[PATCHv2 2/5] block: report direct io attributes through file_getattr

[Keith Busch <kbusch@meta.com>]

From: Keith Busch <kbusch@kernel.org>

Add bdev_fill_dio_attr() to fill the file_attr direct io alignment
fields from a block device's queue limits, so filesystems can share the
derivation. Use it to report the attributes for block devices opened
directly.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 block/bdev.c           | 37 +++++++++++++++++++++++++++++++++++++
 fs/file_attr.c         |  6 +++++-
 include/linux/blkdev.h | 14 ++++++++++++++
 3 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/block/bdev.c b/block/bdev.c
index 85ce57bd2ae4f..3b56f6696d3a3 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -28,6 +28,7 @@
 #include <linux/part_stat.h>
 #include <linux/uaccess.h>
 #include <linux/stat.h>
+#include <linux/fileattr.h>
 #include "../fs/internal.h"
 #include "blk.h"
 
@@ -1353,6 +1354,42 @@ void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask)
 	blkdev_put_no_open(bdev);
 }
 
+/*
+ * Fill the direct I/O alignment attributes derived from a block device's
+ * queue limits.  Filesystems override the offset alignments as needed and
+ * set FS_XFLAG_DIO once they have decided direct I/O is supported.
+ */
+void bdev_fill_dio_attr(struct block_device *bdev, struct file_kattr *fa)
+{
+	fa->fsx_dio_mem_align = bdev_dma_alignment(bdev) + 1;
+	fa->fsx_dio_offset_align = bdev_logical_block_size(bdev);
+	fa->fsx_dio_read_offset_align = bdev_logical_block_size(bdev);
+	fa->fsx_dio_virt_boundary_align = bdev_virt_boundary_alignment(bdev);
+	fa->fsx_dio_offset_align_max_vecs = bdev_max_segments(bdev);
+}
+EXPORT_SYMBOL_GPL(bdev_fill_dio_attr);
+
+/*
+ * Handle DIO alignment for block devices via fileattr.
+ */
+int bdev_fileattr(const struct inode *inode, struct file_kattr *fa)
+{
+	struct block_device *bdev;
+
+	bdev = blkdev_get_no_open(inode->i_rdev, false);
+	if (!bdev)
+		return -ENODEV;
+
+	memset(fa, 0, sizeof(*fa));
+	bdev_fill_dio_attr(bdev, fa);
+	fa->fsx_valid = true;
+	fa->flags_valid = true;
+	fa->fsx_xflags |= FS_XFLAG_DIO;
+
+	blkdev_put_no_open(bdev);
+	return 0;
+}
+
 bool disk_live(struct gendisk *disk)
 {
 	return !inode_unhashed(BD_INODE(disk->part0));
diff --git a/fs/file_attr.c b/fs/file_attr.c
index b37a55f54a449..b637eff9081aa 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/namei.h>
+#include <linux/blkdev.h>
 
 #include "internal.h"
 
@@ -88,13 +89,16 @@ int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 	struct inode *inode = d_inode(dentry);
 	int error;
 
-	if (!inode->i_op->fileattr_get)
+	if (!inode->i_op->fileattr_get && !S_ISBLK(inode->i_mode))
 		return -ENOIOCTLCMD;
 
 	error = security_inode_file_getattr(dentry, fa);
 	if (error)
 		return error;
 
+	if (!inode->i_op->fileattr_get)
+		return bdev_fileattr(inode, fa);
+
 	return inode->i_op->fileattr_get(dentry, fa);
 }
 EXPORT_SYMBOL(vfs_fileattr_get);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9213a5716f95a..2d435fadfdcb9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1607,6 +1607,17 @@ static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
 	return queue_dma_alignment(bdev_get_queue(bdev));
 }
 
+static inline unsigned long bdev_virt_boundary_mask(struct block_device *bdev)
+{
+	return bdev_get_queue(bdev)->limits.virt_boundary_mask;
+}
+
+static inline unsigned int
+bdev_virt_boundary_alignment(struct block_device *bdev)
+{
+	return bdev_virt_boundary_mask(bdev) + 1;
+}
+
 static inline unsigned int
 blk_lim_dma_alignment_and_pad(struct queue_limits *lim)
 {
@@ -1805,6 +1816,9 @@ int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
 void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask);
+struct file_kattr;
+void bdev_fill_dio_attr(struct block_device *bdev, struct file_kattr *fa);
+int bdev_fileattr(const struct inode *inode, struct file_kattr *fa);
 void printk_all_partitions(void);
 int __init early_lookup_bdev(const char *pathname, dev_t *dev);
 #else
-- 
2.53.0-Meta