From: Prasad Singamsetty <prasad.singamsetty@oracle.com>
Extend statx system call to return additional info for atomic write support
support for a file.
Helper function generic_fill_statx_atomic_writes() can be used by FSes to
fill in the relevant statx fields. For now atomic_write_segments_max will
always be 1, otherwise some rules would need to be imposed on iovec length
and alignment, which we don't want now.
Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com>
jpg: relocate bdev support to another patch
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
fs/stat.c | 34 ++++++++++++++++++++++++++++++++++
include/linux/fs.h | 3 +++
include/linux/stat.h | 3 +++
include/uapi/linux/stat.h | 12 ++++++++++--
4 files changed, 50 insertions(+), 2 deletions(-)
diff --git a/fs/stat.c b/fs/stat.c
index 70bd3e888cfa..72d0e6357b91 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
}
EXPORT_SYMBOL(generic_fill_statx_attr);
+/**
+ * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes
+ * @stat: Where to fill in the attribute flags
+ * @unit_min: Minimum supported atomic write length in bytes
+ * @unit_max: Maximum supported atomic write length in bytes
+ *
+ * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from
+ * atomic write unit_min and unit_max values.
+ */
+void generic_fill_statx_atomic_writes(struct kstat *stat,
+ unsigned int unit_min,
+ unsigned int unit_max)
+{
+ /* Confirm that the request type is known */
+ stat->result_mask |= STATX_WRITE_ATOMIC;
+
+ /* Confirm that the file attribute type is known */
+ stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC;
+
+ if (unit_min) {
+ stat->atomic_write_unit_min = unit_min;
+ stat->atomic_write_unit_max = unit_max;
+ /* Initially only allow 1x segment */
+ stat->atomic_write_segments_max = 1;
+
+ /* Confirm atomic writes are actually supported */
+ stat->attributes |= STATX_ATTR_WRITE_ATOMIC;
+ }
+}
+EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes);
+
/**
* vfs_getattr_nosec - getattr without security checks
* @path: file to get attributes from
@@ -659,6 +690,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
tmp.stx_dio_mem_align = stat->dio_mem_align;
tmp.stx_dio_offset_align = stat->dio_offset_align;
tmp.stx_subvol = stat->subvol;
+ tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min;
+ tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max;
+ tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max;
return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e049414bef7d..db26b4a70c62 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3235,6 +3235,9 @@ extern const struct inode_operations page_symlink_inode_operations;
extern void kfree_link(void *);
void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
+void generic_fill_statx_atomic_writes(struct kstat *stat,
+ unsigned int unit_min,
+ unsigned int unit_max);
extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
void __inode_add_bytes(struct inode *inode, loff_t bytes);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index bf92441dbad2..3d900c86981c 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -54,6 +54,9 @@ struct kstat {
u32 dio_offset_align;
u64 change_cookie;
u64 subvol;
+ u32 atomic_write_unit_min;
+ u32 atomic_write_unit_max;
+ u32 atomic_write_segments_max;
};
/* 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 67626d535316..887a25286441 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -126,9 +126,15 @@ struct statx {
__u64 stx_mnt_id;
__u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
__u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
- __u64 stx_subvol; /* Subvolume identifier */
/* 0xa0 */
- __u64 __spare3[11]; /* Spare space for future expansion */
+ __u64 stx_subvol; /* Subvolume identifier */
+ __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
+ /* 0xb0 */
+ __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
+ __u32 __spare1[1];
+ /* 0xb8 */
+ __u64 __spare3[9]; /* Spare space for future expansion */
/* 0x100 */
};
@@ -157,6 +163,7 @@ struct statx {
#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
+#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
@@ -192,6 +199,7 @@ 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 */
--
2.31.1On Mon, Jun 10, 2024 at 10:43:23AM +0000, John Garry wrote:
> From: Prasad Singamsetty <prasad.singamsetty@oracle.com>
>
> Extend statx system call to return additional info for atomic write support
> support for a file.
>
> Helper function generic_fill_statx_atomic_writes() can be used by FSes to
> fill in the relevant statx fields. For now atomic_write_segments_max will
> always be 1, otherwise some rules would need to be imposed on iovec length
> and alignment, which we don't want now.
>
> Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com>
> jpg: relocate bdev support to another patch
> Signed-off-by: John Garry <john.g.garry@oracle.com>
Looks fine to me, assuming there's a manpage update lurking somewhere?
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
--D
> ---
> fs/stat.c | 34 ++++++++++++++++++++++++++++++++++
> include/linux/fs.h | 3 +++
> include/linux/stat.h | 3 +++
> include/uapi/linux/stat.h | 12 ++++++++++--
> 4 files changed, 50 insertions(+), 2 deletions(-)
>
> diff --git a/fs/stat.c b/fs/stat.c
> index 70bd3e888cfa..72d0e6357b91 100644
> --- a/fs/stat.c
> +++ b/fs/stat.c
> @@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
> }
> EXPORT_SYMBOL(generic_fill_statx_attr);
>
> +/**
> + * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes
> + * @stat: Where to fill in the attribute flags
> + * @unit_min: Minimum supported atomic write length in bytes
> + * @unit_max: Maximum supported atomic write length in bytes
> + *
> + * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from
> + * atomic write unit_min and unit_max values.
> + */
> +void generic_fill_statx_atomic_writes(struct kstat *stat,
> + unsigned int unit_min,
> + unsigned int unit_max)
> +{
> + /* Confirm that the request type is known */
> + stat->result_mask |= STATX_WRITE_ATOMIC;
> +
> + /* Confirm that the file attribute type is known */
> + stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC;
> +
> + if (unit_min) {
> + stat->atomic_write_unit_min = unit_min;
> + stat->atomic_write_unit_max = unit_max;
> + /* Initially only allow 1x segment */
> + stat->atomic_write_segments_max = 1;
> +
> + /* Confirm atomic writes are actually supported */
> + stat->attributes |= STATX_ATTR_WRITE_ATOMIC;
> + }
> +}
> +EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes);
> +
> /**
> * vfs_getattr_nosec - getattr without security checks
> * @path: file to get attributes from
> @@ -659,6 +690,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
> tmp.stx_dio_mem_align = stat->dio_mem_align;
> tmp.stx_dio_offset_align = stat->dio_offset_align;
> tmp.stx_subvol = stat->subvol;
> + tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min;
> + tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max;
> + tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max;
>
> return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
> }
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index e049414bef7d..db26b4a70c62 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -3235,6 +3235,9 @@ extern const struct inode_operations page_symlink_inode_operations;
> extern void kfree_link(void *);
> void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
> void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
> +void generic_fill_statx_atomic_writes(struct kstat *stat,
> + unsigned int unit_min,
> + unsigned int unit_max);
> extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
> extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
> void __inode_add_bytes(struct inode *inode, loff_t bytes);
> diff --git a/include/linux/stat.h b/include/linux/stat.h
> index bf92441dbad2..3d900c86981c 100644
> --- a/include/linux/stat.h
> +++ b/include/linux/stat.h
> @@ -54,6 +54,9 @@ struct kstat {
> u32 dio_offset_align;
> u64 change_cookie;
> u64 subvol;
> + u32 atomic_write_unit_min;
> + u32 atomic_write_unit_max;
> + u32 atomic_write_segments_max;
> };
>
> /* 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 67626d535316..887a25286441 100644
> --- a/include/uapi/linux/stat.h
> +++ b/include/uapi/linux/stat.h
> @@ -126,9 +126,15 @@ struct statx {
> __u64 stx_mnt_id;
> __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
> __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
> - __u64 stx_subvol; /* Subvolume identifier */
> /* 0xa0 */
> - __u64 __spare3[11]; /* Spare space for future expansion */
> + __u64 stx_subvol; /* Subvolume identifier */
> + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
> + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
> + /* 0xb0 */
> + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
> + __u32 __spare1[1];
> + /* 0xb8 */
> + __u64 __spare3[9]; /* Spare space for future expansion */
> /* 0x100 */
> };
>
> @@ -157,6 +163,7 @@ struct statx {
> #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
> #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
> #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
> +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
>
> #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
>
> @@ -192,6 +199,7 @@ 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
>
>
On 12/06/2024 21:54, Darrick J. Wong wrote:
> On Mon, Jun 10, 2024 at 10:43:23AM +0000, John Garry wrote:
>> From: Prasad Singamsetty <prasad.singamsetty@oracle.com>
>>
>> Extend statx system call to return additional info for atomic write support
>> support for a file.
>>
>> Helper function generic_fill_statx_atomic_writes() can be used by FSes to
>> fill in the relevant statx fields. For now atomic_write_segments_max will
>> always be 1, otherwise some rules would need to be imposed on iovec length
>> and alignment, which we don't want now.
>>
>> Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com>
>> jpg: relocate bdev support to another patch
>> Signed-off-by: John Garry <john.g.garry@oracle.com>
>
> Looks fine to me, assuming there's a manpage update lurking somewhere?
Sure, see
https://lore.kernel.org/lkml/20240124112731.28579-1-john.g.garry@oracle.com/T/#m520dca97a9748de352b5a723d3155a4bb1e46456
I'll post a rebase, but the API is still the same.
> Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Thanks,
John
>
> --D
>
>> ---
>> fs/stat.c | 34 ++++++++++++++++++++++++++++++++++
>> include/linux/fs.h | 3 +++
>> include/linux/stat.h | 3 +++
>> include/uapi/linux/stat.h | 12 ++++++++++--
>> 4 files changed, 50 insertions(+), 2 deletions(-)
>>
>> diff --git a/fs/stat.c b/fs/stat.c
>> index 70bd3e888cfa..72d0e6357b91 100644
>> --- a/fs/stat.c
>> +++ b/fs/stat.c
>> @@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
>> }
>> EXPORT_SYMBOL(generic_fill_statx_attr);
>>
>> +/**
>> + * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes
>> + * @stat: Where to fill in the attribute flags
>> + * @unit_min: Minimum supported atomic write length in bytes
>> + * @unit_max: Maximum supported atomic write length in bytes
>> + *
>> + * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from
>> + * atomic write unit_min and unit_max values.
>> + */
>> +void generic_fill_statx_atomic_writes(struct kstat *stat,
>> + unsigned int unit_min,
>> + unsigned int unit_max)
>> +{
>> + /* Confirm that the request type is known */
>> + stat->result_mask |= STATX_WRITE_ATOMIC;
>> +
>> + /* Confirm that the file attribute type is known */
>> + stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC;
>> +
>> + if (unit_min) {
>> + stat->atomic_write_unit_min = unit_min;
>> + stat->atomic_write_unit_max = unit_max;
>> + /* Initially only allow 1x segment */
>> + stat->atomic_write_segments_max = 1;
>> +
>> + /* Confirm atomic writes are actually supported */
>> + stat->attributes |= STATX_ATTR_WRITE_ATOMIC;
>> + }
>> +}
>> +EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes);
>> +
>> /**
>> * vfs_getattr_nosec - getattr without security checks
>> * @path: file to get attributes from
>> @@ -659,6 +690,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
>> tmp.stx_dio_mem_align = stat->dio_mem_align;
>> tmp.stx_dio_offset_align = stat->dio_offset_align;
>> tmp.stx_subvol = stat->subvol;
>> + tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min;
>> + tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max;
>> + tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max;
>>
>> return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
>> }
>> diff --git a/include/linux/fs.h b/include/linux/fs.h
>> index e049414bef7d..db26b4a70c62 100644
>> --- a/include/linux/fs.h
>> +++ b/include/linux/fs.h
>> @@ -3235,6 +3235,9 @@ extern const struct inode_operations page_symlink_inode_operations;
>> extern void kfree_link(void *);
>> void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
>> void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
>> +void generic_fill_statx_atomic_writes(struct kstat *stat,
>> + unsigned int unit_min,
>> + unsigned int unit_max);
>> extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
>> extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
>> void __inode_add_bytes(struct inode *inode, loff_t bytes);
>> diff --git a/include/linux/stat.h b/include/linux/stat.h
>> index bf92441dbad2..3d900c86981c 100644
>> --- a/include/linux/stat.h
>> +++ b/include/linux/stat.h
>> @@ -54,6 +54,9 @@ struct kstat {
>> u32 dio_offset_align;
>> u64 change_cookie;
>> u64 subvol;
>> + u32 atomic_write_unit_min;
>> + u32 atomic_write_unit_max;
>> + u32 atomic_write_segments_max;
>> };
>>
>> /* 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 67626d535316..887a25286441 100644
>> --- a/include/uapi/linux/stat.h
>> +++ b/include/uapi/linux/stat.h
>> @@ -126,9 +126,15 @@ struct statx {
>> __u64 stx_mnt_id;
>> __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
>> __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
>> - __u64 stx_subvol; /* Subvolume identifier */
>> /* 0xa0 */
>> - __u64 __spare3[11]; /* Spare space for future expansion */
>> + __u64 stx_subvol; /* Subvolume identifier */
>> + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
>> + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
>> + /* 0xb0 */
>> + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
>> + __u32 __spare1[1];
>> + /* 0xb8 */
>> + __u64 __spare3[9]; /* Spare space for future expansion */
>> /* 0x100 */
>> };
>>
>> @@ -157,6 +163,7 @@ struct statx {
>> #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
>> #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
>> #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
>> +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
>>
>> #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
>>
>> @@ -192,6 +199,7 @@ 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
>>
>>
© 2016 - 2026 Red Hat, Inc.