Virtualization - Aug 2021 - [Virtio-fs] [virtiofsd PATCH v4 4/4] virtiofsd: support per-file DAX in FUSE_LOOKUP

* Jeffle Xu (jefflexu at linux.alibaba.com) wrote:
> For passthrough, when the corresponding virtiofs in guest is mounted
> with '-o dax=inode', advertise that the file is capable of per-file
> DAX if the inode in the backend fs is marked with FS_DAX_FL flag.
> 
> Signed-off-by: Jeffle Xu <jefflexu at linux.alibaba.com>
> ---
>  tools/virtiofsd/passthrough_ll.c | 43 ++++++++++++++++++++++++++++++++
>  1 file changed, 43 insertions(+)
> 
> diff --git a/tools/virtiofsd/passthrough_ll.c
b/tools/virtiofsd/passthrough_ll.c
> index 5b6228210f..4cbd904248 100644
> --- a/tools/virtiofsd/passthrough_ll.c
> +++ b/tools/virtiofsd/passthrough_ll.c
> @@ -171,6 +171,7 @@ struct lo_data {
>      int allow_direct_io;
>      int announce_submounts;
>      int perfile_dax_cap; /* capability of backend fs */
> +    bool perfile_dax; /* enable per-file DAX or not */
>      bool use_statx;
>      struct lo_inode root;
>      GHashTable *inodes; /* protected by lo->mutex */
> @@ -716,6 +717,10 @@ static void lo_init(void *userdata, struct
fuse_conn_info *conn)
>  
>      if (conn->capable & FUSE_CAP_PERFILE_DAX &&
lo->perfile_dax_cap ) {
>          conn->want |= FUSE_CAP_PERFILE_DAX;
> +	lo->perfile_dax = 1;
> +    }
> +    else {
> +	lo->perfile_dax = 0;
>      }
>  }
>  
> @@ -983,6 +988,41 @@ static int do_statx(struct lo_data *lo, int dirfd,
const char *pathname,
>      return 0;
>  }
>  
> +/*
> + * If the file is marked with FS_DAX_FL or FS_XFLAG_DAX, then DAX should
be
> + * enabled for this file.
> + */
> +static bool lo_should_enable_dax(struct lo_data *lo, struct lo_inode *dir,
> +				 const char *name)
> +{
> +    int res, fd;
> +    int ret = false;;
> +    unsigned int attr;
> +    struct fsxattr xattr;
> +
> +    if (!lo->perfile_dax)
> +	return false;
> +
> +    /* Open file without O_PATH, so that ioctl can be called. */
> +    fd = openat(dir->fd, name, O_NOFOLLOW);
> +    if (fd == -1)
> +        return false;
Doesn't that defeat the whole benefit of using O_PATH - i.e. that we
might stumble into a /dev node or something else we're not allowed to
open?
> +    if (lo->perfile_dax_cap == DAX_CAP_FLAGS) {
> +        res = ioctl(fd, FS_IOC_GETFLAGS, &attr);
> +        if (!res && (attr & FS_DAX_FL))
> +	    ret = true;
> +    }
> +    else if (lo->perfile_dax_cap == DAX_CAP_XATTR) {
> +	res = ioctl(fd, FS_IOC_FSGETXATTR, &xattr);
> +	if (!res && (xattr.fsx_xflags & FS_XFLAG_DAX))
> +	    ret = true;
> +    }
This all looks pretty expensive for each lookup.

Dave

> +    close(fd);
> +    return ret;
> +}
> +
>  /*
>   * Increments nlookup on the inode on success. unref_inode_lolocked() must
be
>   * called eventually to decrement nlookup again. If inodep is non-NULL,
the
> @@ -1038,6 +1078,9 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t
parent, const char *name,
>          e->attr_flags |= FUSE_ATTR_SUBMOUNT;
>      }
>  
> +    if (lo_should_enable_dax(lo, dir, name))
> +	e->attr_flags |= FUSE_ATTR_DAX;
> +
>      inode = lo_find(lo, &e->attr, mnt_id);
>      if (inode) {
>          close(newfd);
> -- 
> 2.27.0
> 
> _______________________________________________
> Virtio-fs mailing list
> Virtio-fs at redhat.com
> https://listman.redhat.com/mailman/listinfo/virtio-fs
> 
-- 
Dr. David Alan Gilbert / dgilbert at redhat.com / Manchester, UK

On 8/18/21 3:00 AM, Dr. David Alan Gilbert wrote:
> * Jeffle Xu (jefflexu at linux.alibaba.com) wrote:
>> For passthrough, when the corresponding virtiofs in guest is mounted
>> with '-o dax=inode', advertise that the file is capable of
per-file
>> DAX if the inode in the backend fs is marked with FS_DAX_FL flag.
>>
>> Signed-off-by: Jeffle Xu <jefflexu at linux.alibaba.com>
>> ---
>>  tools/virtiofsd/passthrough_ll.c | 43 ++++++++++++++++++++++++++++++++
>>  1 file changed, 43 insertions(+)
>>
>> diff --git a/tools/virtiofsd/passthrough_ll.c
b/tools/virtiofsd/passthrough_ll.c
>> index 5b6228210f..4cbd904248 100644
>> --- a/tools/virtiofsd/passthrough_ll.c
>> +++ b/tools/virtiofsd/passthrough_ll.c
>> @@ -171,6 +171,7 @@ struct lo_data {
>>      int allow_direct_io;
>>      int announce_submounts;
>>      int perfile_dax_cap; /* capability of backend fs */
>> +    bool perfile_dax; /* enable per-file DAX or not */
>>      bool use_statx;
>>      struct lo_inode root;
>>      GHashTable *inodes; /* protected by lo->mutex */
>> @@ -716,6 +717,10 @@ static void lo_init(void *userdata, struct
fuse_conn_info *conn)
>>  
>>      if (conn->capable & FUSE_CAP_PERFILE_DAX &&
lo->perfile_dax_cap ) {
>>          conn->want |= FUSE_CAP_PERFILE_DAX;
>> +	lo->perfile_dax = 1;
>> +    }
>> +    else {
>> +	lo->perfile_dax = 0;
>>      }
>>  }
>>  
>> @@ -983,6 +988,41 @@ static int do_statx(struct lo_data *lo, int dirfd,
const char *pathname,
>>      return 0;
>>  }
>>  
>> +/*
>> + * If the file is marked with FS_DAX_FL or FS_XFLAG_DAX, then DAX
should be
>> + * enabled for this file.
>> + */
>> +static bool lo_should_enable_dax(struct lo_data *lo, struct lo_inode
*dir,
>> +				 const char *name)
>> +{
>> +    int res, fd;
>> +    int ret = false;;
>> +    unsigned int attr;
>> +    struct fsxattr xattr;
>> +
>> +    if (!lo->perfile_dax)
>> +	return false;
>> +
>> +    /* Open file without O_PATH, so that ioctl can be called. */
>> +    fd = openat(dir->fd, name, O_NOFOLLOW);
>> +    if (fd == -1)
>> +        return false;
> 
> Doesn't that defeat the whole benefit of using O_PATH - i.e. that we
> might stumble into a /dev node or something else we're not allowed to
> open?
As far as I know, virtiofsd will pivot_root/chroot to the source
directory, and can only access files inside the source directory
specified by "-o source=". Then where do these unexpected files come
from? Besides, fd opened without O_PATH here is temporary and used for
FS_IOC_GETFLAGS/FS_IOC_FSGETXATTR ioctl only. It's closed when the
function returns.
> 
>> +    if (lo->perfile_dax_cap == DAX_CAP_FLAGS) {
>> +        res = ioctl(fd, FS_IOC_GETFLAGS, &attr);
>> +        if (!res && (attr & FS_DAX_FL))
>> +	    ret = true;
>> +    }
>> +    else if (lo->perfile_dax_cap == DAX_CAP_XATTR) {
>> +	res = ioctl(fd, FS_IOC_FSGETXATTR, &xattr);
>> +	if (!res && (xattr.fsx_xflags & FS_XFLAG_DAX))
>> +	    ret = true;
>> +    }
> 
> This all looks pretty expensive for each lookup.
Yes. it can be somehow optimized if we can agree on the way of storing
the dax flag persistently.

-- 
Thanks,
Jeffle