Re: [PATCH RFC 11/11] NFSD: Implement the CLONE call

["J. Bruce Fields" <bfields@fieldses.org>]

On Tue, Aug 25, 2015 at 11:33:49PM +0800, Peng Tao wrote:
> From: Anna Schumaker <bjschuma@netapp.com>
> 
> I can simply call vfs_file_clone_range() and have the vfs do the
> right thing for the filesystem being exported.
> 
> Signed-off-by: Anna Schumaker <bjschuma@netapp.com>
> [hch: change to implement the CLONE op instead of COPY]
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Peng Tao <tao.peng@primarydata.com>
> ---
>  fs/nfsd/nfs4proc.c   | 79 ++++++++++++++++++++++++++++++++++++++++++++++++++++
>  fs/nfsd/nfs4xdr.c    | 21 ++++++++++++++
>  fs/nfsd/vfs.c        |  7 +++++
>  fs/nfsd/vfs.h        |  1 +
>  fs/nfsd/xdr4.h       | 10 +++++++
>  include/linux/nfs4.h |  4 +--
>  6 files changed, 120 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
> index d34c967..c2d3558 100644
> --- a/fs/nfsd/nfs4proc.c
> +++ b/fs/nfsd/nfs4proc.c
> @@ -1014,6 +1014,79 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
>  }
>  
>  static __be32
> +nfsd4_verify_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> +		  struct nfsd4_clone *clone, struct file **src, struct file **dst)
> +{
> +	struct inode *src_ino, *dst_ino;
> +	__be32 status;
> +
> +	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
> +					    &clone->cl_src_stateid, RD_STATE,
> +					    src, NULL);
> +	if (status) {
> +		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
> +		return status;
> +	}
> +
> +	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
> +					    &clone->cl_dst_stateid, WR_STATE,
> +					    dst, NULL);
> +	if (status) {
> +		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
> +		fput(*src);
> +	}
> +
> +	/* a few extra check to make sure we send back proper errors per RFC */
> +	src_ino = file_inode(*src);
> +	dst_ino = file_inode(*dst);
> +
> +        if (S_ISDIR(src_ino->i_mode) || S_ISDIR(dst_ino->i_mode)) {
> +		status = nfserr_wrong_type;
> +		goto out_fput;
> +	}
> +
> +	if (src_ino == dst_ino) {
> +		status = nfserr_inval;
> +		goto out_fput;
> +	}
> +
> +	if (!(*src)->f_op || !(*src)->f_op->clone_range) {
> +		status = nfserr_notsupp;
> +		goto out_fput;
> +	}
> +out:
> +	return status;
> +out_fput:
> +	fput(*src);
> +	fput(*dst);
> +	goto out;
> +}
> +
> +static __be32
> +nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> +		struct nfsd4_clone *clone)
> +{
> +	int ret;
> +	__be32 status;
> +	struct file *src = NULL, *dst = NULL;
> +
> +	status = nfsd4_verify_clone(rqstp, cstate, clone, &src, &dst);
> +	if (status)
> +		return status;
> +
> +	ret = nfsd4_clone_range(src, dst, clone->cl_src_pos,
> +				clone->cl_count, clone->cl_dst_pos);
> +	if (ret < 0)
> +		status = nfserrno(ret);
> +	else
> +		status = nfs_ok;

Can ret be positive, then?  If so are we discarding some information?
(E.g. can clone_range return a success having cloned only part of the
range?)

--b.

> +
> +	fput(src);
> +	fput(dst);
> +	return status;
> +}
> +
> +static __be32
>  nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
>  		struct nfsd4_fallocate *fallocate, int flags)
>  {
> @@ -2283,6 +2356,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
>  		.op_name = "OP_DEALLOCATE",
>  		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
>  	},
> +	[OP_CLONE] = {
> +		.op_func = (nfsd4op_func)nfsd4_clone,
> +		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
> +		.op_name = "OP_CLONE",
> +		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
> +	},
>  	[OP_SEEK] = {
>  		.op_func = (nfsd4op_func)nfsd4_seek,
>  		.op_name = "OP_SEEK",
> diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
> index 5463385..a845db1 100644
> --- a/fs/nfsd/nfs4xdr.c
> +++ b/fs/nfsd/nfs4xdr.c
> @@ -1675,6 +1675,25 @@ nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp,
>  }
>  
>  static __be32
> +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone)
> +{
> +	DECODE_HEAD;
> +
> +	status = nfsd4_decode_stateid(argp, &clone->cl_src_stateid);
> +	if (status)
> +		return status;
> +	status = nfsd4_decode_stateid(argp, &clone->cl_dst_stateid);
> +	if (status)
> +		return status;
> +
> +	READ_BUF(8 + 8 + 8);
> +	p = xdr_decode_hyper(p, &clone->cl_src_pos);
> +	p = xdr_decode_hyper(p, &clone->cl_dst_pos);
> +	p = xdr_decode_hyper(p, &clone->cl_count);
> +	DECODE_TAIL;
> +}
> +
> +static __be32
>  nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
>  {
>  	DECODE_HEAD;
> @@ -1785,6 +1804,7 @@ static nfsd4_dec nfsd4_dec_ops[] = {
>  	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
>  	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
>  	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
> +	[OP_CLONE]		= (nfsd4_dec)nfsd4_decode_clone,
>  };
>  
>  static inline bool
> @@ -4249,6 +4269,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
>  	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
>  	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
>  	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
> +	[OP_CLONE]		= (nfsd4_enc)nfsd4_encode_noop,
>  };
>  
>  /*
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index b5e077a..7d43097 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -36,6 +36,7 @@
>  #endif /* CONFIG_NFSD_V3 */
>  
>  #ifdef CONFIG_NFSD_V4
> +#include "../internal.h"
>  #include "acl.h"
>  #include "idmap.h"
>  #endif /* CONFIG_NFSD_V4 */
> @@ -498,6 +499,12 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
>  }
>  #endif
>  
> +int nfsd4_clone_range(struct file *src, struct file *dst, u64 src_pos,
> +		      u64 count, u64 dst_pos)
> +{
> +	return vfs_file_clone_range(src, dst, src_pos, count, dst_pos);
> +}
> +
>  __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
>  			   struct file *file, loff_t offset, loff_t len,
>  			   int flags)
> diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
> index 5be875e..31d56a3 100644
> --- a/fs/nfsd/vfs.h
> +++ b/fs/nfsd/vfs.h
> @@ -56,6 +56,7 @@ __be32          nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
>  		    struct xdr_netobj *);
>  __be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
>  				    struct file *, loff_t, loff_t, int);
> +int		nfsd4_clone_range(struct file *, struct file *, u64, u64, u64);
>  #endif /* CONFIG_NFSD_V4 */
>  __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
>  				char *name, int len, struct iattr *attrs,
> diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
> index 9f99100..3d70712 100644
> --- a/fs/nfsd/xdr4.h
> +++ b/fs/nfsd/xdr4.h
> @@ -491,6 +491,15 @@ struct nfsd4_fallocate {
>  	u64		falloc_length;
>  };
>  
> +struct nfsd4_clone {
> +	/* request */
> +	stateid_t	cl_src_stateid;
> +	stateid_t	cl_dst_stateid;
> +	u64		cl_src_pos;
> +	u64		cl_dst_pos;
> +	u64		cl_count;
> +};
> +
>  struct nfsd4_seek {
>  	/* request */
>  	stateid_t	seek_stateid;
> @@ -555,6 +564,7 @@ struct nfsd4_op {
>  		/* NFSv4.2 */
>  		struct nfsd4_fallocate		allocate;
>  		struct nfsd4_fallocate		deallocate;
> +		struct nfsd4_clone		clone;
>  		struct nfsd4_seek		seek;
>  	} u;
>  	struct nfs4_replay *			replay;
> diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
> index e7e7853..21c6612 100644
> --- a/include/linux/nfs4.h
> +++ b/include/linux/nfs4.h
> @@ -139,10 +139,10 @@ enum nfs_opnum4 {
>  Needs to be updated if more operations are defined in future.*/
>  
>  #define FIRST_NFS4_OP	OP_ACCESS
> -#define LAST_NFS4_OP 	OP_WRITE_SAME
>  #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
>  #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
> -#define LAST_NFS42_OP	OP_WRITE_SAME
> +#define LAST_NFS42_OP	OP_CLONE
> +#define LAST_NFS4_OP 	LAST_NFS42_OP
>  
>  enum nfsstat4 {
>  	NFS4_OK = 0,
> -- 
> 1.8.3.1