[PATCH 03/21] fs/bdev: Add atomic write support info to statx

John Garry john.g.garry at oracle.com
Fri Sep 29 03:27:08 PDT 2023


From: Prasad Singamsetty <prasad.singamsetty at oracle.com>

Extend statx system call to return additional info for atomic write support
support if the specified file is a block device.

Add initial support for a block device.

Signed-off-by: Prasad Singamsetty <prasad.singamsetty at oracle.com>
Signed-off-by: John Garry <john.g.garry at oracle.com>
---
 block/bdev.c              | 33 +++++++++++++++++++++++----------
 fs/stat.c                 | 15 ++++++++-------
 include/linux/blkdev.h    |  4 ++--
 include/linux/stat.h      |  2 ++
 include/uapi/linux/stat.h |  7 ++++++-
 5 files changed, 41 insertions(+), 20 deletions(-)

diff --git a/block/bdev.c b/block/bdev.c
index f3b13aa1b7d4..037a3d9ecbcb 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -1028,24 +1028,37 @@ void sync_bdevs(bool wait)
 	iput(old_inode);
 }
 
+#define BDEV_STATX_SUPPORTED_MSK (STATX_DIOALIGN | STATX_WRITE_ATOMIC)
+
 /*
- * 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.
+ * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices.
  */
-void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+void bdev_statx(struct dentry *dentry, struct kstat *stat, u32 request_mask)
 {
 	struct block_device *bdev;
 
-	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!(request_mask & BDEV_STATX_SUPPORTED_MSK))
+		return;
+
+	bdev = blkdev_get_no_open(d_backing_inode(dentry)->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;
+	if (request_mask & STATX_DIOALIGN) {
+		stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+		stat->dio_offset_align = bdev_logical_block_size(bdev);
+		stat->result_mask |= STATX_DIOALIGN;
+	}
+
+	if (request_mask & STATX_WRITE_ATOMIC) {
+		stat->atomic_write_unit_min =
+			queue_atomic_write_unit_min_bytes(bdev->bd_queue);
+		stat->atomic_write_unit_max =
+			queue_atomic_write_unit_max_bytes(bdev->bd_queue);
+		stat->attributes |= STATX_ATTR_WRITE_ATOMIC;
+		stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC;
+		stat->result_mask |= STATX_WRITE_ATOMIC;
+	}
 
 	blkdev_put_no_open(bdev);
 }
diff --git a/fs/stat.c b/fs/stat.c
index d43a5cc1bfa4..b840e58f41fa 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -250,13 +250,12 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
 		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);
-	}
+	/* If this is a block device inode, override the filesystem
+	 * attributes with the block device specific parameters
+	 * that need to be obtained from the bdev backing inode
+	 */
+	if (S_ISBLK(d_backing_inode(path.dentry)->i_mode))
+		bdev_statx(path.dentry, stat, request_mask);
 
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
@@ -649,6 +648,8 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	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;
+	tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min;
+	tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max;
 
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c10e47bdb34f..f70988083734 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1533,7 +1533,7 @@ int sync_blockdev(struct block_device *bdev);
 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_dioalign(struct inode *inode, struct kstat *stat);
+void bdev_statx(struct dentry *dentry, struct kstat *stat, u32 request_mask);
 void printk_all_partitions(void);
 int __init early_lookup_bdev(const char *pathname, dev_t *dev);
 #else
@@ -1551,7 +1551,7 @@ 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 bdev_statx(struct dentry *dentry, struct kstat *stat, u32 request_mask)
 {
 }
 static inline void printk_all_partitions(void)
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 52150570d37a..dfa69ecfaacf 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -53,6 +53,8 @@ struct kstat {
 	u32		dio_mem_align;
 	u32		dio_offset_align;
 	u64		change_cookie;
+	u32		atomic_write_unit_max;
+	u32		atomic_write_unit_min;
 };
 
 /* These definitions are internal to the kernel for now. Mainly used by nfsd. */
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7cab2c65d3d7..c99d7cac2aa6 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -127,7 +127,10 @@ struct statx {
 	__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 */
+	__u32	stx_atomic_write_unit_max;
+	__u32	stx_atomic_write_unit_min;
+	/* 0xb0 */
+	__u64	__spare3[11];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -154,6 +157,7 @@ struct statx {
 #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_WRITE_ATOMIC	0x00004000U	/* Want/got atomic_write_* fields */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
@@ -189,6 +193,7 @@ struct statx {
 #define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 #define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
+#define STATX_ATTR_WRITE_ATOMIC		0x00400000 /* File supports atomic write operations */
 
 
 #endif /* _UAPI_LINUX_STAT_H */
-- 
2.31.1




More information about the Linux-nvme mailing list