de);
 		}
-		ext2_put_page(page, page_addr);
+		ext2_put_page(page, kaddr);
 
 		if (++n >= npages)
 			n = 0;
@@ -398,7 +396,6 @@ out:
 
 found:
 	*res_page = page;
-	*res_page_addr = page_addr;
 	ei->i_dir_start_lookup = n;
 	return de;
 }
@@ -415,33 +412,26 @@ found:
  * ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page() and
  * should be treated as a call to ext2_get_page() for nesting purposes.
  */
-struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p,
-				     void **pa)
+struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p)
 {
-	void *page_addr;
-	struct page *page = ext2_get_page(dir, 0, 0, &page_addr);
-	ext2_dirent *de = NULL;
+	ext2_dirent *de = ext2_get_page(dir, 0, 0, p);
 
-	if (!IS_ERR(page)) {
-		de = ext2_next_entry((ext2_dirent *) page_addr);
-		*p = page;
-		*pa = page_addr;
-	}
-	return de;
+	if (!IS_ERR(de))
+		return ext2_next_entry(de);
+	return NULL;
 }
 
 int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino)
 {
 	struct ext2_dir_entry_2 *de;
 	struct page *page;
-	void *page_addr;
 	
-	de = ext2_find_entry(dir, child, &page, &page_addr);
+	de = ext2_find_entry(dir, child, &page);
 	if (IS_ERR(de))
 		return PTR_ERR(de);
 
 	*ino = le32_to_cpu(de->inode);
-	ext2_put_page(page, page_addr);
+	ext2_put_page(page, de);
 	return 0;
 }
 
@@ -462,11 +452,9 @@ static int ext2_handle_dirsync(struct inode *dir)
 }
 
 int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
-		struct page *page, void *page_addr, struct inode *inode,
-		bool update_times)
+		struct page *page, struct inode *inode, bool update_times)
 {
-	loff_t pos = page_offset(page) +
-			(char *) de - (char *) page_addr;
+	loff_t pos = page_offset(page) + offset_in_page(de);
 	unsigned len = ext2_rec_len_from_disk(de->rec_len);
 	int err;
 
@@ -498,7 +486,6 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 	unsigned reclen = EXT2_DIR_REC_LEN(namelen);
 	unsigned short rec_len, name_len;
 	struct page *page = NULL;
-	void *page_addr = NULL;
 	ext2_dirent * de;
 	unsigned long npages = dir_pages(dir);
 	unsigned long n;
@@ -511,15 +498,12 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 	 * to protect that region.
 	 */
 	for (n = 0; n <= npages; n++) {
-		char *kaddr;
+		char *kaddr = ext2_get_page(dir, n, 0, &page);
 		char *dir_end;
 
-		page = ext2_get_page(dir, n, 0, &page_addr);
-		err = PTR_ERR(page);
-		if (IS_ERR(page))
-			goto out;
+		if (IS_ERR(kaddr))
+			return PTR_ERR(kaddr);
 		lock_page(page);
-		kaddr = page_addr;
 		dir_end = kaddr + ext2_last_byte(dir, n);
 		de = (ext2_dirent *)kaddr;
 		kaddr += PAGE_SIZE - reclen;
@@ -550,14 +534,13 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 			de = (ext2_dirent *) ((char *) de + rec_len);
 		}
 		unlock_page(page);
-		ext2_put_page(page, page_addr);
+		ext2_put_page(page, kaddr);
 	}
 	BUG();
 	return -EINVAL;
 
 got_it:
-	pos = page_offset(page) +
-		(char *)de - (char *)page_addr;
+	pos = page_offset(page) + offset_in_page(de);
 	err = ext2_prepare_chunk(page, pos, rec_len);
 	if (err)
 		goto out_unlock;
@@ -578,8 +561,7 @@ got_it:
 	err = ext2_handle_dirsync(dir);
 	/* OFFSET_CACHE */
 out_put:
-	ext2_put_page(page, page_addr);
-out:
+	ext2_put_page(page, de);
 	return err;
 out_unlock:
 	unlock_page(page);
@@ -590,34 +572,36 @@ out_unlock:
  * ext2_delete_entry deletes a directory entry by merging it with the
  * previous entry. Page is up-to-date.
  */
-int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page,
-			char *kaddr)
+int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
-	unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
-	unsigned to = ((char *)dir - kaddr) +
+	char *kaddr = (char *)((unsigned long)dir & PAGE_MASK);
+	unsigned from = offset_in_page(dir) & ~(ext2_chunk_size(inode)-1);
+	unsigned to = offset_in_page(dir) +
 				ext2_rec_len_from_disk(dir->rec_len);
 	loff_t pos;
-	ext2_dirent * pde = NULL;
-	ext2_dirent * de = (ext2_dirent *) (kaddr + from);
+	ext2_dirent *pde = NULL;
+	ext2_dirent *de = (ext2_dirent *)(kaddr + from);
 	int err;
 
 	while ((char*)de < (char*)dir) {
 		if (de->rec_len == 0) {
 			ext2_error(inode->i_sb, __func__,
 				"zero-length directory entry");
-			err = -EIO;
-			goto out;
+			return -EIO;
 		}
 		pde = de;
 		de = ext2_next_entry(de);
 	}
 	if (pde)
-		from = (char *)pde - kaddr;
+		from = offset_in_page(pde);
 	pos = page_offset(page) + from;
 	lock_page(page);
 	err = ext2_prepare_chunk(page, pos, to - from);
-	BUG_ON(err);
+	if (err) {
+		unlock_page(page);
+		return err;
+	}
 	if (pde)
 		pde->rec_len = ext2_rec_len_to_disk(to - from);
 	dir->inode = 0;
@@ -625,9 +609,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page,
 	inode->i_ctime = inode->i_mtime = current_time(inode);
 	EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL;
 	mark_inode_dirty(inode);
-	err = ext2_handle_dirsync(inode);
-out:
-	return err;
+	return ext2_handle_dirsync(inode);
 }
 
 /*
@@ -677,19 +659,17 @@ fail:
  */
 int ext2_empty_dir (struct inode * inode)
 {
-	void *page_addr = NULL;
-	struct page *page = NULL;
+	struct page *page;
+	char *kaddr;
 	unsigned long i, npages = dir_pages(inode);
 
 	for (i = 0; i < npages; i++) {
-		char *kaddr;
-		ext2_dirent * de;
-		page = ext2_get_page(inode, i, 0, &page_addr);
+		ext2_dirent *de;
 
-		if (IS_ERR(page))
+		kaddr = ext2_get_page(inode, i, 0, &page);
+		if (IS_ERR(kaddr))
 			return 0;
 
-		kaddr = page_addr;
 		de = (ext2_dirent *)kaddr;
 		kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1);
 
@@ -715,12 +695,12 @@ int ext2_empty_dir (struct inode * inode)
 			}
 			de = ext2_next_entry(de);
 		}
-		ext2_put_page(page, page_addr);
+		ext2_put_page(page, kaddr);
 	}
 	return 1;
 
 not_empty:
-	ext2_put_page(page, page_addr);
+	ext2_put_page(page, kaddr);
 	return 0;
 }
 
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 8244366862e4..35a041c47c38 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -70,10 +70,7 @@ struct mb_cache;
  * second extended-fs super-block data in memory
  */
 struct ext2_sb_info {
-	unsigned long s_frag_size;	/* Size of a fragment in bytes */
-	unsigned long s_frags_per_block;/* Number of fragments per block */
 	unsigned long s_inodes_per_block;/* Number of inodes per block */
-	unsigned long s_frags_per_group;/* Number of fragments in a group */
 	unsigned long s_blocks_per_group;/* Number of blocks in a group */
 	unsigned long s_inodes_per_group;/* Number of inodes in a group */
 	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
@@ -189,15 +186,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
 #define EXT2_FIRST_INO(s)		(EXT2_SB(s)->s_first_ino)
 
 /*
- * Macro-instructions used to manage fragments
- */
-#define EXT2_MIN_FRAG_SIZE		1024
-#define	EXT2_MAX_FRAG_SIZE		4096
-#define EXT2_MIN_FRAG_LOG_SIZE		  10
-#define EXT2_FRAG_SIZE(s)		(EXT2_SB(s)->s_frag_size)
-#define EXT2_FRAGS_PER_BLOCK(s)		(EXT2_SB(s)->s_frags_per_block)
-
-/*
  * Structure of a blocks group descriptor
  */
 struct ext2_group_desc
@@ -730,14 +718,12 @@ extern int ext2_inode_by_name(struct inode *dir,
 			      const struct qstr *child, ino_t *ino);
 extern int ext2_make_empty(struct inode *, struct inode *);
 extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *,
-						struct page **, void **res_page_addr);
-extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page,
-			     char *kaddr);
+						struct page **);
+extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page);
 extern int ext2_empty_dir (struct inode *);
-extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa);
+extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p);
 int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
-		struct page *page, void *page_addr, struct inode *inode,
-		bool update_times);
+		struct page *page, struct inode *inode, bool update_times);
 static inline void ext2_put_page(struct page *page, void *page_addr)
 {
 	kunmap_local(page_addr);
@@ -754,6 +740,7 @@ extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
 extern struct inode *ext2_iget (struct super_block *, unsigned long);
 extern int ext2_write_inode (struct inode *, struct writeback_control *);
 extern void ext2_evict_inode(struct inode *);
+void ext2_write_failed(struct address_space *mapping, loff_t to);
 extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
 extern int ext2_setattr (struct mnt_idmap *, struct dentry *, struct iattr *);
 extern int ext2_getattr (struct mnt_idmap *, const struct path *,
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index d1ae0f0a3726..0b4c91c62e1f 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -25,9 +25,11 @@
 #include <linux/quotaops.h>
 #include <linux/iomap.h>
 #include <linux/uio.h>
+#include <linux/buffer_head.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
+#include "trace.h"
 
 #ifdef CONFIG_FS_DAX
 static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -153,7 +155,7 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct super_block *sb = file->f_mapping->host->i_sb;
 
-	ret = generic_file_fsync(file, start, end, datasync);
+	ret = generic_buffers_fsync(file, start, end, datasync);
 	if (ret == -EIO)
 		/* We don't really know where the IO error happened... */
 		ext2_error(sb, __func__,
@@ -161,12 +163,131 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return ret;
 }
 
+static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+
+	trace_ext2_dio_read_begin(iocb, to, 0);
+	inode_lock_shared(inode);
+	ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0);
+	inode_unlock_shared(inode);
+	trace_ext2_dio_read_end(iocb, to, ret);
+
+	return ret;
+}
+
+static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+				 int error, unsigned int flags)
+{
+	loff_t pos = iocb->ki_pos;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (error)
+		goto out;
+
+	/*
+	 * If we are extending the file, we have to update i_size here before
+	 * page cache gets invalidated in iomap_dio_rw(). This prevents racing
+	 * buffered reads from zeroing out too much from page cache pages.
+	 * Note that all extending writes always happens synchronously with
+	 * inode lock held by ext2_dio_write_iter(). So it is safe to update
+	 * inode size here for extending file writes.
+	 */
+	pos += size;
+	if (pos > i_size_read(inode)) {
+		i_size_write(inode, pos);
+		mark_inode_dirty(inode);
+	}
+out:
+	trace_ext2_dio_write_endio(iocb, size, error);
+	return error;
+}
+
+static const struct iomap_dio_ops ext2_dio_write_ops = {
+	.end_io = ext2_dio_write_end_io,
+};
+
+static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+	unsigned int flags = 0;
+	unsigned long blocksize = inode->i_sb->s_blocksize;
+	loff_t offset = iocb->ki_pos;
+	loff_t count = iov_iter_count(from);
+	ssize_t status = 0;
+
+	trace_ext2_dio_write_begin(iocb, from, 0);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out_unlock;
+
+	ret = kiocb_modified(iocb);
+	if (ret)
+		goto out_unlock;
+
+	/* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */
+	if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) ||
+	   (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize)))
+		flags |= IOMAP_DIO_FORCE_WAIT;
+
+	ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops,
+			   flags, NULL, 0);
+
+	/* ENOTBLK is magic return value for fallback to buffered-io */
+	if (ret == -ENOTBLK)
+		ret = 0;
+
+	if (ret < 0 && ret != -EIOCBQUEUED)
+		ext2_write_failed(inode->i_mapping, offset + count);
+
+	/* handle case for partial write and for fallback to buffered write */
+	if (ret >= 0 && iov_iter_count(from)) {
+		loff_t pos, endbyte;
+		int ret2;
+
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		pos = iocb->ki_pos;
+		status = generic_perform_write(iocb, from);
+		if (unlikely(status < 0)) {
+			ret = status;
+			goto out_unlock;
+		}
+
+		iocb->ki_pos += status;
+		ret += status;
+		endbyte = pos + status - 1;
+		ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
+						    endbyte);
+		if (!ret2)
+			invalidate_mapping_pages(inode->i_mapping,
+						 pos >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+		if (ret > 0)
+			generic_write_sync(iocb, ret);
+	}
+
+out_unlock:
+	inode_unlock(inode);
+	if (status)
+		trace_ext2_dio_write_buff_end(iocb, from, status);
+	trace_ext2_dio_write_end(iocb, from, ret);
+	return ret;
+}
+
 static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 #ifdef CONFIG_FS_DAX
 	if (IS_DAX(iocb->ki_filp->f_mapping->host))
 		return ext2_dax_read_iter(iocb, to);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext2_dio_read_iter(iocb, to);
+
 	return generic_file_read_iter(iocb, to);
 }
 
@@ -176,6 +297,9 @@ static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (IS_DAX(iocb->ki_filp->f_mapping->host))
 		return ext2_dax_write_iter(iocb, from);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext2_dio_write_iter(iocb, from);
+
 	return generic_file_write_iter(iocb, from);
 }
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 26f135e7ffce..75983215c7a1 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -56,7 +56,7 @@ static inline int ext2_inode_is_fast_symlink(struct inode *inode)
 
 static void ext2_truncate_blocks(struct inode *inode, loff_t offset);
 
-static void ext2_write_failed(struct address_space *mapping, loff_t to)
+void ext2_write_failed(struct address_space *mapping, loff_t to)
 {
 	struct inode *inode = mapping->host;
 
@@ -809,9 +809,27 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	bool new = false, boundary = false;
 	u32 bno;
 	int ret;
+	bool create = flags & IOMAP_WRITE;
+
+	/*
+	 * For writes that could fill holes inside i_size on a
+	 * DIO_SKIP_HOLES filesystem we forbid block creations: only
+	 * overwrites are permitted.
+	 */
+	if ((flags & IOMAP_DIRECT) &&
+	    (first_block << blkbits) < i_size_read(inode))
+		create = 0;
+
+	/*
+	 * Writes that span EOF might trigger an IO size update on completion,
+	 * so consider them to be dirty for the purposes of O_DSYNC even if
+	 * there is no other metadata changes pending or have been made here.
+	 */
+	if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode))
+		iomap->flags |= IOMAP_F_DIRTY;
 
 	ret = ext2_get_blocks(inode, first_block, max_blocks,
-			&bno, &new, &boundary, flags & IOMAP_WRITE);
+			&bno, &new, &boundary, create);
 	if (ret < 0)
 		return ret;
 
@@ -823,6 +841,12 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		iomap->bdev = inode->i_sb->s_bdev;
 
 	if (ret == 0) {
+		/*
+		 * Switch to buffered-io for writing to holes in a non-extent
+		 * based filesystem to avoid stale data exposure problem.
+		 */
+		if (!create && (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))
+			return -ENOTBLK;
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->length = 1 << blkbits;
@@ -844,6 +868,13 @@ static int
 ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 		ssize_t written, unsigned flags, struct iomap *iomap)
 {
+	/*
+	 * Switch to buffered-io in case of any error.
+	 * Blocks allocated can be used by the buffered-io path.
+	 */
+	if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE) && written == 0)
+		return -ENOTBLK;
+
 	if (iomap->type == IOMAP_MAPPED &&
 	    written < length &&
 	    (flags & IOMAP_WRITE))
@@ -908,22 +939,6 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping,block,ext2_get_block);
 }
 
-static ssize_t
-ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	size_t count = iov_iter_count(iter);
-	loff_t offset = iocb->ki_pos;
-	ssize_t ret;
-
-	ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
-	if (ret < 0 && iov_iter_rw(iter) == WRITE)
-		ext2_write_failed(mapping, offset + count);
-	return ret;
-}
-
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
@@ -946,7 +961,7 @@ const struct address_space_operations ext2_aops = {
 	.write_begin		= ext2_write_begin,
 	.write_end		= ext2_write_end,
 	.bmap			= ext2_bmap,
-	.direct_IO		= ext2_direct_IO,
+	.direct_IO		= noop_direct_IO,
 	.writepages		= ext2_writepages,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
@@ -1259,9 +1274,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	inode_dio_wait(inode);
 
 	if (IS_DAX(inode))
-		error = dax_zero_range(inode, newsize,
-				       PAGE_ALIGN(newsize) - newsize, NULL,
-				       &ext2_iomap_ops);
+		error = dax_truncate_page(inode, newsize, NULL,
+					  &ext2_iomap_ops);
 	else
 		error = block_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 7f5dfa87cc95..937dd8f60f96 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -269,26 +269,25 @@ out_dir:
 	goto out;
 }
 
-static int ext2_unlink(struct inode * dir, struct dentry *dentry)
+static int ext2_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct inode * inode = d_inode(dentry);
-	struct ext2_dir_entry_2 * de;
-	struct page * page;
-	void *page_addr;
+	struct inode *inode = d_inode(dentry);
+	struct ext2_dir_entry_2 *de;
+	struct page *page;
 	int err;
 
 	err = dquot_initialize(dir);
 	if (err)
 		goto out;
 
-	de = ext2_find_entry(dir, &dentry->d_name, &page, &page_addr);
+	de = ext2_find_entry(dir, &dentry->d_name, &page);
 	if (IS_ERR(de)) {
 		err = PTR_ERR(de);
 		goto out;
 	}
 
-	err = ext2_delete_entry (de, page, page_addr);
-	ext2_put_page(page, page_addr);
+	err = ext2_delete_entry(de, page);
+	ext2_put_page(page, de);
 	if (err)
 		goto out;
 
@@ -323,10 +322,8 @@ static int ext2_rename (struct mnt_idmap * idmap,
 	struct inode * old_inode = d_inode(old_dentry);
 	struct inode * new_inode = d_inode(new_dentry);
 	struct page * dir_page = NULL;
-	void *dir_page_addr;
 	struct ext2_dir_entry_2 * dir_de = NULL;
 	struct page * old_page;
-	void *old_page_addr;
 	struct ext2_dir_entry_2 * old_de;
 	int err;
 
@@ -335,28 +332,24 @@ static int ext2_rename (struct mnt_idmap * idmap,
 
 	err = dquot_initialize(old_dir);
 	if (err)
-		goto out;
+		return err;
 
 	err = dquot_initialize(new_dir);
 	if (err)
-		goto out;
+		return err;
 
-	old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page,
-				 &old_page_addr);
-	if (IS_ERR(old_de)) {
-		err = PTR_ERR(old_de);
-		goto out;
-	}
+	old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page);
+	if (IS_ERR(old_de))
+		return PTR_ERR(old_de);
 
 	if (S_ISDIR(old_inode->i_mode)) {
 		err = -EIO;
-		dir_de = ext2_dotdot(old_inode, &dir_page, &dir_page_addr);
+		dir_de = ext2_dotdot(old_inode, &dir_page);
 		if (!dir_de)
 			goto out_old;
 	}
 
 	if (new_inode) {
-		void *page_addr;
 		struct page *new_page;
 		struct ext2_dir_entry_2 *new_de;
 
@@ -365,14 +358,13 @@ static int ext2_rename (struct mnt_idmap * idmap,
 			goto out_dir;
 
 		new_de = ext2_find_entry(new_dir, &new_dentry->d_name,
-					 &new_page, &page_addr);
+					 &new_page);
 		if (IS_ERR(new_de)) {
 			err = PTR_ERR(new_de);
 			goto out_dir;
 		}
-		err = ext2_set_link(new_dir, new_de, new_page, page_addr,
-				    old_inode, true);
-		ext2_put_page(new_page, page_addr);
+		err = ext2_set_link(new_dir, new_de, new_page, old_inode, true);
+		ext2_put_page(new_page, new_de);
 		if (err)
 			goto out_dir;
 		new_inode->i_ctime = current_time(new_inode);
@@ -394,27 +386,20 @@ static int ext2_rename (struct mnt_idmap * idmap,
 	old_inode->i_ctime = current_time(old_inode);
 	mark_inode_dirty(old_inode);
 
-	ext2_delete_entry(old_de, old_page, old_page_addr);
-
-	if (dir_de) {
-		if (old_dir != new_dir) {
+	err = ext2_delete_entry(old_de, old_page);
+	if (!err && dir_de) {
+		if (old_dir != new_dir)
 			err = ext2_set_link(old_inode, dir_de, dir_page,
-					    dir_page_addr, new_dir, false);
+					    new_dir, false);
 
-		}
-		ext2_put_page(dir_page, dir_page_addr);
 		inode_dec_link_count(old_dir);
 	}
-
-out_old:
-	ext2_put_page(old_page, old_page_addr);
-out:
-	return err;
-
 out_dir:
 	if (dir_de)
-		ext2_put_page(dir_page, dir_page_addr);
-	goto out_old;
+		ext2_put_page(dir_page, dir_de);
+out_old:
+	ext2_put_page(old_page, old_de);
+	return err;
 }
 
 const struct inode_operations ext2_dir_inode_operations = {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index f342f347a695..2959afc7541c 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -668,10 +668,9 @@ static int ext2_setup_super (struct super_block * sb,
 		es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
 	if (test_opt (sb, DEBUG))
-		ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, "
+		ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, "
 			"bpg=%lu, ipg=%lu, mo=%04lx]",
 			EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
-			sbi->s_frag_size,
 			sbi->s_groups_count,
 			EXT2_BLOCKS_PER_GROUP(sb),
 			EXT2_INODES_PER_GROUP(sb),
@@ -1012,14 +1011,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	}
 
-	sbi->s_frag_size = EXT2_MIN_FRAG_SIZE <<
-				   le32_to_cpu(es->s_log_frag_size);
-	if (sbi->s_frag_size == 0)
-		goto cantfind_ext2;
-	sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size;
-
 	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
-	sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
 	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
 
 	sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
@@ -1045,11 +1037,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (sb->s_blocksize != sbi->s_frag_size) {
+	if (es->s_log_frag_size != es->s_log_block_size) {
 		ext2_msg(sb, KERN_ERR,
-			"error: fragsize %lu != blocksize %lu"
-			"(not supported yet)",
-			sbi->s_frag_size, sb->s_blocksize);
+			"error: fragsize log %u != blocksize log %u",
+			le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits);
 		goto failed_mount;
 	}
 
@@ -1066,12 +1057,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 			sbi->s_blocks_per_group, sbi->s_inodes_per_group + 3);
 		goto failed_mount;
 	}
-	if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
-		ext2_msg(sb, KERN_ERR,
-			"error: #fragments per group too big: %lu",
-			sbi->s_frags_per_group);
-		goto failed_mount;
-	}
 	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
 	    sbi->s_inodes_per_group > sb->s_blocksize * 8) {
 		ext2_msg(sb, KERN_ERR,
diff --git a/fs/ext2/trace.c b/fs/ext2/trace.c
new file mode 100644
index 000000000000..b01cdf6526fd
--- /dev/null
+++ b/fs/ext2/trace.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "ext2.h"
+#include <linux/uio.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/ext2/trace.h b/fs/ext2/trace.h
new file mode 100644
index 000000000000..7d230e13576e
--- /dev/null
+++ b/fs/ext2/trace.h
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ext2
+
+#if !defined(_EXT2_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _EXT2_TRACE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(ext2_dio_class,
+	TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, ssize_t ret),
+	TP_ARGS(iocb, iter, ret),
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t, isize)
+		__field(loff_t, pos)
+		__field(size_t,	count)
+		__field(int,	ki_flags)
+		__field(bool,	aio)
+		__field(ssize_t, ret)
+	),
+	TP_fast_assign(
+		__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+		__entry->ino = file_inode(iocb->ki_filp)->i_ino;
+		__entry->isize = file_inode(iocb->ki_filp)->i_size;
+		__entry->pos = iocb->ki_pos;
+		__entry->count = iov_iter_count(iter);
+		__entry->ki_flags = iocb->ki_flags;
+		__entry->aio = !is_sync_kiocb(iocb);
+		__entry->ret = ret;
+	),
+	TP_printk("dev %d:%d ino 0x%lx isize 0x%llx pos 0x%llx len %zu flags %s aio %d ret %zd",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->isize,
+		  __entry->pos,
+		  __entry->count,
+		  __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+		  __entry->aio,
+		  __entry->ret)
+);
+
+#define DEFINE_DIO_RW_EVENT(name)					  \
+DEFINE_EVENT(ext2_dio_class, name,					  \
+	TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, ssize_t ret), \
+	TP_ARGS(iocb, iter, ret))
+DEFINE_DIO_RW_EVENT(ext2_dio_write_begin);
+DEFINE_DIO_RW_EVENT(ext2_dio_write_end);
+DEFINE_DIO_RW_EVENT(ext2_dio_write_buff_end);
+DEFINE_DIO_RW_EVENT(ext2_dio_read_begin);
+DEFINE_DIO_RW_EVENT(ext2_dio_read_end);
+
+TRACE_EVENT(ext2_dio_write_endio,
+	TP_PROTO(struct kiocb *iocb, ssize_t size, int ret),
+	TP_ARGS(iocb, size, ret),
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t, isize)
+		__field(loff_t, pos)
+		__field(ssize_t, size)
+		__field(int,	ki_flags)
+		__field(bool,	aio)
+		__field(int,	ret)
+	),
+	TP_fast_assign(
+		__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+		__entry->ino = file_inode(iocb->ki_filp)->i_ino;
+		__entry->isize = file_inode(iocb->ki_filp)->i_size;
+		__entry->pos = iocb->ki_pos;
+		__entry->size = size;
+		__entry->ki_flags = iocb->ki_flags;
+		__entry->aio = !is_sync_kiocb(iocb);
+		__entry->ret = ret;
+	),
+	TP_printk("dev %d:%d ino 0x%lx isize 0x%llx pos 0x%llx len %zd flags %s aio %d ret %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->isize,
+		  __entry->pos,
+		  __entry->size,
+		  __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+		  __entry->aio,
+		  __entry->ret)
+);
+
+#endif /* _EXT2_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>