| Message ID | 20191020155935.12297-2-ira.weiny@intel.com |
|---|---|
| State | Not Applicable |
| Headers | show |
| Series | Enable per-file/directory DAX operations | expand |
On 20/10/2019 18:59, ira.weiny@intel.com wrote: > From: Ira Weiny <ira.weiny@intel.com> > > In order for users to determine if a file is currently operating in DAX > mode (effective DAX). Define a statx attribute value and set that > attribute if the effective DAX flag is set. > > To go along with this we propose the following addition to the statx man > page: > > STATX_ATTR_DAX > > DAX (cpu direct access) is a file mode that attempts to minimize > software cache effects for both I/O and memory mappings of this > file. It requires a capable device, a compatible filesystem > block size, and filesystem opt-in. It generally assumes all > accesses are via cpu load / store instructions which can > minimize overhead for small accesses, but adversely affect cpu > utilization for large transfers. File I/O is done directly > to/from user-space buffers. While the DAX property tends to > result in data being transferred synchronously it does not give > the guarantees of synchronous I/O that data and necessary > metadata are transferred. Memory mapped I/O may be performed > with direct mappings that bypass system memory buffering. Again > while memory-mapped I/O tends to result in data being > transferred synchronously it does not guarantee synchronous > metadata updates. A dax file may optionally support being mapped > with the MAP_SYNC flag which does allow cpu store operations to > be considered synchronous modulo cpu cache effects. > > Signed-off-by: Ira Weiny <ira.weiny@intel.com> > --- > fs/stat.c | 3 +++ > include/uapi/linux/stat.h | 1 + > 2 files changed, 4 insertions(+) > > diff --git a/fs/stat.c b/fs/stat.c > index c38e4c2e1221..59ca360c1ffb 100644 > --- a/fs/stat.c > +++ b/fs/stat.c > @@ -77,6 +77,9 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, > if (IS_AUTOMOUNT(inode)) > stat->attributes |= STATX_ATTR_AUTOMOUNT; > > + if (inode->i_flags & S_DAX) Is there a reason not to use IS_DAX(inode) ? > + stat->attributes |= STATX_ATTR_DAX; > + > if (inode->i_op->getattr) > return inode->i_op->getattr(path, stat, request_mask, > query_flags); > diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h > index 7b35e98d3c58..5b0962121ef7 100644 > --- a/include/uapi/linux/stat.h > +++ b/include/uapi/linux/stat.h > @@ -169,6 +169,7 @@ struct statx { > #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ > > #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ > +#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ > > > #endif /* _UAPI_LINUX_STAT_H */ >
On Tue, Oct 22, 2019 at 02:32:04PM +0300, Boaz Harrosh wrote: > On 20/10/2019 18:59, ira.weiny@intel.com wrote: > > From: Ira Weiny <ira.weiny@intel.com> > > > > In order for users to determine if a file is currently operating in DAX > > mode (effective DAX). Define a statx attribute value and set that > > attribute if the effective DAX flag is set. > > > > To go along with this we propose the following addition to the statx man > > page: > > > > STATX_ATTR_DAX > > > > DAX (cpu direct access) is a file mode that attempts to minimize > > software cache effects for both I/O and memory mappings of this > > file. It requires a capable device, a compatible filesystem > > block size, and filesystem opt-in. It generally assumes all > > accesses are via cpu load / store instructions which can > > minimize overhead for small accesses, but adversely affect cpu > > utilization for large transfers. File I/O is done directly > > to/from user-space buffers. While the DAX property tends to > > result in data being transferred synchronously it does not give > > the guarantees of synchronous I/O that data and necessary > > metadata are transferred. Memory mapped I/O may be performed > > with direct mappings that bypass system memory buffering. Again > > while memory-mapped I/O tends to result in data being > > transferred synchronously it does not guarantee synchronous > > metadata updates. A dax file may optionally support being mapped > > with the MAP_SYNC flag which does allow cpu store operations to > > be considered synchronous modulo cpu cache effects. > > > > Signed-off-by: Ira Weiny <ira.weiny@intel.com> > > --- > > fs/stat.c | 3 +++ > > include/uapi/linux/stat.h | 1 + > > 2 files changed, 4 insertions(+) > > > > diff --git a/fs/stat.c b/fs/stat.c > > index c38e4c2e1221..59ca360c1ffb 100644 > > --- a/fs/stat.c > > +++ b/fs/stat.c > > @@ -77,6 +77,9 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, > > if (IS_AUTOMOUNT(inode)) > > stat->attributes |= STATX_ATTR_AUTOMOUNT; > > > > + if (inode->i_flags & S_DAX) > > Is there a reason not to use IS_DAX(inode) ? No, just forgot there was a macro when this was written. Changed. Thanks, Ira > > > + stat->attributes |= STATX_ATTR_DAX; > > + > > if (inode->i_op->getattr) > > return inode->i_op->getattr(path, stat, request_mask, > > query_flags); > > diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h > > index 7b35e98d3c58..5b0962121ef7 100644 > > --- a/include/uapi/linux/stat.h > > +++ b/include/uapi/linux/stat.h > > @@ -169,6 +169,7 @@ struct statx { > > #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ > > > > #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ > > +#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ > > > > > > #endif /* _UAPI_LINUX_STAT_H */ > > >
diff --git a/fs/stat.c b/fs/stat.c index c38e4c2e1221..59ca360c1ffb 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -77,6 +77,9 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; + if (inode->i_flags & S_DAX) + stat->attributes |= STATX_ATTR_DAX; + if (inode->i_op->getattr) return inode->i_op->getattr(path, stat, request_mask, query_flags); diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 7b35e98d3c58..5b0962121ef7 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -169,6 +169,7 @@ struct statx { #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ #endif /* _UAPI_LINUX_STAT_H */