[RFC,v2,3/7] ext4: support STATX_IOALIGN

Commit Message

Eric Biggers May 18, 2022, 11:50 p.m. UTC

From: Eric Biggers <[e-mail]>

Add support for STATX_IOALIGN to ext4, so that I/O alignment information
is exposed to userspace in a consistent and easy-to-use way.

Signed-off-by: Eric Biggers <[e-mail]>
---
 fs/ext4/ext4.h  |  1 +
 fs/ext4/file.c  | 15 ++++-----------
 fs/ext4/inode.c | 31 +++++++++++++++++++++++++++++++
 3 files changed, 36 insertions(+), 11 deletions(-)

Patch

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a743b1e3b89ec..7c43428901632 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3020,6 +3020,7 @@  extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct user_namespace *, struct dentry *,
 			 struct iattr *);
+extern u32  ext4_dio_alignment(struct inode *inode);
 extern int  ext4_getattr(struct user_namespace *, const struct path *,
 			 struct kstat *, u32, unsigned int);
 extern void ext4_evict_inode(struct inode *);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index de153b508b20a..ba2271e5287b2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -39,19 +39,12 @@ 
 static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
+	u32 dio_align = ext4_dio_alignment(inode);
 
-	if (IS_ENCRYPTED(inode)) {
-		if (!fscrypt_dio_supported(inode))
-			return false;
-		if (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter),
-				i_blocksize(inode)))
-			return false;
-	}
-	if (fsverity_active(inode))
-		return false;
-	if (ext4_should_journal_data(inode))
+	if (!dio_align)
 		return false;
-	if (ext4_has_inline_data(inode))
+	if (dio_align > bdev_logical_block_size(inode->i_sb->s_bdev) &&
+	    !IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align))
 		return false;
 	return true;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 646ece9b3455f..5af2598aa170d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5533,6 +5533,22 @@  int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	return error;
 }
 
+u32 ext4_dio_alignment(struct inode *inode)
+{
+	if (fsverity_active(inode))
+		return 0;
+	if (ext4_should_journal_data(inode))
+		return 0;
+	if (ext4_has_inline_data(inode))
+		return 0;
+	if (IS_ENCRYPTED(inode)) {
+		if (!fscrypt_dio_supported(inode))
+			return 0;
+		return i_blocksize(inode);
+	}
+	return bdev_logical_block_size(inode->i_sb->s_bdev);
+}
+
 int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
@@ -5548,6 +5564,21 @@  int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
 	}
 
+	/*
+	 * Return the I/O alignment information if requested.  We only return
+	 * this information when requested, since on encrypted files it might
+	 * take a fair bit of work to get if the file wasn't opened recently.
+	 */
+	if ((request_mask & STATX_IOALIGN) && S_ISREG(inode->i_mode)) {
+		u32 dio_align = ext4_dio_alignment(inode);
+		unsigned int io_opt = bdev_io_opt(inode->i_sb->s_bdev);
+
+		stat->result_mask |= STATX_IOALIGN;
+		stat->mem_align_dio = dio_align;
+		stat->offset_align_dio = dio_align;
+		stat->offset_align_optimal = max(io_opt, i_blocksize(inode));
+	}
+
 	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 	if (flags & EXT4_APPEND_FL)
 		stat->attributes |= STATX_ATTR_APPEND;