From: Eric Biggers <ebiggers@google.com>

Add support for STATX_DIOALIGN to ext4, so that direct I/O alignment
restrictions are exposed to userspace in a generic way.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/ext4/ext4.h  |  1 +
 fs/ext4/file.c  | 42 ++++++++++++++++++++++++++----------------
 fs/ext4/inode.c | 36 ++++++++++++++++++++++++++++++++++++
 3 files changed, 63 insertions(+), 16 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 75b8d81b24692c..68e964394e9173 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2968,6 +2968,7 @@ 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 26d7426208970d..8bb1c35fd6dd5a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -36,24 +36,34 @@
 #include "acl.h"
 #include "truncate.h"
 
-static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
+/*
+ * Returns %true if the given DIO request should be attempted with DIO, or
+ * %false if it should fall back to buffered I/O.
+ *
+ * DIO isn't well specified; when it's unsupported (either due to the request
+ * being misaligned, or due to the file not supporting DIO at all), filesystems
+ * either fall back to buffered I/O or return EINVAL.  For files that don't use
+ * any special features like encryption or verity, ext4 has traditionally
+ * returned EINVAL for misaligned DIO.  iomap_dio_rw() uses this convention too.
+ * In this case, we should attempt the DIO, *not* fall back to buffered I/O.
+ *
+ * In contrast, in cases where DIO is unsupported due to ext4 features, ext4
+ * traditionally falls back to buffered I/O.
+ *
+ * This function implements the traditional ext4 behavior in all these cases.
+ */
+static bool ext4_should_use_dio(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))
+	if (dio_align == 0)
 		return false;
-	if (ext4_should_journal_data(inode))
-		return false;
-	if (ext4_has_inline_data(inode))
-		return false;
-	return true;
+
+	if (dio_align == 1)
+		return true;
+
+	return IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align);
 }
 
 static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -68,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		inode_lock_shared(inode);
 	}
 
-	if (!ext4_dio_supported(iocb, to)) {
+	if (!ext4_should_use_dio(iocb, to)) {
 		inode_unlock_shared(inode);
 		/*
 		 * Fallback to buffered I/O if the operation being performed on
@@ -516,7 +526,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	/* Fallback to buffered I/O if the inode does not support direct I/O. */
-	if (!ext4_dio_supported(iocb, from)) {
+	if (!ext4_should_use_dio(iocb, from)) {
 		if (ilock_shared)
 			inode_unlock_shared(inode);
 		else
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 84c0eb55071d65..75dd332e9da57b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5536,6 +5536,22 @@ 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 1; /* use the iomap defaults */
+}
+
 int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
@@ -5551,6 +5567,26 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
 	}
 
+	/*
+	 * Return the DIO alignment restrictions 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_DIOALIGN) && S_ISREG(inode->i_mode)) {
+		u32 dio_align = ext4_dio_alignment(inode);
+		unsigned int lbs = bdev_logical_block_size(inode->i_sb->s_bdev);
+
+		stat->result_mask |= STATX_DIOALIGN;
+		if (dio_align == 1) {
+			/* iomap defaults */
+			stat->dio_mem_align = lbs;
+			stat->dio_offset_align = lbs;
+		} else {
+			stat->dio_mem_align = dio_align;
+			stat->dio_offset_align = dio_align;
+		}
+	}
+
 	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 	if (flags & EXT4_APPEND_FL)
 		stat->attributes |= STATX_ATTR_APPEND;
-- 
2.37.0

On Fri, Jul 22, 2022 at 12:12:23AM -0700, Eric Biggers wrote:
> -static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
> +/*
> + * Returns %true if the given DIO request should be attempted with DIO, or
> + * %false if it should fall back to buffered I/O.
> + *
> + * DIO isn't well specified; when it's unsupported (either due to the request
> + * being misaligned, or due to the file not supporting DIO at all), filesystems
> + * either fall back to buffered I/O or return EINVAL.  For files that don't use
> + * any special features like encryption or verity, ext4 has traditionally
> + * returned EINVAL for misaligned DIO.  iomap_dio_rw() uses this convention too.
> + * In this case, we should attempt the DIO, *not* fall back to buffered I/O.
> + *
> + * In contrast, in cases where DIO is unsupported due to ext4 features, ext4
> + * traditionally falls back to buffered I/O.
> + *
> + * This function implements the traditional ext4 behavior in all these cases.

Heh.  I had been under the impression that misaligned I/O fell back to
buffered I/O for ext4, since that's what a lot of historical Unix
systems did.  Obviously, it's not something I've tested since "you
should never do that".

There's actually some interesting discussion about what Linux *should*
be doing in the futre in this discussion:

https://patchwork.ozlabs.org/project/linux-ext4/patch/1461472078-20104-1-git-send-email-tytso@mit.edu/

Including the following from Christoph Hellwig:

https://patchwork.ozlabs.org/project/linux-ext4/patch/1461472078-20104-1-git-send-email-tytso@mit.edu/#1335016

> I've been doing an audit of our direct I/O implementations, and most
> of them does some form of transparent fallback, including some that
> only pretend to support O_DIRECT, but do anything special for it at all,
> while at the same time we go through greast efforts to check a file
> system actualy supports direct I/O, leading to nasty no-op ->direct_IO
> implementations as we even got that abstraction wrong.
> 
> At this point I wonder if we should simply treat O_DIRECT as a hint
> and always allow it, and just let the file system optimize for it
> (skip buffering, require alignment, relaxed Posix atomicy requirements)
> if it is set.

The thread also mentioned XFS_IOC_DIOINFO and how We Really Should
have something with equivalent functionality to the VFS --- six years
ago.  :-)


Anyway, this change to ext4 looks good.

Acked-by: Theodore Ts'o <tytso@mit.edu>

							- Ted