| Message ID | 20240219130109.341523-5-john.g.garry@oracle.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | block atomic writes | expand |
John Garry <john.g.garry@oracle.com> writes: > 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. > > Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com> > #jpg: relocate bdev support to another patch ^^^ miss maybe? > 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 | 9 ++++++++- > 4 files changed, 48 insertions(+), 1 deletion(-) > > diff --git a/fs/stat.c b/fs/stat.c > index 77cdc69eb422..522787a4ab6a 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 the atomic writes statx attributes > + * @stat: Where to fill in the attribute flags > + * @unit_min: Minimum supported atomic write length + * @unit_min: Minimum supported atomic write length in bytes > + * @unit_max: Maximum supported atomic write length + * @unit_max: Maximum supported atomic write length in bytes mentioning unit of the length might be useful here. > + * > + * 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, This (unit_min) can still go above in the same line. > + 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; Please log info about this in commit message about where this limit came from? Is it since we only support ubuf (which IIUC, only supports 1 segment)? Later when we will add support for iovec, this limit can be lifted? > + > + /* Confirm atomic writes are actually supported */ > + stat->attributes |= STATX_ATTR_WRITE_ATOMIC; > + } > +} > +EXPORT_SYMBOL(generic_fill_statx_atomic_writes); > + > /** > * vfs_getattr_nosec - getattr without security checks > * @path: file to get attributes from > @@ -658,6 +689,9 @@ 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; > + 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 7271640fd600..531140a7e27a 100644 > --- a/include/linux/fs.h > +++ b/include/linux/fs.h > @@ -3167,6 +3167,9 @@ 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); We can make 80 col. width even with unit_min in the same first line as of *stat. > 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 52150570d37a..2c5e2b8c6559 100644 > --- a/include/linux/stat.h > +++ b/include/linux/stat.h > @@ -53,6 +53,9 @@ struct kstat { > u32 dio_mem_align; > u32 dio_offset_align; > u64 change_cookie; > + 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 2f2ee82d5517..c0e8e10d1de6 100644 > --- a/include/uapi/linux/stat.h > +++ b/include/uapi/linux/stat.h > @@ -127,7 +127,12 @@ 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_min; > + __u32 stx_atomic_write_unit_max; > + __u32 stx_atomic_write_segments_max; Let's add one liner for each of these fields similar to how it was done for others? /* Minimum supported atomic write length in bytes */ /* Maximum supported atomic write length in bytes */ /* Maximum no. of segments (iovecs?) supported for atomic write */ > + __u32 __spare1; > + /* 0xb0 */ > + __u64 __spare3[10]; /* Spare space for future expansion */ > /* 0x100 */ > }; > > @@ -155,6 +160,7 @@ struct statx { > #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ > #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_WRITE_ATOMIC 0x00008000U /* Want/got atomic_write_* fields */ > > #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ > > @@ -190,6 +196,7 @@ 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 24/02/2024 18:46, Ritesh Harjani (IBM) wrote: > John Garry <john.g.garry@oracle.com> writes: > >> 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. >> >> Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com> >> #jpg: relocate bdev support to another patch > > ^^^ miss maybe? >> 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 | 9 ++++++++- >> 4 files changed, 48 insertions(+), 1 deletion(-) >> >> diff --git a/fs/stat.c b/fs/stat.c >> index 77cdc69eb422..522787a4ab6a 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 the atomic writes statx attributes >> + * @stat: Where to fill in the attribute flags >> + * @unit_min: Minimum supported atomic write length > + * @unit_min: Minimum supported atomic write length in bytes > > >> + * @unit_max: Maximum supported atomic write length > + * @unit_max: Maximum supported atomic write length in bytes > > mentioning unit of the length might be useful here. Yeah, I have already improved this as suggested. > >> + * >> + * 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, > > This (unit_min) can still go above in the same line. ok > >> + 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; > > Please log info about this in commit message about where this limit came > from? ok > Is it since we only support ubuf (which IIUC, only supports 1 > segment)? Later when we will add support for iovec, this limit can be > lifted? It's not that we only support ubuf, but rather we only support one segment and that gives a ubuf type iter. This is all related to how can can guarantee a unit_max advertised to userspace can always be written atomically. This is further mentioned in the block layer patch. > >> + >> + /* Confirm atomic writes are actually supported */ >> + stat->attributes |= STATX_ATTR_WRITE_ATOMIC; >> + } >> +} >> +EXPORT_SYMBOL(generic_fill_statx_atomic_writes); >> + >> /** >> * vfs_getattr_nosec - getattr without security checks >> * @path: file to get attributes from >> @@ -658,6 +689,9 @@ 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; >> + 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 7271640fd600..531140a7e27a 100644 >> --- a/include/linux/fs.h >> +++ b/include/linux/fs.h >> @@ -3167,6 +3167,9 @@ 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); > > We can make 80 col. width even with unit_min in the same first line as of *stat. ok, I can check this. > > >> 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 52150570d37a..2c5e2b8c6559 100644 >> --- a/include/linux/stat.h >> +++ b/include/linux/stat.h >> @@ -53,6 +53,9 @@ struct kstat { >> u32 dio_mem_align; >> u32 dio_offset_align; >> u64 change_cookie; >> + 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 2f2ee82d5517..c0e8e10d1de6 100644 >> --- a/include/uapi/linux/stat.h >> +++ b/include/uapi/linux/stat.h >> @@ -127,7 +127,12 @@ 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_min; >> + __u32 stx_atomic_write_unit_max; >> + __u32 stx_atomic_write_segments_max; > > Let's add one liner for each of these fields similar to how it was done > for others? > > /* Minimum supported atomic write length in bytes */ > /* Maximum supported atomic write length in bytes */ > /* Maximum no. of segments (iovecs?) supported for atomic write */ ok > > >> + __u32 __spare1; >> + /* 0xb0 */ >> + __u64 __spare3[10]; /* Spare space for future expansion */ >> /* 0x100 */ >> }; >> >> @@ -155,6 +160,7 @@ struct statx { >> #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ >> #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_WRITE_ATOMIC 0x00008000U /* Want/got atomic_write_* fields */ >> >> #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ >> >> @@ -190,6 +196,7 @@ 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 Thanks, John
diff --git a/fs/stat.c b/fs/stat.c index 77cdc69eb422..522787a4ab6a 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 the atomic writes statx attributes + * @stat: Where to fill in the attribute flags + * @unit_min: Minimum supported atomic write length + * @unit_max: Maximum supported atomic write length + * + * 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(generic_fill_statx_atomic_writes); + /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from @@ -658,6 +689,9 @@ 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; + 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 7271640fd600..531140a7e27a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3167,6 +3167,9 @@ 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 52150570d37a..2c5e2b8c6559 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,9 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + 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 2f2ee82d5517..c0e8e10d1de6 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -127,7 +127,12 @@ 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_min; + __u32 stx_atomic_write_unit_max; + __u32 stx_atomic_write_segments_max; + __u32 __spare1; + /* 0xb0 */ + __u64 __spare3[10]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +160,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #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_WRITE_ATOMIC 0x00008000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -190,6 +196,7 @@ 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 */