diff mbox series

[v7,04/11] NFS: add COPY_NOTIFY operation

Message ID 20181030205614.40754-6-olga.kornievskaia@gmail.com (mailing list archive)
State New, archived
Headers show
Series client-side support for "inter" SSC copy | expand

Commit Message

Olga Kornievskaia Oct. 30, 2018, 8:56 p.m. UTC
From: Olga Kornievskaia <kolga@netapp.com>

Try using the delegation stateid, then the open stateid.

Only NL4_NETATTR, No support for NL4_NAME and NL4_URL.
Allow only one source server address to be returned for now.

To distinguish between same server copy offload ("intra") and
a copy between different server ("inter"), do a check of server
owner identity.

Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
---
 fs/nfs/nfs42.h            |  12 +++
 fs/nfs/nfs42proc.c        |  91 +++++++++++++++++++++++
 fs/nfs/nfs42xdr.c         | 181 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h          |   2 +
 fs/nfs/nfs4client.c       |   2 +-
 fs/nfs/nfs4file.c         |  14 ++++
 fs/nfs/nfs4proc.c         |   1 +
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   1 +
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |  16 ++++
 11 files changed, 321 insertions(+), 1 deletion(-)

Comments

Schumaker, Anna Oct. 31, 2018, 3:07 p.m. UTC | #1
Hi Olga,

On Tue, 2018-10-30 at 16:56 -0400, Olga Kornievskaia wrote:
> From: Olga Kornievskaia <kolga@netapp.com>
> 
> Try using the delegation stateid, then the open stateid.
> 
> Only NL4_NETATTR, No support for NL4_NAME and NL4_URL.
> Allow only one source server address to be returned for now.
> 
> To distinguish between same server copy offload ("intra") and
> a copy between different server ("inter"), do a check of server
> owner identity.
> 
> Reviewed-by: Jeff Layton <jlayton@redhat.com>
> Signed-off-by: Andy Adamson <andros@netapp.com>
> Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
> ---
>  fs/nfs/nfs42.h            |  12 +++
>  fs/nfs/nfs42proc.c        |  91 +++++++++++++++++++++++
>  fs/nfs/nfs42xdr.c         | 181
> ++++++++++++++++++++++++++++++++++++++++++++++
>  fs/nfs/nfs4_fs.h          |   2 +
>  fs/nfs/nfs4client.c       |   2 +-
>  fs/nfs/nfs4file.c         |  14 ++++
>  fs/nfs/nfs4proc.c         |   1 +
>  fs/nfs/nfs4xdr.c          |   1 +
>  include/linux/nfs4.h      |   1 +
>  include/linux/nfs_fs_sb.h |   1 +
>  include/linux/nfs_xdr.h   |  16 ++++
>  11 files changed, 321 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
> index 19ec38f8..bbe49a3 100644
> --- a/fs/nfs/nfs42.h
> +++ b/fs/nfs/nfs42.h
> @@ -13,6 +13,7 @@
>  #define PNFS_LAYOUTSTATS_MAXDEV (4)
>  
>  /* nfs4.2proc.c */
> +#ifdef CONFIG_NFS_V4_2
>  int nfs42_proc_allocate(struct file *, loff_t, loff_t);
>  ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t,
> size_t);
>  int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
> @@ -20,5 +21,16 @@
>  int nfs42_proc_layoutstats_generic(struct nfs_server *,
>  				   struct nfs42_layoutstat_data *);
>  int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
> +int nfs42_proc_copy_notify(struct file *, struct file *,
> +			   struct nfs42_copy_notify_res *);
> +static inline bool nfs42_files_from_same_server(struct file *in,
> +						struct file *out)
> +{
> +	struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client;
> +	struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client;
>  
> +	return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
> +				c_out->cl_serverowner);
> +}
> +#endif /* CONFIG_NFS_V4_2 */
>  #endif /* __LINUX_FS_NFS_NFS4_2_H */
> diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
> index ac5b784..b1c57a4 100644
> --- a/fs/nfs/nfs42proc.c
> +++ b/fs/nfs/nfs42proc.c
> @@ -3,6 +3,7 @@
>   * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
>   */
>  #include <linux/fs.h>
> +#include <linux/sunrpc/addr.h>
>  #include <linux/sunrpc/sched.h>
>  #include <linux/nfs.h>
>  #include <linux/nfs3.h>
> @@ -15,10 +16,30 @@
>  #include "pnfs.h"
>  #include "nfs4session.h"
>  #include "internal.h"
> +#include "delegation.h"
>  
>  #define NFSDBG_FACILITY NFSDBG_PROC
>  static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid
> *std);
>  
> +static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr
> *naddr)
> +{
> +	struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client;
> +	unsigned short port = 2049;
> +
> +	rcu_read_lock();
> +	naddr->netid_len = scnprintf(naddr->netid,
> +					sizeof(naddr->netid), "%s",
> +					rpc_peeraddr2str(clp->cl_rpcclient,
> +					RPC_DISPLAY_NETID));
> +	naddr->addr_len = scnprintf(naddr->addr,
> +					sizeof(naddr->addr),
> +					"%s.%u.%u",
> +					rpc_peeraddr2str(clp->cl_rpcclient,
> +					RPC_DISPLAY_ADDR),
> +					port >> 8, port & 255);
> +	rcu_read_unlock();
> +}
> +
>  static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
>  		struct nfs_lock_context *lock, loff_t offset, loff_t len)
>  {
> @@ -461,6 +482,76 @@ static int nfs42_do_offload_cancel_async(struct file
> *dst,
>  	return status;
>  }
>  
> +int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
> +			    struct nfs42_copy_notify_args *args,
> +			    struct nfs42_copy_notify_res *res)
> +{
> +	struct nfs_server *src_server = NFS_SERVER(file_inode(src));
> +	struct rpc_message msg = {
> +		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY],
> +		.rpc_argp = args,
> +		.rpc_resp = res,
> +	};
> +	int status;
> +	struct nfs_open_context *ctx;
> +	struct nfs_lock_context *l_ctx;
> +
> +	ctx = get_nfs_open_context(nfs_file_open_context(src));
> +	l_ctx = nfs_get_lock_context(ctx);
> +	if (IS_ERR(l_ctx))
> +		return PTR_ERR(l_ctx);
> +
> +	status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
> +				     FMODE_READ);
> +	nfs_put_lock_context(l_ctx);
> +	if (status)
> +		return status;
> +
> +	status = nfs4_call_sync(src_server->client, src_server, &msg,
> +				&args->cna_seq_args, &res->cnr_seq_res, 0);
> +	if (status == -ENOTSUPP)
> +		src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
> +
> +	put_nfs_open_context(nfs_file_open_context(src));
> +	return status;
> +}
> +
> +int nfs42_proc_copy_notify(struct file *src, struct file *dst,
> +				struct nfs42_copy_notify_res *res)
> +{
> +	struct nfs_server *src_server = NFS_SERVER(file_inode(src));
> +	struct nfs42_copy_notify_args *args;
> +	struct nfs4_exception exception = {
> +		.inode = file_inode(src),
> +	};
> +	int status;
> +
> +	if (!(src_server->caps & NFS_CAP_COPY_NOTIFY))
> +		return -EOPNOTSUPP;
> +
> +	args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS);
> +	if (args == NULL)
> +		return -ENOMEM;
> +
> +	args->cna_src_fh  = NFS_FH(file_inode(src)),
> +	args->cna_dst.nl4_type = NL4_NETADDR;
> +	nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr);
> +	exception.stateid = &args->cna_src_stateid;
> +
> +	do {
> +		status = _nfs42_proc_copy_notify(src, dst, args, res);
> +		if (status == -ENOTSUPP) {
> +			status = -EOPNOTSUPP;
> +			goto out;
> +		}
> +		status = nfs4_handle_exception(src_server, status, &exception);
> +	} while (exception.retry);
> +
> +out:
> +	kfree(args);
> +	return status;
> +}
> +
>  static loff_t _nfs42_proc_llseek(struct file *filep,
>  		struct nfs_lock_context *lock, loff_t offset, int whence)
>  {
> diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
> index 69f72ed..e6e7cbf 100644
> --- a/fs/nfs/nfs42xdr.c
> +++ b/fs/nfs/nfs42xdr.c
> @@ -29,6 +29,16 @@
>  #define encode_offload_cancel_maxsz	(op_encode_hdr_maxsz + \
>  					 XDR_QUADLEN(NFS4_STATEID_SIZE))
>  #define decode_offload_cancel_maxsz	(op_decode_hdr_maxsz)
> +#define encode_copy_notify_maxsz	(op_encode_hdr_maxsz + \
> +					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
> +					 1 + /* nl4_type */ \
> +					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
> +#define decode_copy_notify_maxsz	(op_decode_hdr_maxsz + \
> +					 3 + /* cnr_lease_time */\
> +					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
> +					 1 + /* Support 1 cnr_source_server */\
> +					 1 + /* nl4_type */ \
> +					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
>  #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
>  					 encode_fallocate_maxsz)
>  #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
> @@ -84,6 +94,12 @@
>  #define NFS4_dec_offload_cancel_sz	(compound_decode_hdr_maxsz + \
>  					 decode_putfh_maxsz + \
>  					 decode_offload_cancel_maxsz)
> +#define NFS4_enc_copy_notify_sz		(compound_encode_hdr_maxsz + \
> +					 encode_putfh_maxsz + \
> +					 encode_copy_notify_maxsz)
> +#define NFS4_dec_copy_notify_sz		(compound_decode_hdr_maxsz + \
> +					 decode_putfh_maxsz + \
> +					 decode_copy_notify_maxsz)
>  #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
>  					 encode_putfh_maxsz + \
>  					 encode_deallocate_maxsz + \
> @@ -137,6 +153,25 @@ static void encode_allocate(struct xdr_stream *xdr,
>  	encode_fallocate(xdr, args);
>  }
>  
> +static void encode_nl4_server(struct xdr_stream *xdr, const struct nl4_server
> *ns)
> +{
> +	encode_uint32(xdr, ns->nl4_type);
> +	switch (ns->nl4_type) {
> +	case NL4_NAME:
> +	case NL4_URL:
> +		encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str);
> +		break;
> +	case NL4_NETADDR:
> +		encode_string(xdr, ns->u.nl4_addr.netid_len,
> +			      ns->u.nl4_addr.netid);
> +		encode_string(xdr, ns->u.nl4_addr.addr_len,
> +			      ns->u.nl4_addr.addr);
> +		break;
> +	default:
> +		WARN_ON_ONCE(1);
> +	}
> +}
> +
>  static void encode_copy(struct xdr_stream *xdr,
>  			const struct nfs42_copy_args *args,
>  			struct compound_hdr *hdr)
> @@ -162,6 +197,15 @@ static void encode_offload_cancel(struct xdr_stream *xdr,
>  	encode_nfs4_stateid(xdr, &args->osa_stateid);
>  }
>  
> +static void encode_copy_notify(struct xdr_stream *xdr,
> +			       const struct nfs42_copy_notify_args *args,
> +			       struct compound_hdr *hdr)
> +{
> +	encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr);
> +	encode_nfs4_stateid(xdr, &args->cna_src_stateid);
> +	encode_nl4_server(xdr, &args->cna_dst);
> +}
> +
>  static void encode_deallocate(struct xdr_stream *xdr,
>  			      const struct nfs42_falloc_args *args,
>  			      struct compound_hdr *hdr)
> @@ -298,6 +342,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst
> *req,
>  }
>  
>  /*
> + * Encode COPY_NOTIFY request
> + */
> +static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req,
> +				     struct xdr_stream *xdr,
> +				     const void *data)
> +{
> +	const struct nfs42_copy_notify_args *args = data;
> +	struct compound_hdr hdr = {
> +		.minorversion = nfs4_xdr_minorversion(&args->cna_seq_args),
> +	};
> +
> +	encode_compound_hdr(xdr, req, &hdr);
> +	encode_sequence(xdr, &args->cna_seq_args, &hdr);
> +	encode_putfh(xdr, args->cna_src_fh, &hdr);
> +	encode_copy_notify(xdr, args, &hdr);
> +	encode_nops(&hdr);
> +}
> +
> +/*
>   * Encode DEALLOCATE request
>   */
>  static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
> @@ -416,6 +479,58 @@ static int decode_write_response(struct xdr_stream *xdr,
>  	return -EIO;
>  }
>  
> +static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns)
> +{
> +	struct nfs42_netaddr *naddr;
> +	uint32_t dummy;
> +	char *dummy_str;
> +	__be32 *p;
> +	int status;
> +
> +	/* nl_type */
> +	p = xdr_inline_decode(xdr, 4);
> +	if (unlikely(!p))
> +		return -EIO;
> +	ns->nl4_type = be32_to_cpup(p);
> +	switch (ns->nl4_type) {
> +	case NL4_NAME:
> +	case NL4_URL:
> +		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
> +		if (unlikely(status))
> +			return status;
> +		if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
> +			return -EIO;
> +		memcpy(&ns->u.nl4_str, dummy_str, dummy);
> +		ns->u.nl4_str_sz = dummy;
> +		break;
> +	case NL4_NETADDR:
> +		naddr = &ns->u.nl4_addr;
> +
> +		/* netid string */
> +		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
> +		if (unlikely(status))
> +			return status;
> +		if (unlikely(dummy > RPCBIND_MAXNETIDLEN))
> +			return -EIO;
> +		naddr->netid_len = dummy;
> +		memcpy(naddr->netid, dummy_str, naddr->netid_len);
> +
> +		/* uaddr string */
> +		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
> +		if (unlikely(status))
> +			return status;
> +		if (unlikely(dummy > RPCBIND_MAXUADDRLEN))
> +			return -EIO;
> +		naddr->addr_len = dummy;
> +		memcpy(naddr->addr, dummy_str, naddr->addr_len);
> +		break;
> +	default:
> +		WARN_ON_ONCE(1);
> +		return -EIO;
> +	}
> +	return 0;
> +}
> +
>  static int decode_copy_requirements(struct xdr_stream *xdr,
>  				    struct nfs42_copy_res *res) {
>  	__be32 *p;
> @@ -458,6 +573,46 @@ static int decode_offload_cancel(struct xdr_stream *xdr,
>  	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
>  }
>  
> +static int decode_copy_notify(struct xdr_stream *xdr,
> +			      struct nfs42_copy_notify_res *res)
> +{
> +	__be32 *p;
> +	int status, count;
> +
> +	status = decode_op_hdr(xdr, OP_COPY_NOTIFY);
> +	if (status)
> +		return status;
> +	/* cnr_lease_time */
> +	p = xdr_inline_decode(xdr, 12);
> +	if (unlikely(!p))
> +		goto out_overflow;
> +	p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds);
> +	res->cnr_lease_time.nseconds = be32_to_cpup(p);
> +
> +	status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE);
> +	if (unlikely(status))
> +		goto out_overflow;
> +
> +	/* number of source addresses */
> +	p = xdr_inline_decode(xdr, 4);
> +	if (unlikely(!p))
> +		goto out_overflow;
> +
> +	count = be32_to_cpup(p);
> +	if (count > 1)
> +		pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n",
> +			 __func__, count);
> +
> +	status = decode_nl4_server(xdr, &res->cnr_src);
> +	if (unlikely(status))
> +		goto out_overflow;
> +	return 0;
> +
> +out_overflow:
> +	print_overflow_msg(__func__, xdr);
> +	return -EIO;
> +}
> +
>  static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res
> *res)
>  {
>  	return decode_op_hdr(xdr, OP_DEALLOCATE);
> @@ -585,6 +740,32 @@ static int nfs4_xdr_dec_offload_cancel(struct rpc_rqst
> *rqstp,
>  }
>  
>  /*
> + * Decode COPY_NOTIFY response
> + */
> +static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp,
> +				    struct xdr_stream *xdr,
> +				    void *data)
> +{
> +	struct nfs42_copy_notify_res *res = data;
> +	struct compound_hdr hdr;
> +	int status;
> +
> +	status = decode_compound_hdr(xdr, &hdr);
> +	if (status)
> +		goto out;
> +	status = decode_sequence(xdr, &res->cnr_seq_res, rqstp);
> +	if (status)
> +		goto out;
> +	status = decode_putfh(xdr);
> +	if (status)
> +		goto out;
> +	status = decode_copy_notify(xdr, res);
> +
> +out:
> +	return status;
> +}
> +
> +/*
>   * Decode DEALLOCATE request
>   */
>  static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
> diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
> index 8d59c96..7d17b31 100644
> --- a/fs/nfs/nfs4_fs.h
> +++ b/fs/nfs/nfs4_fs.h
> @@ -460,6 +460,8 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
>  			struct nfs_client **, struct rpc_cred *);
>  extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
>  extern void nfs41_notify_server(struct nfs_client *);
> +bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
> +			struct nfs41_server_owner *o2);
>  #else
>  static inline void nfs4_schedule_session_recovery(struct nfs4_session
> *session, int err)
>  {
> diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
> index 8f53455..ac00eb8 100644
> --- a/fs/nfs/nfs4client.c
> +++ b/fs/nfs/nfs4client.c
> @@ -625,7 +625,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
>  /*
>   * Returns true if the server major ids match
>   */
> -static bool
> +bool
>  nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
>  				struct nfs41_server_owner *o2)
>  {
> diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
> index 7838bdf..beda4b3 100644
> --- a/fs/nfs/nfs4file.c
> +++ b/fs/nfs/nfs4file.c
> @@ -133,6 +133,7 @@ static ssize_t nfs4_copy_file_range(struct file *file_in,
> loff_t pos_in,
>  				    struct file *file_out, loff_t pos_out,
>  				    size_t count, unsigned int flags)
>  {
> +	struct nfs42_copy_notify_res *cn_resp = NULL;
>  	ssize_t ret;
>  
>  	if (pos_in >= i_size_read(file_inode(file_in)))
> @@ -144,7 +145,20 @@ static ssize_t nfs4_copy_file_range(struct file *file_in,
> loff_t pos_in,
>  	if (file_inode(file_in) == file_inode(file_out))
>  		return -EINVAL;
>  retry:
> +	if (!nfs42_files_from_same_server(file_in, file_out)) {

I'm seeing this crash when I try to use vfs_copy_file_range() on NFS v4.0.  I
think it's because clients don't have a cl_serverowner defined in this case:

[  +0.051545] BUG: unable to handle kernel NULL pointer dereference at
0000000000000008
[  +0.002032] PGD 0 P4D 0 
[  +0.002021] Oops: 0000 [#4] PREEMPT SMP PTI
[  +0.001980] CPU: 1 PID: 1194 Comm: nfscopy Tainted: G      D           4.19.0-
ANNA+ #2124
[  +0.001386] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  +0.001266] RIP: 0010:nfs4_check_serverowner_major_id+0x5/0x30 [nfsv4]
[  +0.001254] Code: ff ff 48 8b 7c 24 10 eb 95 41 bf da d8 ff ff eb da e8 ef ec
eb d3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 0f 1f 44 00 00 <8b> 57 08 31
c0 3b 56 08 75 12 48 83 c6 0c 48 83 c7 0c e8 64 06 63
[  +0.002487] RSP: 0018:ffffac0b40b77e50 EFLAGS: 00010246
[  +0.001233] RAX: ffff8eb6f45a6000 RBX: ffff8eb77738e500 RCX: 0000000000000000
[  +0.001218] RDX: ffff8eb6f45a6000 RSI: 0000000000000000 RDI: 0000000000000000
[  +0.001271] RBP: ffff8eb6f533eb00 R08: 0000000080000000 R09: ffff8eb778c10800
[  +0.000956] R10: ffff8eb77aa36f98 R11: ffff8eb77ab66320 R12: 0000000000000000
[  +0.000848] R13: 0000000080000000 R14: 0000000000000000 R15: 0000000080000000
[  +0.000880] FS:  00007f7bf84d9500(0000) GS:ffff8eb77cb00000(0000)
knlGS:0000000000000000
[  +0.000876] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  +0.000815] CR2: 0000000000000008 CR3: 00000000b3e80005 CR4: 0000000000160ee0
[  +0.000809] Call Trace:
[  +0.000803]  nfs4_copy_file_range+0x8b/0x120 [nfsv4]
[  +0.000793]  vfs_copy_file_range+0x135/0x360
[  +0.000768]  __se_sys_copy_file_range+0xce/0x1f0
[  +0.000756]  do_syscall_64+0x5b/0x170
[  +0.000765]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  +0.000728] RIP: 0033:0x7f7bf840a40d
[  +0.000718] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8
48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0
ff ff 73 01 c3 48 8b 0d 23 7a 0c 00 f7 d8 64 89 01 48
[  +0.001446] RSP: 002b:00007ffd9ee8c158 EFLAGS: 00000202 ORIG_RAX:
0000000000000146
[  +0.000771] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7bf840a40d
[  +0.000727] RDX: 0000000000000004 RSI: 0000000000000000 RDI: 0000000000000003
[  +0.000709] RBP: 00007ffd9ee8c1a0 R08: 0000000080000000 R09: 0000000000000000
[  +0.000692] R10: 0000000000000000 R11: 0000000000000202 R12: 0000561b5b15e720
[  +0.000680] R13: 00007ffd9ee8c360 R14: 0000000000000000 R15: 0000000000000000
[  +0.000667] Modules linked in: rpcsec_gss_krb5 nfsv4 nfs fscache rpcrdma
ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt
target_core_mod ib_srp scsi_transport_srp ib_ipoib rdma_ucm ib_uverbs ib_umad
rdma_cm ib_cm iw_cm ib_core crct10dif_pclmul crc32_pclmul cfg80211
ghash_clmulni_intel nfsd joydev mousedev psmouse aesni_intel auth_rpcgss rfkill
aes_x86_64 8021q crypto_simd nfs_acl cryptd lockd mrp input_leds glue_helper
led_class grace evdev pcspkr intel_agp i2c_piix4 intel_gtt sunrpc mac_hid
ip_tables x_tables ata_generic pata_acpi ata_piix libata scsi_mod serio_raw
atkbd libps2 i8042 floppy serio xfs virtio_gpu drm_kms_helper syscopyarea
sysfillrect sysimgblt fb_sys_fops ttm drm libcrc32c crc32c_generic crc32c_intel
virtio_balloon virtio_net net_failover failover agpgart virtio_pci virtio_blk
virtio_ring virtio
[  +0.004802] CR2: 0000000000000008
[  +0.000742] ---[ end trace 24756b969e170fa4 ]---


Thanks,
Anna

> +		cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
> +				GFP_NOFS);
> +		if (unlikely(cn_resp == NULL))
> +			return -ENOMEM;
> +
> +		ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp);
> +		if (ret)
> +			goto out;
> +	}
> +
>  	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
> +out:
> +	kfree(cn_resp);
>  	if (ret == -EAGAIN)
>  		goto retry;
>  	return ret;
> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
> index db84b4a..fec6e6b 100644
> --- a/fs/nfs/nfs4proc.c
> +++ b/fs/nfs/nfs4proc.c
> @@ -9692,6 +9692,7 @@ static bool nfs4_match_stateid(const nfs4_stateid *s1,
>  		| NFS_CAP_ALLOCATE
>  		| NFS_CAP_COPY
>  		| NFS_CAP_OFFLOAD_CANCEL
> +		| NFS_CAP_COPY_NOTIFY
>  		| NFS_CAP_DEALLOCATE
>  		| NFS_CAP_SEEK
>  		| NFS_CAP_LAYOUTSTATS
> diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
> index b7bde12..2163900 100644
> --- a/fs/nfs/nfs4xdr.c
> +++ b/fs/nfs/nfs4xdr.c
> @@ -7790,6 +7790,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct
> nfs_entry *entry,
>  	PROC42(CLONE,		enc_clone,		dec_clone),
>  	PROC42(COPY,		enc_copy,		dec_copy),
>  	PROC42(OFFLOAD_CANCEL,	enc_offload_cancel,	dec_offload_cancel),
> +	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
>  	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
>  };
>  
> diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
> index 4803507..9e49a6c 100644
> --- a/include/linux/nfs4.h
> +++ b/include/linux/nfs4.h
> @@ -537,6 +537,7 @@ enum {
>  	NFSPROC4_CLNT_CLONE,
>  	NFSPROC4_CLNT_COPY,
>  	NFSPROC4_CLNT_OFFLOAD_CANCEL,
> +	NFSPROC4_CLNT_COPY_NOTIFY,
>  
>  	NFSPROC4_CLNT_LOOKUPP,
>  };
> diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
> index 0fc0b91..e5d89ff 100644
> --- a/include/linux/nfs_fs_sb.h
> +++ b/include/linux/nfs_fs_sb.h
> @@ -261,5 +261,6 @@ struct nfs_server {
>  #define NFS_CAP_CLONE		(1U << 23)
>  #define NFS_CAP_COPY		(1U << 24)
>  #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
> +#define NFS_CAP_COPY_NOTIFY	(1U << 26)
>  
>  #endif
> diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
> index 0e01625..dfc59bc 100644
> --- a/include/linux/nfs_xdr.h
> +++ b/include/linux/nfs_xdr.h
> @@ -1428,6 +1428,22 @@ struct nfs42_offload_status_res {
>  	int				osr_status;
>  };
>  
> +struct nfs42_copy_notify_args {
> +	struct nfs4_sequence_args	cna_seq_args;
> +
> +	struct nfs_fh		*cna_src_fh;
> +	nfs4_stateid		cna_src_stateid;
> +	struct nl4_server	cna_dst;
> +};
> +
> +struct nfs42_copy_notify_res {
> +	struct nfs4_sequence_res	cnr_seq_res;
> +
> +	struct nfstime4		cnr_lease_time;
> +	nfs4_stateid		cnr_stateid;
> +	struct nl4_server	cnr_src;
> +};
> +
>  struct nfs42_seek_args {
>  	struct nfs4_sequence_args	seq_args;
>
Olga Kornievskaia Oct. 31, 2018, 3:28 p.m. UTC | #2
On Wed, Oct 31, 2018 at 11:07 AM Schumaker, Anna
<Anna.Schumaker@netapp.com> wrote:
>
> Hi Olga,
>
> On Tue, 2018-10-30 at 16:56 -0400, Olga Kornievskaia wrote:
> > From: Olga Kornievskaia <kolga@netapp.com>
> >
> > Try using the delegation stateid, then the open stateid.
> >
> > Only NL4_NETATTR, No support for NL4_NAME and NL4_URL.
> > Allow only one source server address to be returned for now.
> >
> > To distinguish between same server copy offload ("intra") and
> > a copy between different server ("inter"), do a check of server
> > owner identity.
> >
> > Reviewed-by: Jeff Layton <jlayton@redhat.com>
> > Signed-off-by: Andy Adamson <andros@netapp.com>
> > Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
> > ---
> >  fs/nfs/nfs42.h            |  12 +++
> >  fs/nfs/nfs42proc.c        |  91 +++++++++++++++++++++++
> >  fs/nfs/nfs42xdr.c         | 181
> > ++++++++++++++++++++++++++++++++++++++++++++++
> >  fs/nfs/nfs4_fs.h          |   2 +
> >  fs/nfs/nfs4client.c       |   2 +-
> >  fs/nfs/nfs4file.c         |  14 ++++
> >  fs/nfs/nfs4proc.c         |   1 +
> >  fs/nfs/nfs4xdr.c          |   1 +
> >  include/linux/nfs4.h      |   1 +
> >  include/linux/nfs_fs_sb.h |   1 +
> >  include/linux/nfs_xdr.h   |  16 ++++
> >  11 files changed, 321 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
> > index 19ec38f8..bbe49a3 100644
> > --- a/fs/nfs/nfs42.h
> > +++ b/fs/nfs/nfs42.h
> > @@ -13,6 +13,7 @@
> >  #define PNFS_LAYOUTSTATS_MAXDEV (4)
> >
> >  /* nfs4.2proc.c */
> > +#ifdef CONFIG_NFS_V4_2
> >  int nfs42_proc_allocate(struct file *, loff_t, loff_t);
> >  ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t,
> > size_t);
> >  int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
> > @@ -20,5 +21,16 @@
> >  int nfs42_proc_layoutstats_generic(struct nfs_server *,
> >                                  struct nfs42_layoutstat_data *);
> >  int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
> > +int nfs42_proc_copy_notify(struct file *, struct file *,
> > +                        struct nfs42_copy_notify_res *);
> > +static inline bool nfs42_files_from_same_server(struct file *in,
> > +                                             struct file *out)
> > +{
> > +     struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client;
> > +     struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client;
> >
> > +     return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
> > +                             c_out->cl_serverowner);
> > +}
> > +#endif /* CONFIG_NFS_V4_2 */
> >  #endif /* __LINUX_FS_NFS_NFS4_2_H */
> > diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
> > index ac5b784..b1c57a4 100644
> > --- a/fs/nfs/nfs42proc.c
> > +++ b/fs/nfs/nfs42proc.c
> > @@ -3,6 +3,7 @@
> >   * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
> >   */
> >  #include <linux/fs.h>
> > +#include <linux/sunrpc/addr.h>
> >  #include <linux/sunrpc/sched.h>
> >  #include <linux/nfs.h>
> >  #include <linux/nfs3.h>
> > @@ -15,10 +16,30 @@
> >  #include "pnfs.h"
> >  #include "nfs4session.h"
> >  #include "internal.h"
> > +#include "delegation.h"
> >
> >  #define NFSDBG_FACILITY NFSDBG_PROC
> >  static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid
> > *std);
> >
> > +static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr
> > *naddr)
> > +{
> > +     struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client;
> > +     unsigned short port = 2049;
> > +
> > +     rcu_read_lock();
> > +     naddr->netid_len = scnprintf(naddr->netid,
> > +                                     sizeof(naddr->netid), "%s",
> > +                                     rpc_peeraddr2str(clp->cl_rpcclient,
> > +                                     RPC_DISPLAY_NETID));
> > +     naddr->addr_len = scnprintf(naddr->addr,
> > +                                     sizeof(naddr->addr),
> > +                                     "%s.%u.%u",
> > +                                     rpc_peeraddr2str(clp->cl_rpcclient,
> > +                                     RPC_DISPLAY_ADDR),
> > +                                     port >> 8, port & 255);
> > +     rcu_read_unlock();
> > +}
> > +
> >  static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
> >               struct nfs_lock_context *lock, loff_t offset, loff_t len)
> >  {
> > @@ -461,6 +482,76 @@ static int nfs42_do_offload_cancel_async(struct file
> > *dst,
> >       return status;
> >  }
> >
> > +int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
> > +                         struct nfs42_copy_notify_args *args,
> > +                         struct nfs42_copy_notify_res *res)
> > +{
> > +     struct nfs_server *src_server = NFS_SERVER(file_inode(src));
> > +     struct rpc_message msg = {
> > +             .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY],
> > +             .rpc_argp = args,
> > +             .rpc_resp = res,
> > +     };
> > +     int status;
> > +     struct nfs_open_context *ctx;
> > +     struct nfs_lock_context *l_ctx;
> > +
> > +     ctx = get_nfs_open_context(nfs_file_open_context(src));
> > +     l_ctx = nfs_get_lock_context(ctx);
> > +     if (IS_ERR(l_ctx))
> > +             return PTR_ERR(l_ctx);
> > +
> > +     status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
> > +                                  FMODE_READ);
> > +     nfs_put_lock_context(l_ctx);
> > +     if (status)
> > +             return status;
> > +
> > +     status = nfs4_call_sync(src_server->client, src_server, &msg,
> > +                             &args->cna_seq_args, &res->cnr_seq_res, 0);
> > +     if (status == -ENOTSUPP)
> > +             src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
> > +
> > +     put_nfs_open_context(nfs_file_open_context(src));
> > +     return status;
> > +}
> > +
> > +int nfs42_proc_copy_notify(struct file *src, struct file *dst,
> > +                             struct nfs42_copy_notify_res *res)
> > +{
> > +     struct nfs_server *src_server = NFS_SERVER(file_inode(src));
> > +     struct nfs42_copy_notify_args *args;
> > +     struct nfs4_exception exception = {
> > +             .inode = file_inode(src),
> > +     };
> > +     int status;
> > +
> > +     if (!(src_server->caps & NFS_CAP_COPY_NOTIFY))
> > +             return -EOPNOTSUPP;
> > +
> > +     args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS);
> > +     if (args == NULL)
> > +             return -ENOMEM;
> > +
> > +     args->cna_src_fh  = NFS_FH(file_inode(src)),
> > +     args->cna_dst.nl4_type = NL4_NETADDR;
> > +     nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr);
> > +     exception.stateid = &args->cna_src_stateid;
> > +
> > +     do {
> > +             status = _nfs42_proc_copy_notify(src, dst, args, res);
> > +             if (status == -ENOTSUPP) {
> > +                     status = -EOPNOTSUPP;
> > +                     goto out;
> > +             }
> > +             status = nfs4_handle_exception(src_server, status, &exception);
> > +     } while (exception.retry);
> > +
> > +out:
> > +     kfree(args);
> > +     return status;
> > +}
> > +
> >  static loff_t _nfs42_proc_llseek(struct file *filep,
> >               struct nfs_lock_context *lock, loff_t offset, int whence)
> >  {
> > diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
> > index 69f72ed..e6e7cbf 100644
> > --- a/fs/nfs/nfs42xdr.c
> > +++ b/fs/nfs/nfs42xdr.c
> > @@ -29,6 +29,16 @@
> >  #define encode_offload_cancel_maxsz  (op_encode_hdr_maxsz + \
> >                                        XDR_QUADLEN(NFS4_STATEID_SIZE))
> >  #define decode_offload_cancel_maxsz  (op_decode_hdr_maxsz)
> > +#define encode_copy_notify_maxsz     (op_encode_hdr_maxsz + \
> > +                                      XDR_QUADLEN(NFS4_STATEID_SIZE) + \
> > +                                      1 + /* nl4_type */ \
> > +                                      1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
> > +#define decode_copy_notify_maxsz     (op_decode_hdr_maxsz + \
> > +                                      3 + /* cnr_lease_time */\
> > +                                      XDR_QUADLEN(NFS4_STATEID_SIZE) + \
> > +                                      1 + /* Support 1 cnr_source_server */\
> > +                                      1 + /* nl4_type */ \
> > +                                      1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
> >  #define encode_deallocate_maxsz              (op_encode_hdr_maxsz + \
> >                                        encode_fallocate_maxsz)
> >  #define decode_deallocate_maxsz              (op_decode_hdr_maxsz)
> > @@ -84,6 +94,12 @@
> >  #define NFS4_dec_offload_cancel_sz   (compound_decode_hdr_maxsz + \
> >                                        decode_putfh_maxsz + \
> >                                        decode_offload_cancel_maxsz)
> > +#define NFS4_enc_copy_notify_sz              (compound_encode_hdr_maxsz + \
> > +                                      encode_putfh_maxsz + \
> > +                                      encode_copy_notify_maxsz)
> > +#define NFS4_dec_copy_notify_sz              (compound_decode_hdr_maxsz + \
> > +                                      decode_putfh_maxsz + \
> > +                                      decode_copy_notify_maxsz)
> >  #define NFS4_enc_deallocate_sz               (compound_encode_hdr_maxsz + \
> >                                        encode_putfh_maxsz + \
> >                                        encode_deallocate_maxsz + \
> > @@ -137,6 +153,25 @@ static void encode_allocate(struct xdr_stream *xdr,
> >       encode_fallocate(xdr, args);
> >  }
> >
> > +static void encode_nl4_server(struct xdr_stream *xdr, const struct nl4_server
> > *ns)
> > +{
> > +     encode_uint32(xdr, ns->nl4_type);
> > +     switch (ns->nl4_type) {
> > +     case NL4_NAME:
> > +     case NL4_URL:
> > +             encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str);
> > +             break;
> > +     case NL4_NETADDR:
> > +             encode_string(xdr, ns->u.nl4_addr.netid_len,
> > +                           ns->u.nl4_addr.netid);
> > +             encode_string(xdr, ns->u.nl4_addr.addr_len,
> > +                           ns->u.nl4_addr.addr);
> > +             break;
> > +     default:
> > +             WARN_ON_ONCE(1);
> > +     }
> > +}
> > +
> >  static void encode_copy(struct xdr_stream *xdr,
> >                       const struct nfs42_copy_args *args,
> >                       struct compound_hdr *hdr)
> > @@ -162,6 +197,15 @@ static void encode_offload_cancel(struct xdr_stream *xdr,
> >       encode_nfs4_stateid(xdr, &args->osa_stateid);
> >  }
> >
> > +static void encode_copy_notify(struct xdr_stream *xdr,
> > +                            const struct nfs42_copy_notify_args *args,
> > +                            struct compound_hdr *hdr)
> > +{
> > +     encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr);
> > +     encode_nfs4_stateid(xdr, &args->cna_src_stateid);
> > +     encode_nl4_server(xdr, &args->cna_dst);
> > +}
> > +
> >  static void encode_deallocate(struct xdr_stream *xdr,
> >                             const struct nfs42_falloc_args *args,
> >                             struct compound_hdr *hdr)
> > @@ -298,6 +342,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst
> > *req,
> >  }
> >
> >  /*
> > + * Encode COPY_NOTIFY request
> > + */
> > +static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req,
> > +                                  struct xdr_stream *xdr,
> > +                                  const void *data)
> > +{
> > +     const struct nfs42_copy_notify_args *args = data;
> > +     struct compound_hdr hdr = {
> > +             .minorversion = nfs4_xdr_minorversion(&args->cna_seq_args),
> > +     };
> > +
> > +     encode_compound_hdr(xdr, req, &hdr);
> > +     encode_sequence(xdr, &args->cna_seq_args, &hdr);
> > +     encode_putfh(xdr, args->cna_src_fh, &hdr);
> > +     encode_copy_notify(xdr, args, &hdr);
> > +     encode_nops(&hdr);
> > +}
> > +
> > +/*
> >   * Encode DEALLOCATE request
> >   */
> >  static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
> > @@ -416,6 +479,58 @@ static int decode_write_response(struct xdr_stream *xdr,
> >       return -EIO;
> >  }
> >
> > +static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns)
> > +{
> > +     struct nfs42_netaddr *naddr;
> > +     uint32_t dummy;
> > +     char *dummy_str;
> > +     __be32 *p;
> > +     int status;
> > +
> > +     /* nl_type */
> > +     p = xdr_inline_decode(xdr, 4);
> > +     if (unlikely(!p))
> > +             return -EIO;
> > +     ns->nl4_type = be32_to_cpup(p);
> > +     switch (ns->nl4_type) {
> > +     case NL4_NAME:
> > +     case NL4_URL:
> > +             status = decode_opaque_inline(xdr, &dummy, &dummy_str);
> > +             if (unlikely(status))
> > +                     return status;
> > +             if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
> > +                     return -EIO;
> > +             memcpy(&ns->u.nl4_str, dummy_str, dummy);
> > +             ns->u.nl4_str_sz = dummy;
> > +             break;
> > +     case NL4_NETADDR:
> > +             naddr = &ns->u.nl4_addr;
> > +
> > +             /* netid string */
> > +             status = decode_opaque_inline(xdr, &dummy, &dummy_str);
> > +             if (unlikely(status))
> > +                     return status;
> > +             if (unlikely(dummy > RPCBIND_MAXNETIDLEN))
> > +                     return -EIO;
> > +             naddr->netid_len = dummy;
> > +             memcpy(naddr->netid, dummy_str, naddr->netid_len);
> > +
> > +             /* uaddr string */
> > +             status = decode_opaque_inline(xdr, &dummy, &dummy_str);
> > +             if (unlikely(status))
> > +                     return status;
> > +             if (unlikely(dummy > RPCBIND_MAXUADDRLEN))
> > +                     return -EIO;
> > +             naddr->addr_len = dummy;
> > +             memcpy(naddr->addr, dummy_str, naddr->addr_len);
> > +             break;
> > +     default:
> > +             WARN_ON_ONCE(1);
> > +             return -EIO;
> > +     }
> > +     return 0;
> > +}
> > +
> >  static int decode_copy_requirements(struct xdr_stream *xdr,
> >                                   struct nfs42_copy_res *res) {
> >       __be32 *p;
> > @@ -458,6 +573,46 @@ static int decode_offload_cancel(struct xdr_stream *xdr,
> >       return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
> >  }
> >
> > +static int decode_copy_notify(struct xdr_stream *xdr,
> > +                           struct nfs42_copy_notify_res *res)
> > +{
> > +     __be32 *p;
> > +     int status, count;
> > +
> > +     status = decode_op_hdr(xdr, OP_COPY_NOTIFY);
> > +     if (status)
> > +             return status;
> > +     /* cnr_lease_time */
> > +     p = xdr_inline_decode(xdr, 12);
> > +     if (unlikely(!p))
> > +             goto out_overflow;
> > +     p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds);
> > +     res->cnr_lease_time.nseconds = be32_to_cpup(p);
> > +
> > +     status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE);
> > +     if (unlikely(status))
> > +             goto out_overflow;
> > +
> > +     /* number of source addresses */
> > +     p = xdr_inline_decode(xdr, 4);
> > +     if (unlikely(!p))
> > +             goto out_overflow;
> > +
> > +     count = be32_to_cpup(p);
> > +     if (count > 1)
> > +             pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n",
> > +                      __func__, count);
> > +
> > +     status = decode_nl4_server(xdr, &res->cnr_src);
> > +     if (unlikely(status))
> > +             goto out_overflow;
> > +     return 0;
> > +
> > +out_overflow:
> > +     print_overflow_msg(__func__, xdr);
> > +     return -EIO;
> > +}
> > +
> >  static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res
> > *res)
> >  {
> >       return decode_op_hdr(xdr, OP_DEALLOCATE);
> > @@ -585,6 +740,32 @@ static int nfs4_xdr_dec_offload_cancel(struct rpc_rqst
> > *rqstp,
> >  }
> >
> >  /*
> > + * Decode COPY_NOTIFY response
> > + */
> > +static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp,
> > +                                 struct xdr_stream *xdr,
> > +                                 void *data)
> > +{
> > +     struct nfs42_copy_notify_res *res = data;
> > +     struct compound_hdr hdr;
> > +     int status;
> > +
> > +     status = decode_compound_hdr(xdr, &hdr);
> > +     if (status)
> > +             goto out;
> > +     status = decode_sequence(xdr, &res->cnr_seq_res, rqstp);
> > +     if (status)
> > +             goto out;
> > +     status = decode_putfh(xdr);
> > +     if (status)
> > +             goto out;
> > +     status = decode_copy_notify(xdr, res);
> > +
> > +out:
> > +     return status;
> > +}
> > +
> > +/*
> >   * Decode DEALLOCATE request
> >   */
> >  static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
> > diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
> > index 8d59c96..7d17b31 100644
> > --- a/fs/nfs/nfs4_fs.h
> > +++ b/fs/nfs/nfs4_fs.h
> > @@ -460,6 +460,8 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
> >                       struct nfs_client **, struct rpc_cred *);
> >  extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
> >  extern void nfs41_notify_server(struct nfs_client *);
> > +bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
> > +                     struct nfs41_server_owner *o2);
> >  #else
> >  static inline void nfs4_schedule_session_recovery(struct nfs4_session
> > *session, int err)
> >  {
> > diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
> > index 8f53455..ac00eb8 100644
> > --- a/fs/nfs/nfs4client.c
> > +++ b/fs/nfs/nfs4client.c
> > @@ -625,7 +625,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
> >  /*
> >   * Returns true if the server major ids match
> >   */
> > -static bool
> > +bool
> >  nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
> >                               struct nfs41_server_owner *o2)
> >  {
> > diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
> > index 7838bdf..beda4b3 100644
> > --- a/fs/nfs/nfs4file.c
> > +++ b/fs/nfs/nfs4file.c
> > @@ -133,6 +133,7 @@ static ssize_t nfs4_copy_file_range(struct file *file_in,
> > loff_t pos_in,
> >                                   struct file *file_out, loff_t pos_out,
> >                                   size_t count, unsigned int flags)
> >  {
> > +     struct nfs42_copy_notify_res *cn_resp = NULL;
> >       ssize_t ret;
> >
> >       if (pos_in >= i_size_read(file_inode(file_in)))
> > @@ -144,7 +145,20 @@ static ssize_t nfs4_copy_file_range(struct file *file_in,
> > loff_t pos_in,
> >       if (file_inode(file_in) == file_inode(file_out))
> >               return -EINVAL;
> >  retry:
> > +     if (!nfs42_files_from_same_server(file_in, file_out)) {
>
> I'm seeing this crash when I try to use vfs_copy_file_range() on NFS v4.0.  I
> think it's because clients don't have a cl_serverowner defined in this case:

Thanks for the catch. Will fix it.

> [  +0.051545] BUG: unable to handle kernel NULL pointer dereference at
> 0000000000000008
> [  +0.002032] PGD 0 P4D 0
> [  +0.002021] Oops: 0000 [#4] PREEMPT SMP PTI
> [  +0.001980] CPU: 1 PID: 1194 Comm: nfscopy Tainted: G      D           4.19.0-
> ANNA+ #2124
> [  +0.001386] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> [  +0.001266] RIP: 0010:nfs4_check_serverowner_major_id+0x5/0x30 [nfsv4]
> [  +0.001254] Code: ff ff 48 8b 7c 24 10 eb 95 41 bf da d8 ff ff eb da e8 ef ec
> eb d3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 0f 1f 44 00 00 <8b> 57 08 31
> c0 3b 56 08 75 12 48 83 c6 0c 48 83 c7 0c e8 64 06 63
> [  +0.002487] RSP: 0018:ffffac0b40b77e50 EFLAGS: 00010246
> [  +0.001233] RAX: ffff8eb6f45a6000 RBX: ffff8eb77738e500 RCX: 0000000000000000
> [  +0.001218] RDX: ffff8eb6f45a6000 RSI: 0000000000000000 RDI: 0000000000000000
> [  +0.001271] RBP: ffff8eb6f533eb00 R08: 0000000080000000 R09: ffff8eb778c10800
> [  +0.000956] R10: ffff8eb77aa36f98 R11: ffff8eb77ab66320 R12: 0000000000000000
> [  +0.000848] R13: 0000000080000000 R14: 0000000000000000 R15: 0000000080000000
> [  +0.000880] FS:  00007f7bf84d9500(0000) GS:ffff8eb77cb00000(0000)
> knlGS:0000000000000000
> [  +0.000876] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [  +0.000815] CR2: 0000000000000008 CR3: 00000000b3e80005 CR4: 0000000000160ee0
> [  +0.000809] Call Trace:
> [  +0.000803]  nfs4_copy_file_range+0x8b/0x120 [nfsv4]
> [  +0.000793]  vfs_copy_file_range+0x135/0x360
> [  +0.000768]  __se_sys_copy_file_range+0xce/0x1f0
> [  +0.000756]  do_syscall_64+0x5b/0x170
> [  +0.000765]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
> [  +0.000728] RIP: 0033:0x7f7bf840a40d
> [  +0.000718] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8
> 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0
> ff ff 73 01 c3 48 8b 0d 23 7a 0c 00 f7 d8 64 89 01 48
> [  +0.001446] RSP: 002b:00007ffd9ee8c158 EFLAGS: 00000202 ORIG_RAX:
> 0000000000000146
> [  +0.000771] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7bf840a40d
> [  +0.000727] RDX: 0000000000000004 RSI: 0000000000000000 RDI: 0000000000000003
> [  +0.000709] RBP: 00007ffd9ee8c1a0 R08: 0000000080000000 R09: 0000000000000000
> [  +0.000692] R10: 0000000000000000 R11: 0000000000000202 R12: 0000561b5b15e720
> [  +0.000680] R13: 00007ffd9ee8c360 R14: 0000000000000000 R15: 0000000000000000
> [  +0.000667] Modules linked in: rpcsec_gss_krb5 nfsv4 nfs fscache rpcrdma
> ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt
> target_core_mod ib_srp scsi_transport_srp ib_ipoib rdma_ucm ib_uverbs ib_umad
> rdma_cm ib_cm iw_cm ib_core crct10dif_pclmul crc32_pclmul cfg80211
> ghash_clmulni_intel nfsd joydev mousedev psmouse aesni_intel auth_rpcgss rfkill
> aes_x86_64 8021q crypto_simd nfs_acl cryptd lockd mrp input_leds glue_helper
> led_class grace evdev pcspkr intel_agp i2c_piix4 intel_gtt sunrpc mac_hid
> ip_tables x_tables ata_generic pata_acpi ata_piix libata scsi_mod serio_raw
> atkbd libps2 i8042 floppy serio xfs virtio_gpu drm_kms_helper syscopyarea
> sysfillrect sysimgblt fb_sys_fops ttm drm libcrc32c crc32c_generic crc32c_intel
> virtio_balloon virtio_net net_failover failover agpgart virtio_pci virtio_blk
> virtio_ring virtio
> [  +0.004802] CR2: 0000000000000008
> [  +0.000742] ---[ end trace 24756b969e170fa4 ]---
>
>
> Thanks,
> Anna
>
> > +             cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
> > +                             GFP_NOFS);
> > +             if (unlikely(cn_resp == NULL))
> > +                     return -ENOMEM;
> > +
> > +             ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp);
> > +             if (ret)
> > +                     goto out;
> > +     }
> > +
> >       ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
> > +out:
> > +     kfree(cn_resp);
> >       if (ret == -EAGAIN)
> >               goto retry;
> >       return ret;
> > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
> > index db84b4a..fec6e6b 100644
> > --- a/fs/nfs/nfs4proc.c
> > +++ b/fs/nfs/nfs4proc.c
> > @@ -9692,6 +9692,7 @@ static bool nfs4_match_stateid(const nfs4_stateid *s1,
> >               | NFS_CAP_ALLOCATE
> >               | NFS_CAP_COPY
> >               | NFS_CAP_OFFLOAD_CANCEL
> > +             | NFS_CAP_COPY_NOTIFY
> >               | NFS_CAP_DEALLOCATE
> >               | NFS_CAP_SEEK
> >               | NFS_CAP_LAYOUTSTATS
> > diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
> > index b7bde12..2163900 100644
> > --- a/fs/nfs/nfs4xdr.c
> > +++ b/fs/nfs/nfs4xdr.c
> > @@ -7790,6 +7790,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct
> > nfs_entry *entry,
> >       PROC42(CLONE,           enc_clone,              dec_clone),
> >       PROC42(COPY,            enc_copy,               dec_copy),
> >       PROC42(OFFLOAD_CANCEL,  enc_offload_cancel,     dec_offload_cancel),
> > +     PROC42(COPY_NOTIFY,     enc_copy_notify,        dec_copy_notify),
> >       PROC(LOOKUPP,           enc_lookupp,            dec_lookupp),
> >  };
> >
> > diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
> > index 4803507..9e49a6c 100644
> > --- a/include/linux/nfs4.h
> > +++ b/include/linux/nfs4.h
> > @@ -537,6 +537,7 @@ enum {
> >       NFSPROC4_CLNT_CLONE,
> >       NFSPROC4_CLNT_COPY,
> >       NFSPROC4_CLNT_OFFLOAD_CANCEL,
> > +     NFSPROC4_CLNT_COPY_NOTIFY,
> >
> >       NFSPROC4_CLNT_LOOKUPP,
> >  };
> > diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
> > index 0fc0b91..e5d89ff 100644
> > --- a/include/linux/nfs_fs_sb.h
> > +++ b/include/linux/nfs_fs_sb.h
> > @@ -261,5 +261,6 @@ struct nfs_server {
> >  #define NFS_CAP_CLONE                (1U << 23)
> >  #define NFS_CAP_COPY         (1U << 24)
> >  #define NFS_CAP_OFFLOAD_CANCEL       (1U << 25)
> > +#define NFS_CAP_COPY_NOTIFY  (1U << 26)
> >
> >  #endif
> > diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
> > index 0e01625..dfc59bc 100644
> > --- a/include/linux/nfs_xdr.h
> > +++ b/include/linux/nfs_xdr.h
> > @@ -1428,6 +1428,22 @@ struct nfs42_offload_status_res {
> >       int                             osr_status;
> >  };
> >
> > +struct nfs42_copy_notify_args {
> > +     struct nfs4_sequence_args       cna_seq_args;
> > +
> > +     struct nfs_fh           *cna_src_fh;
> > +     nfs4_stateid            cna_src_stateid;
> > +     struct nl4_server       cna_dst;
> > +};
> > +
> > +struct nfs42_copy_notify_res {
> > +     struct nfs4_sequence_res        cnr_seq_res;
> > +
> > +     struct nfstime4         cnr_lease_time;
> > +     nfs4_stateid            cnr_stateid;
> > +     struct nl4_server       cnr_src;
> > +};
> > +
> >  struct nfs42_seek_args {
> >       struct nfs4_sequence_args       seq_args;
> >
diff mbox series

Patch

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 19ec38f8..bbe49a3 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -13,6 +13,7 @@ 
 #define PNFS_LAYOUTSTATS_MAXDEV (4)
 
 /* nfs4.2proc.c */
+#ifdef CONFIG_NFS_V4_2
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
 ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
@@ -20,5 +21,16 @@ 
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
 				   struct nfs42_layoutstat_data *);
 int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
+int nfs42_proc_copy_notify(struct file *, struct file *,
+			   struct nfs42_copy_notify_res *);
+static inline bool nfs42_files_from_same_server(struct file *in,
+						struct file *out)
+{
+	struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client;
+	struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client;
 
+	return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
+				c_out->cl_serverowner);
+}
+#endif /* CONFIG_NFS_V4_2 */
 #endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index ac5b784..b1c57a4 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -3,6 +3,7 @@ 
  * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
  */
 #include <linux/fs.h>
+#include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
@@ -15,10 +16,30 @@ 
 #include "pnfs.h"
 #include "nfs4session.h"
 #include "internal.h"
+#include "delegation.h"
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
 
+static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr)
+{
+	struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client;
+	unsigned short port = 2049;
+
+	rcu_read_lock();
+	naddr->netid_len = scnprintf(naddr->netid,
+					sizeof(naddr->netid), "%s",
+					rpc_peeraddr2str(clp->cl_rpcclient,
+					RPC_DISPLAY_NETID));
+	naddr->addr_len = scnprintf(naddr->addr,
+					sizeof(naddr->addr),
+					"%s.%u.%u",
+					rpc_peeraddr2str(clp->cl_rpcclient,
+					RPC_DISPLAY_ADDR),
+					port >> 8, port & 255);
+	rcu_read_unlock();
+}
+
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, loff_t len)
 {
@@ -461,6 +482,76 @@  static int nfs42_do_offload_cancel_async(struct file *dst,
 	return status;
 }
 
+int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
+			    struct nfs42_copy_notify_args *args,
+			    struct nfs42_copy_notify_res *res)
+{
+	struct nfs_server *src_server = NFS_SERVER(file_inode(src));
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY],
+		.rpc_argp = args,
+		.rpc_resp = res,
+	};
+	int status;
+	struct nfs_open_context *ctx;
+	struct nfs_lock_context *l_ctx;
+
+	ctx = get_nfs_open_context(nfs_file_open_context(src));
+	l_ctx = nfs_get_lock_context(ctx);
+	if (IS_ERR(l_ctx))
+		return PTR_ERR(l_ctx);
+
+	status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
+				     FMODE_READ);
+	nfs_put_lock_context(l_ctx);
+	if (status)
+		return status;
+
+	status = nfs4_call_sync(src_server->client, src_server, &msg,
+				&args->cna_seq_args, &res->cnr_seq_res, 0);
+	if (status == -ENOTSUPP)
+		src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
+
+	put_nfs_open_context(nfs_file_open_context(src));
+	return status;
+}
+
+int nfs42_proc_copy_notify(struct file *src, struct file *dst,
+				struct nfs42_copy_notify_res *res)
+{
+	struct nfs_server *src_server = NFS_SERVER(file_inode(src));
+	struct nfs42_copy_notify_args *args;
+	struct nfs4_exception exception = {
+		.inode = file_inode(src),
+	};
+	int status;
+
+	if (!(src_server->caps & NFS_CAP_COPY_NOTIFY))
+		return -EOPNOTSUPP;
+
+	args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS);
+	if (args == NULL)
+		return -ENOMEM;
+
+	args->cna_src_fh  = NFS_FH(file_inode(src)),
+	args->cna_dst.nl4_type = NL4_NETADDR;
+	nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr);
+	exception.stateid = &args->cna_src_stateid;
+
+	do {
+		status = _nfs42_proc_copy_notify(src, dst, args, res);
+		if (status == -ENOTSUPP) {
+			status = -EOPNOTSUPP;
+			goto out;
+		}
+		status = nfs4_handle_exception(src_server, status, &exception);
+	} while (exception.retry);
+
+out:
+	kfree(args);
+	return status;
+}
+
 static loff_t _nfs42_proc_llseek(struct file *filep,
 		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 69f72ed..e6e7cbf 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -29,6 +29,16 @@ 
 #define encode_offload_cancel_maxsz	(op_encode_hdr_maxsz + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE))
 #define decode_offload_cancel_maxsz	(op_decode_hdr_maxsz)
+#define encode_copy_notify_maxsz	(op_encode_hdr_maxsz + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 1 + /* nl4_type */ \
+					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
+#define decode_copy_notify_maxsz	(op_decode_hdr_maxsz + \
+					 3 + /* cnr_lease_time */\
+					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+					 1 + /* Support 1 cnr_source_server */\
+					 1 + /* nl4_type */ \
+					 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
@@ -84,6 +94,12 @@ 
 #define NFS4_dec_offload_cancel_sz	(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_offload_cancel_maxsz)
+#define NFS4_enc_copy_notify_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_copy_notify_maxsz)
+#define NFS4_dec_copy_notify_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_copy_notify_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_deallocate_maxsz + \
@@ -137,6 +153,25 @@  static void encode_allocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_nl4_server(struct xdr_stream *xdr, const struct nl4_server *ns)
+{
+	encode_uint32(xdr, ns->nl4_type);
+	switch (ns->nl4_type) {
+	case NL4_NAME:
+	case NL4_URL:
+		encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str);
+		break;
+	case NL4_NETADDR:
+		encode_string(xdr, ns->u.nl4_addr.netid_len,
+			      ns->u.nl4_addr.netid);
+		encode_string(xdr, ns->u.nl4_addr.addr_len,
+			      ns->u.nl4_addr.addr);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
 static void encode_copy(struct xdr_stream *xdr,
 			const struct nfs42_copy_args *args,
 			struct compound_hdr *hdr)
@@ -162,6 +197,15 @@  static void encode_offload_cancel(struct xdr_stream *xdr,
 	encode_nfs4_stateid(xdr, &args->osa_stateid);
 }
 
+static void encode_copy_notify(struct xdr_stream *xdr,
+			       const struct nfs42_copy_notify_args *args,
+			       struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->cna_src_stateid);
+	encode_nl4_server(xdr, &args->cna_dst);
+}
+
 static void encode_deallocate(struct xdr_stream *xdr,
 			      const struct nfs42_falloc_args *args,
 			      struct compound_hdr *hdr)
@@ -298,6 +342,25 @@  static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
 }
 
 /*
+ * Encode COPY_NOTIFY request
+ */
+static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req,
+				     struct xdr_stream *xdr,
+				     const void *data)
+{
+	const struct nfs42_copy_notify_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->cna_seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->cna_seq_args, &hdr);
+	encode_putfh(xdr, args->cna_src_fh, &hdr);
+	encode_copy_notify(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode DEALLOCATE request
  */
 static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -416,6 +479,58 @@  static int decode_write_response(struct xdr_stream *xdr,
 	return -EIO;
 }
 
+static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns)
+{
+	struct nfs42_netaddr *naddr;
+	uint32_t dummy;
+	char *dummy_str;
+	__be32 *p;
+	int status;
+
+	/* nl_type */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+	ns->nl4_type = be32_to_cpup(p);
+	switch (ns->nl4_type) {
+	case NL4_NAME:
+	case NL4_URL:
+		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+		if (unlikely(status))
+			return status;
+		if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+			return -EIO;
+		memcpy(&ns->u.nl4_str, dummy_str, dummy);
+		ns->u.nl4_str_sz = dummy;
+		break;
+	case NL4_NETADDR:
+		naddr = &ns->u.nl4_addr;
+
+		/* netid string */
+		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+		if (unlikely(status))
+			return status;
+		if (unlikely(dummy > RPCBIND_MAXNETIDLEN))
+			return -EIO;
+		naddr->netid_len = dummy;
+		memcpy(naddr->netid, dummy_str, naddr->netid_len);
+
+		/* uaddr string */
+		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+		if (unlikely(status))
+			return status;
+		if (unlikely(dummy > RPCBIND_MAXUADDRLEN))
+			return -EIO;
+		naddr->addr_len = dummy;
+		memcpy(naddr->addr, dummy_str, naddr->addr_len);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+	return 0;
+}
+
 static int decode_copy_requirements(struct xdr_stream *xdr,
 				    struct nfs42_copy_res *res) {
 	__be32 *p;
@@ -458,6 +573,46 @@  static int decode_offload_cancel(struct xdr_stream *xdr,
 	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
 }
 
+static int decode_copy_notify(struct xdr_stream *xdr,
+			      struct nfs42_copy_notify_res *res)
+{
+	__be32 *p;
+	int status, count;
+
+	status = decode_op_hdr(xdr, OP_COPY_NOTIFY);
+	if (status)
+		return status;
+	/* cnr_lease_time */
+	p = xdr_inline_decode(xdr, 12);
+	if (unlikely(!p))
+		goto out_overflow;
+	p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds);
+	res->cnr_lease_time.nseconds = be32_to_cpup(p);
+
+	status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE);
+	if (unlikely(status))
+		goto out_overflow;
+
+	/* number of source addresses */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	count = be32_to_cpup(p);
+	if (count > 1)
+		pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n",
+			 __func__, count);
+
+	status = decode_nl4_server(xdr, &res->cnr_src);
+	if (unlikely(status))
+		goto out_overflow;
+	return 0;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -585,6 +740,32 @@  static int nfs4_xdr_dec_offload_cancel(struct rpc_rqst *rqstp,
 }
 
 /*
+ * Decode COPY_NOTIFY response
+ */
+static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp,
+				    struct xdr_stream *xdr,
+				    void *data)
+{
+	struct nfs42_copy_notify_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->cnr_seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_copy_notify(xdr, res);
+
+out:
+	return status;
+}
+
+/*
  * Decode DEALLOCATE request
  */
 static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 8d59c96..7d17b31 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -460,6 +460,8 @@  int nfs41_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **, struct rpc_cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 extern void nfs41_notify_server(struct nfs_client *);
+bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
+			struct nfs41_server_owner *o2);
 #else
 static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8f53455..ac00eb8 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -625,7 +625,7 @@  int nfs40_walk_client_list(struct nfs_client *new,
 /*
  * Returns true if the server major ids match
  */
-static bool
+bool
 nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
 				struct nfs41_server_owner *o2)
 {
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 7838bdf..beda4b3 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,6 +133,7 @@  static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    size_t count, unsigned int flags)
 {
+	struct nfs42_copy_notify_res *cn_resp = NULL;
 	ssize_t ret;
 
 	if (pos_in >= i_size_read(file_inode(file_in)))
@@ -144,7 +145,20 @@  static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EINVAL;
 retry:
+	if (!nfs42_files_from_same_server(file_in, file_out)) {
+		cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
+				GFP_NOFS);
+		if (unlikely(cn_resp == NULL))
+			return -ENOMEM;
+
+		ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp);
+		if (ret)
+			goto out;
+	}
+
 	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+out:
+	kfree(cn_resp);
 	if (ret == -EAGAIN)
 		goto retry;
 	return ret;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index db84b4a..fec6e6b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9692,6 +9692,7 @@  static bool nfs4_match_stateid(const nfs4_stateid *s1,
 		| NFS_CAP_ALLOCATE
 		| NFS_CAP_COPY
 		| NFS_CAP_OFFLOAD_CANCEL
+		| NFS_CAP_COPY_NOTIFY
 		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b7bde12..2163900 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7790,6 +7790,7 @@  int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	PROC42(CLONE,		enc_clone,		dec_clone),
 	PROC42(COPY,		enc_copy,		dec_copy),
 	PROC42(OFFLOAD_CANCEL,	enc_offload_cancel,	dec_offload_cancel),
+	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 4803507..9e49a6c 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -537,6 +537,7 @@  enum {
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
 	NFSPROC4_CLNT_OFFLOAD_CANCEL,
+	NFSPROC4_CLNT_COPY_NOTIFY,
 
 	NFSPROC4_CLNT_LOOKUPP,
 };
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 0fc0b91..e5d89ff 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -261,5 +261,6 @@  struct nfs_server {
 #define NFS_CAP_CLONE		(1U << 23)
 #define NFS_CAP_COPY		(1U << 24)
 #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
+#define NFS_CAP_COPY_NOTIFY	(1U << 26)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0e01625..dfc59bc 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1428,6 +1428,22 @@  struct nfs42_offload_status_res {
 	int				osr_status;
 };
 
+struct nfs42_copy_notify_args {
+	struct nfs4_sequence_args	cna_seq_args;
+
+	struct nfs_fh		*cna_src_fh;
+	nfs4_stateid		cna_src_stateid;
+	struct nl4_server	cna_dst;
+};
+
+struct nfs42_copy_notify_res {
+	struct nfs4_sequence_res	cnr_seq_res;
+
+	struct nfstime4		cnr_lease_time;
+	nfs4_stateid		cnr_stateid;
+	struct nl4_server	cnr_src;
+};
+
 struct nfs42_seek_args {
 	struct nfs4_sequence_args	seq_args;