Merge: statx: add direct I/O alignment information

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1812

Bugzilla: https://bugzilla.redhat.com/2150284

Tested: xfstests
Upstream Status: upstream

Implement STATX_DIOALIGN for statx.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>

Approved-by: Ming Lei <ming.lei@redhat.com>
Approved-by: Carlos Maiolino <cmaiolino@redhat.com>
Approved-by: Brian Foster <bfoster@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

block/bdev.c

@@ -26,6 +26,7 @@
 #include <linux/namei.h>
 #include <linux/part_stat.h>
 #include <linux/uaccess.h>
+#include <linux/stat.h>
 #include "../fs/internal.h"
 #include "blk.h"
 
@@ -1062,3 +1063,25 @@ void sync_bdevs(bool wait)
 	spin_unlock(&blockdev_superblock->s_inode_list_lock);
 	iput(old_inode);
 }
+
+/*
+ * Handle STATX_DIOALIGN for block devices.
+ *
+ * Note that the inode passed to this is the inode of a block device node file,
+ * not the block device's internal inode.  Therefore it is *not* valid to use
+ * I_BDEV() here; the block device has to be looked up by i_rdev instead.
+ */
+void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+{
+	struct block_device *bdev;
+
+	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!bdev)
+		return;
+
+	stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+	stat->dio_offset_align = bdev_logical_block_size(bdev);
+	stat->result_mask |= STATX_DIOALIGN;
+
+	blkdev_put_no_open(bdev);
+}

fs/ext4/ext4.h

@@ -3013,6 +3013,7 @@ 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 *);

fs/ext4/file.c

@@ -36,17 +36,34 @@
 #include "acl.h"
 #include "truncate.h"
 
-static bool ext4_dio_supported(struct inode *inode)
+/*
+ * 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)
 {
-	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
-		return false;
-	if (fsverity_active(inode))
-		return false;
-	if (ext4_should_journal_data(inode))
-		return false;
-	if (ext4_has_inline_data(inode))
+	struct inode *inode = file_inode(iocb->ki_filp);
+	u32 dio_align = ext4_dio_alignment(inode);
+
+	if (dio_align == 0)
 		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)
@@ -61,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		inode_lock_shared(inode);
 	}
 
-	if (!ext4_dio_supported(inode)) {
+	if (!ext4_should_use_dio(iocb, to)) {
 		inode_unlock_shared(inode);
 		/*
 		 * Fallback to buffered I/O if the operation being performed on
@@ -509,7 +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(inode)) {
+	if (!ext4_should_use_dio(iocb, from)) {
 		if (ilock_shared)
 			inode_unlock_shared(inode);
 		else

fs/ext4/inode.c

@@ -5515,6 +5515,19 @@ 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))
+		return 0;
+	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)
 {
@@ -5530,6 +5543,29 @@ 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.
+	 * (RHEL9: this comment isn't exactly correct on rhel9, because there
+	 * is no DIO support in fscrypt. But we'll leave the code as is.)
+	 */
+	if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
+		u32 dio_align = ext4_dio_alignment(inode);
+
+		stat->result_mask |= STATX_DIOALIGN;
+		if (dio_align == 1) {
+			struct block_device *bdev = inode->i_sb->s_bdev;
+
+			/* iomap defaults */
+			stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+			stat->dio_offset_align = bdev_logical_block_size(bdev);
+		} 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;

fs/stat.c

@@ -5,6 +5,7 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
+#include <linux/blkdev.h>
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
@@ -212,11 +213,22 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
 		goto out;
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
+
 	stat->mnt_id = real_mount(path.mnt)->mnt_id;
 	stat->result_mask |= STATX_MNT_ID;
+
 	if (path.mnt->mnt_root == path.dentry)
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
 	stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
+
+	/* Handle STATX_DIOALIGN for block devices. */
+	if (request_mask & STATX_DIOALIGN) {
+		struct inode *inode = d_backing_inode(path.dentry);
+
+		if (S_ISBLK(inode->i_mode))
+			bdev_statx_dioalign(inode, stat);
+	}
+
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -594,6 +606,8 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	tmp.stx_dev_major = MAJOR(stat->dev);
 	tmp.stx_dev_minor = MINOR(stat->dev);
 	tmp.stx_mnt_id = stat->mnt_id;
+	tmp.stx_dio_mem_align = stat->dio_mem_align;
+	tmp.stx_dio_offset_align = stat->dio_offset_align;
 
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }

fs/xfs/xfs_iops.c

@@ -604,6 +604,16 @@ xfs_vn_getattr(
 		stat->blksize = BLKDEV_IOSIZE;
 		stat->rdev = inode->i_rdev;
 		break;
+	case S_IFREG:
+		if (request_mask & STATX_DIOALIGN) {
+			struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
+			struct block_device	*bdev = target->bt_bdev;
+
+			stat->result_mask |= STATX_DIOALIGN;
+			stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+			stat->dio_offset_align = bdev_logical_block_size(bdev);
+		}
+		fallthrough;
 	default:
 		stat->blksize = xfs_stat_blksize(ip);
 		stat->rdev = 0;

include/linux/blkdev.h

@@ -1521,6 +1521,7 @@ void invalidate_bdev(struct block_device *bdev);
 int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
+void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
 void printk_all_partitions(void);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
@@ -1537,6 +1538,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
 static inline void sync_bdevs(bool wait)
 {
 }
+static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+{
+}
 static inline void printk_all_partitions(void)
 {
 }

include/linux/stat.h

@@ -46,6 +46,8 @@ struct kstat {
 	struct timespec64 btime;			/* File creation time */
 	u64		blocks;
 	u64		mnt_id;
+	u32		dio_mem_align;
+	u32		dio_offset_align;
 };
 
 #endif

include/uapi/linux/stat.h

@@ -124,7 +124,8 @@ struct statx {
 	__u32	stx_dev_minor;
 	/* 0x90 */
 	__u64	stx_mnt_id;
-	__u64	__spare2;
+	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
+	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
 	/* 0xa0 */
 	__u64	__spare3[12];	/* Spare space for future expansion */
 	/* 0x100 */
@@ -152,6 +153,7 @@ struct statx {
 #define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
+#define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 

tools/include/uapi/linux/stat.h

@@ -124,7 +124,8 @@ struct statx {
 	__u32	stx_dev_minor;
 	/* 0x90 */
 	__u64	stx_mnt_id;
-	__u64	__spare2;
+	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
+	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
 	/* 0xa0 */
 	__u64	__spare3[12];	/* Spare space for future expansion */
 	/* 0x100 */
@@ -152,6 +153,7 @@ struct statx {
 #define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
+#define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */