Merge tag 'nfsd-5.6' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - Server-to-server copy code from Olga.

     To use it, client and both servers must have support, the target
     server must be able to access the source server over NFSv4.2, and
     the target server must have the inter_copy_offload_enable module
     parameter set.

   - Improvements and bugfixes for the new filehandle cache, especially
     in the container case, from Trond

   - Also from Trond, better reporting of write errors.

   - Y2038 work from Arnd"

* tag 'nfsd-5.6' of git://linux-nfs.org/~bfields/linux: (55 commits)
  sunrpc: expiry_time should be seconds not timeval
  nfsd: make nfsd_filecache_wq variable static
  nfsd4: fix double free in nfsd4_do_async_copy()
  nfsd: convert file cache to use over/underflow safe refcount
  nfsd: Define the file access mode enum for tracing
  nfsd: Fix a perf warning
  nfsd: Ensure sampling of the write verifier is atomic with the write
  nfsd: Ensure sampling of the commit verifier is atomic with the commit
  sunrpc: clean up cache entry add/remove from hashtable
  sunrpc: Fix potential leaks in sunrpc_cache_unhash()
  nfsd: Ensure exclusion between CLONE and WRITE errors
  nfsd: Pass the nfsd_file as arguments to nfsd4_clone_file_range()
  nfsd: Update the boot verifier on stable writes too.
  nfsd: Fix stable writes
  nfsd: Allow nfsd_vfs_write() to take the nfsd_file as an argument
  nfsd: Fix a soft lockup race in nfsd_file_mark_find_or_create()
  nfsd: Reduce the number of calls to nfsd_file_gc()
  nfsd: Schedule the laundrette regularly irrespective of file errors
  nfsd: Remove unused constant NFSD_FILE_LRU_RESCAN
  nfsd: Containerise filecache laundrette
  ...

fs/nfsd/Kconfig

@@ -134,6 +134,16 @@ config NFSD_FLEXFILELAYOUT
 
 	  If unsure, say N.
 
+config NFSD_V4_2_INTER_SSC
+	bool "NFSv4.2 inter server to server COPY"
+	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
+	help
+	  This option enables support for NFSv4.2 inter server to
+	  server copy where the destination server calls the NFSv4.2
+	  client to read the data to copy from the source server.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY

fs/nfsd/filecache.h

@@ -19,7 +19,7 @@
  */
 struct nfsd_file_mark {
 	struct fsnotify_mark	nfm_mark;
-	atomic_t		nfm_ref;
+	refcount_t		nfm_ref;
 };
 
 /*
@@ -43,14 +43,17 @@ struct nfsd_file {
 	unsigned long		nf_flags;
 	struct inode		*nf_inode;
 	unsigned int		nf_hashval;
-	atomic_t		nf_ref;
+	refcount_t		nf_ref;
 	unsigned char		nf_may;
 	struct nfsd_file_mark	*nf_mark;
+	struct rw_semaphore	nf_rwsem;
 };
 
 int nfsd_file_cache_init(void);
 void nfsd_file_cache_purge(struct net *);
 void nfsd_file_cache_shutdown(void);
+int nfsd_file_cache_start_net(struct net *net);
+void nfsd_file_cache_shutdown_net(struct net *net);
 void nfsd_file_put(struct nfsd_file *nf);
 struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);

fs/nfsd/netns.h

@@ -40,7 +40,7 @@ struct nfsd_net {
 
 	struct lock_manager nfsd4_manager;
 	bool grace_ended;
-	time_t boot_time;
+	time64_t boot_time;
 
 	/* internal mount of the "nfsd" pseudofilesystem: */
 	struct vfsmount *nfsd_mnt;
@@ -92,8 +92,8 @@ struct nfsd_net {
 	bool in_grace;
 	const struct nfsd4_client_tracking_ops *client_tracking_ops;
 
-	time_t nfsd4_lease;
-	time_t nfsd4_grace;
+	time64_t nfsd4_lease;
+	time64_t nfsd4_grace;
 	bool somebody_reclaimed;
 
 	bool track_reclaim_completes;

fs/nfsd/nfs3proc.c

@@ -203,7 +203,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
 		RETURN_STATUS(nfserr_io);
 	nfserr = nfsd_write(rqstp, &resp->fh, argp->offset,
 			    rqstp->rq_vec, nvecs, &cnt,
-			    resp->committed);
+			    resp->committed, resp->verf);
 	resp->count = cnt;
 	RETURN_STATUS(nfserr);
 }
@@ -683,7 +683,8 @@ nfsd3_proc_commit(struct svc_rqst *rqstp)
 		RETURN_STATUS(nfserr_inval);
 
 	fh_copy(&resp->fh, &argp->fh);
-	nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count);
+	nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count,
+			resp->verf);
 
 	RETURN_STATUS(nfserr);
 }

fs/nfsd/nfs3xdr.c

@@ -32,14 +32,14 @@ static u32	nfs3_ftypes[] = {
  * XDR functions for basic NFS types
  */
 static __be32 *
-encode_time3(__be32 *p, struct timespec *time)
+encode_time3(__be32 *p, struct timespec64 *time)
 {
 	*p++ = htonl((u32) time->tv_sec); *p++ = htonl(time->tv_nsec);
 	return p;
 }
 
 static __be32 *
-decode_time3(__be32 *p, struct timespec *time)
+decode_time3(__be32 *p, struct timespec64 *time)
 {
 	time->tv_sec = ntohl(*p++);
 	time->tv_nsec = ntohl(*p++);
@@ -167,7 +167,6 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
 	      struct kstat *stat)
 {
 	struct user_namespace *userns = nfsd_user_namespace(rqstp);
-	struct timespec ts;
 	*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
 	*p++ = htonl((u32) (stat->mode & S_IALLUGO));
 	*p++ = htonl((u32) stat->nlink);
@@ -183,12 +182,9 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
 	*p++ = htonl((u32) MINOR(stat->rdev));
 	p = encode_fsid(p, fhp);
 	p = xdr_encode_hyper(p, stat->ino);
-	ts = timespec64_to_timespec(stat->atime);
-	p = encode_time3(p, &ts);
-	ts = timespec64_to_timespec(stat->mtime);
-	p = encode_time3(p, &ts);
-	ts = timespec64_to_timespec(stat->ctime);
-	p = encode_time3(p, &ts);
+	p = encode_time3(p, &stat->atime);
+	p = encode_time3(p, &stat->mtime);
+	p = encode_time3(p, &stat->ctime);
 
 	return p;
 }
@@ -277,8 +273,8 @@ void fill_pre_wcc(struct svc_fh *fhp)
 		stat.size  = inode->i_size;
 	}
 
-	fhp->fh_pre_mtime = timespec64_to_timespec(stat.mtime);
-	fhp->fh_pre_ctime = timespec64_to_timespec(stat.ctime);
+	fhp->fh_pre_mtime = stat.mtime;
+	fhp->fh_pre_ctime = stat.ctime;
 	fhp->fh_pre_size  = stat.size;
 	fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
 	fhp->fh_pre_saved = true;
@@ -330,7 +326,7 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 	p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp));
 
 	if ((args->check_guard = ntohl(*p++)) != 0) { 
-		struct timespec time; 
+		struct timespec64 time;
 		p = decode_time3(p, &time);
 		args->guardtime = time.tv_sec;
 	}
@@ -751,17 +747,13 @@ int
 nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_writeres *resp = rqstp->rq_resp;
-	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
-	__be32 verf[2];
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
 		*p++ = htonl(resp->committed);
-		/* unique identifier, y2038 overflow can be ignored */
-		nfsd_copy_boot_verifier(verf, nn);
-		*p++ = verf[0];
-		*p++ = verf[1];
+		*p++ = resp->verf[0];
+		*p++ = resp->verf[1];
 	}
 	return xdr_ressize_check(rqstp, p);
 }
@@ -1125,16 +1117,12 @@ int
 nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_commitres *resp = rqstp->rq_resp;
-	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
-	__be32 verf[2];
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	/* Write verifier */
 	if (resp->status == 0) {
-		/* unique identifier, y2038 overflow can be ignored */
-		nfsd_copy_boot_verifier(verf, nn);
-		*p++ = verf[0];
-		*p++ = verf[1];
+		*p++ = resp->verf[0];
+		*p++ = resp->verf[1];
 	}
 	return xdr_ressize_check(rqstp, p);
 }

fs/nfsd/nfs4callback.c

@@ -823,7 +823,16 @@ static const struct rpc_program cb_program = {
 static int max_cb_time(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
+
+	/*
+	 * nfsd4_lease is set to at most one hour in __nfsd4_write_time,
+	 * so we can use 32-bit math on it. Warn if that assumption
+	 * ever stops being true.
+	 */
+	if (WARN_ON_ONCE(nn->nfsd4_lease > 3600))
+		return 360 * HZ;
+
+	return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ;
 }
 
 static struct workqueue_struct *callback_wq;

fs/nfsd/nfs4layouts.c

@@ -675,7 +675,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 
 		/* Client gets 2 lease periods to return it */
 		cutoff = ktime_add_ns(task->tk_start,
-					 nn->nfsd4_lease * NSEC_PER_SEC * 2);
+					 (u64)nn->nfsd4_lease * NSEC_PER_SEC * 2);
 
 		if (ktime_before(now, cutoff)) {
 			rpc_delay(task, HZ/100); /* 10 mili-seconds */

fs/nfsd/nfs4recover.c

@@ -1445,7 +1445,7 @@ nfsd4_cld_grace_done_v0(struct nfsd_net *nn)
 	}
 
 	cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone;
-	cup->cu_u.cu_msg.cm_u.cm_gracetime = (int64_t)nn->boot_time;
+	cup->cu_u.cu_msg.cm_u.cm_gracetime = nn->boot_time;
 	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
 	if (!ret)
 		ret = cup->cu_u.cu_msg.cm_status;
@@ -1782,7 +1782,7 @@ nfsd4_cltrack_client_has_session(struct nfs4_client *clp)
 }
 
 static char *
-nfsd4_cltrack_grace_start(time_t grace_start)
+nfsd4_cltrack_grace_start(time64_t grace_start)
 {
 	int copied;
 	size_t len;
@@ -1795,7 +1795,7 @@ nfsd4_cltrack_grace_start(time_t grace_start)
 	if (!result)
 		return result;
 
-	copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%ld",
+	copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%lld",
 				grace_start);
 	if (copied >= len) {
 		/* just return nothing if output was truncated */
@@ -2004,7 +2004,7 @@ nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
 	char *legacy;
 	char timestr[22]; /* FIXME: better way to determine max size? */
 
-	sprintf(timestr, "%ld", nn->boot_time);
+	sprintf(timestr, "%lld", nn->boot_time);
 	legacy = nfsd4_cltrack_legacy_topdir();
 	nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy, NULL);
 	kfree(legacy);

fs/nfsd/nfs4xdr.c

@@ -40,6 +40,7 @@
 #include <linux/utsname.h>
 #include <linux/pagemap.h>
 #include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/addr.h>
 
 #include "idmap.h"
 #include "acl.h"
@@ -1744,10 +1745,47 @@ nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone)
 	DECODE_TAIL;
 }
 
+static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp,
+				      struct nl4_server *ns)
+{
+	DECODE_HEAD;
+	struct nfs42_netaddr *naddr;
+
+	READ_BUF(4);
+	ns->nl4_type = be32_to_cpup(p++);
+
+	/* currently support for 1 inter-server source server */
+	switch (ns->nl4_type) {
+	case NL4_NETADDR:
+		naddr = &ns->u.nl4_addr;
+
+		READ_BUF(4);
+		naddr->netid_len = be32_to_cpup(p++);
+		if (naddr->netid_len > RPCBIND_MAXNETIDLEN)
+			goto xdr_error;
+
+		READ_BUF(naddr->netid_len + 4); /* 4 for uaddr len */
+		COPYMEM(naddr->netid, naddr->netid_len);
+
+		naddr->addr_len = be32_to_cpup(p++);
+		if (naddr->addr_len > RPCBIND_MAXUADDRLEN)
+			goto xdr_error;
+
+		READ_BUF(naddr->addr_len);
+		COPYMEM(naddr->addr, naddr->addr_len);
+		break;
+	default:
+		goto xdr_error;
+	}
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
 {
 	DECODE_HEAD;
+	struct nl4_server *ns_dummy;
+	int i, count;
 
 	status = nfsd4_decode_stateid(argp, &copy->cp_src_stateid);
 	if (status)
@@ -1762,7 +1800,32 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
 	p = xdr_decode_hyper(p, &copy->cp_count);
 	p++; /* ca_consecutive: we always do consecutive copies */
 	copy->cp_synchronous = be32_to_cpup(p++);
-	/* tmp = be32_to_cpup(p); Source server list not supported */
+
+	count = be32_to_cpup(p++);
+
+	copy->cp_intra = false;
+	if (count == 0) { /* intra-server copy */
+		copy->cp_intra = true;
+		goto intra;
+	}
+
+	/* decode all the supplied server addresses but use first */
+	status = nfsd4_decode_nl4_server(argp, &copy->cp_src);
+	if (status)
+		return status;
+
+	ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL);
+	if (ns_dummy == NULL)
+		return nfserrno(-ENOMEM);
+	for (i = 0; i < count - 1; i++) {
+		status = nfsd4_decode_nl4_server(argp, ns_dummy);
+		if (status) {
+			kfree(ns_dummy);
+			return status;
+		}
+	}
+	kfree(ns_dummy);
+intra:
 
 	DECODE_TAIL;
 }
@@ -1774,6 +1837,18 @@ nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp,
 	return nfsd4_decode_stateid(argp, &os->stateid);
 }
 
+static __be32
+nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp,
+			 struct nfsd4_copy_notify *cn)
+{
+	int status;
+
+	status = nfsd4_decode_stateid(argp, &cn->cpn_src_stateid);
+	if (status)
+		return status;
+	return nfsd4_decode_nl4_server(argp, &cn->cpn_dst);
+}
+
 static __be32
 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 {
@@ -1875,7 +1950,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = {
 	/* new operations for NFSv4.2 */
 	[OP_ALLOCATE]		= (nfsd4_dec)nfsd4_decode_fallocate,
 	[OP_COPY]		= (nfsd4_dec)nfsd4_decode_copy,
-	[OP_COPY_NOTIFY]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_COPY_NOTIFY]	= (nfsd4_dec)nfsd4_decode_copy_notify,
 	[OP_DEALLOCATE]		= (nfsd4_dec)nfsd4_decode_fallocate,
 	[OP_IO_ADVISE]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTERROR]	= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2024,11 +2099,11 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode,
  */
 static __be32 *encode_time_delta(__be32 *p, struct inode *inode)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	u32 ns;
 
 	ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran);
-	ts = ns_to_timespec(ns);
+	ts = ns_to_timespec64(ns);
 
 	p = xdr_encode_hyper(p, ts.tv_sec);
 	*p++ = cpu_to_be32(ts.tv_nsec);
@@ -4243,6 +4318,46 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
 	return nfs_ok;
 }
 
+static __be32
+nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	struct nfs42_netaddr *addr;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 4);
+	*p++ = cpu_to_be32(ns->nl4_type);
+
+	switch (ns->nl4_type) {
+	case NL4_NETADDR:
+		addr = &ns->u.nl4_addr;
+
+		/* netid_len, netid, uaddr_len, uaddr (port included
+		 * in RPCBIND_MAXUADDRLEN)
+		 */
+		p = xdr_reserve_space(xdr,
+			4 /* netid len */ +
+			(XDR_QUADLEN(addr->netid_len) * 4) +
+			4 /* uaddr len */ +
+			(XDR_QUADLEN(addr->addr_len) * 4));
+		if (!p)
+			return nfserr_resource;
+
+		*p++ = cpu_to_be32(addr->netid_len);
+		p = xdr_encode_opaque_fixed(p, addr->netid,
+					    addr->netid_len);
+		*p++ = cpu_to_be32(addr->addr_len);
+		p = xdr_encode_opaque_fixed(p, addr->addr,
+					addr->addr_len);
+		break;
+	default:
+		WARN_ON_ONCE(ns->nl4_type != NL4_NETADDR);
+		return nfserr_inval;
+	}
+
+	return 0;
+}
+
 static __be32
 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_copy *copy)
@@ -4276,6 +4391,40 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+static __be32
+nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,
+			 struct nfsd4_copy_notify *cn)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	/* 8 sec, 4 nsec */
+	p = xdr_reserve_space(xdr, 12);
+	if (!p)
+		return nfserr_resource;
+
+	/* cnr_lease_time */
+	p = xdr_encode_hyper(p, cn->cpn_sec);
+	*p++ = cpu_to_be32(cn->cpn_nsec);
+
+	/* cnr_stateid */
+	nfserr = nfsd4_encode_stateid(xdr, &cn->cpn_cnr_stateid);
+	if (nfserr)
+		return nfserr;
+
+	/* cnr_src.nl_nsvr */
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+
+	*p++ = cpu_to_be32(1);
+
+	return nfsd42_encode_nl4_server(resp, &cn->cpn_src);
+}
+
 static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
@@ -4373,7 +4522,7 @@ static const nfsd4_enc nfsd4_enc_ops[] = {
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_COPY]		= (nfsd4_enc)nfsd4_encode_copy,
-	[OP_COPY_NOTIFY]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_COPY_NOTIFY]	= (nfsd4_enc)nfsd4_encode_copy_notify,
 	[OP_DEALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_IO_ADVISE]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTERROR]	= (nfsd4_enc)nfsd4_encode_noop,
@@ -4500,8 +4649,6 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
 	__be32 *p;
 	struct nfs4_replay *rp = op->replay;
 
-	BUG_ON(!rp);
-
 	p = xdr_reserve_space(xdr, 8 + rp->rp_buflen);
 	if (!p) {
 		WARN_ON_ONCE(1);

fs/nfsd/nfsctl.c

@@ -956,7 +956,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size)
 
 #ifdef CONFIG_NFSD_V4
 static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
-				  time_t *time, struct nfsd_net *nn)
+				  time64_t *time, struct nfsd_net *nn)
 {
 	char *mesg = buf;
 	int rv, i;
@@ -984,11 +984,11 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
 		*time = i;
 	}
 
-	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n", *time);
+	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%lld\n", *time);
 }
 
 static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
-				time_t *time, struct nfsd_net *nn)
+				time64_t *time, struct nfsd_net *nn)
 {
 	ssize_t rv;
 

fs/nfsd/nfsd.h

@@ -19,6 +19,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/addr.h>
 
 #include <uapi/linux/nfsd/debug.h>
 
@@ -142,7 +143,6 @@ int nfs4_state_start(void);
 int nfs4_state_start_net(struct net *net);
 void nfs4_state_shutdown(void);
 void nfs4_state_shutdown_net(struct net *net);
-void nfs4_reset_lease(time_t leasetime);
 int nfs4_reset_recoverydir(char *recdir);
 char * nfs4_recoverydir(void);
 bool nfsd4_spo_must_allow(struct svc_rqst *rqstp);
@@ -153,7 +153,6 @@ static inline int nfs4_state_start(void) { return 0; }
 static inline int nfs4_state_start_net(struct net *net) { return 0; }
 static inline void nfs4_state_shutdown(void) { }
 static inline void nfs4_state_shutdown_net(struct net *net) { }
-static inline void nfs4_reset_lease(time_t leasetime) { }
 static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
 static inline char * nfs4_recoverydir(void) {return NULL; }
 static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
@@ -387,6 +386,37 @@ void		nfsd_lockd_shutdown(void);
 
 extern const u32 nfsd_suppattrs[3][3];
 
+static inline __be32 nfsd4_set_netaddr(struct sockaddr *addr,
+				    struct nfs42_netaddr *netaddr)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+	unsigned int port;
+	size_t ret_addr, ret_port;
+
+	switch (addr->sa_family) {
+	case AF_INET:
+		port = ntohs(sin->sin_port);
+		sprintf(netaddr->netid, "tcp");
+		netaddr->netid_len = 3;
+		break;
+	case AF_INET6:
+		port = ntohs(sin6->sin6_port);
+		sprintf(netaddr->netid, "tcp6");
+		netaddr->netid_len = 4;
+		break;
+	default:
+		return nfserr_inval;
+	}
+	ret_addr = rpc_ntop(addr, netaddr->addr, sizeof(netaddr->addr));
+	ret_port = snprintf(netaddr->addr + ret_addr,
+			    RPCBIND_MAXUADDRLEN + 1 - ret_addr,
+			    ".%u.%u", port >> 8, port & 0xff);
+	WARN_ON(ret_port >= RPCBIND_MAXUADDRLEN + 1 - ret_addr);
+	netaddr->addr_len = ret_addr + ret_port;
+	return 0;
+}
+
 static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2)
 {
 	return !((bm1[0] & ~bm2[0]) ||

fs/nfsd/nfsfh.h

@@ -35,15 +35,15 @@ typedef struct svc_fh {
 
 	bool			fh_locked;	/* inode locked by us */
 	bool			fh_want_write;	/* remount protection taken */
-
+	int			fh_flags;	/* FH flags */
 #ifdef CONFIG_NFSD_V3
 	bool			fh_post_saved;	/* post-op attrs saved */
 	bool			fh_pre_saved;	/* pre-op attrs saved */
 
 	/* Pre-op attributes saved during fh_lock */
 	__u64			fh_pre_size;	/* size before operation */
-	struct timespec		fh_pre_mtime;	/* mtime before oper */
-	struct timespec		fh_pre_ctime;	/* ctime before oper */
+	struct timespec64	fh_pre_mtime;	/* mtime before oper */
+	struct timespec64	fh_pre_ctime;	/* ctime before oper */
 	/*
 	 * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
 	 *  to find out if it is valid.
@@ -56,6 +56,9 @@ typedef struct svc_fh {
 #endif /* CONFIG_NFSD_V3 */
 
 } svc_fh;
+#define NFSD4_FH_FOREIGN (1<<0)
+#define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f))
+#define HAS_FH_FLAG(c, f) ((c)->fh_flags & (f))
 
 enum nfsd_fsid {
 	FSID_DEV = 0,

fs/nfsd/nfsproc.c

@@ -94,7 +94,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
 		 * Solaris, at least, doesn't seem to care what the time
 		 * request is.  We require it be within 30 minutes of now.
 		 */
-		time_t delta = iap->ia_atime.tv_sec - get_seconds();
+		time64_t delta = iap->ia_atime.tv_sec - ktime_get_real_seconds();
 
 		nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
 		if (nfserr)
@@ -113,7 +113,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
 		}
 	}
 
-	nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0);
+	nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0);
 done:
 	return nfsd_return_attrs(nfserr, resp);
 }
@@ -226,7 +226,7 @@ nfsd_proc_write(struct svc_rqst *rqstp)
 		return nfserr_io;
 	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh),
 			    argp->offset, rqstp->rq_vec, nvecs,
-			    &cnt, NFS_DATA_SYNC);
+			    &cnt, NFS_DATA_SYNC, NULL);
 	return nfsd_return_attrs(nfserr, resp);
 }
 
@@ -380,7 +380,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 		 */
 		attr->ia_valid &= ATTR_SIZE;
 		if (attr->ia_valid)
-			nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time_t)0);
+			nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time64_t)0);
 	}
 
 out_unlock:

fs/nfsd/nfssvc.c

@@ -31,6 +31,12 @@
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
+bool inter_copy_offload_enable;
+EXPORT_SYMBOL_GPL(inter_copy_offload_enable);
+module_param(inter_copy_offload_enable, bool, 0644);
+MODULE_PARM_DESC(inter_copy_offload_enable,
+		 "Enable inter server to server copy offload. Default: false");
+
 extern struct svc_program	nfsd_program;
 static int			nfsd(void *vrqstp);
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
@@ -391,20 +397,25 @@ static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cre
 		ret = lockd_up(net, cred);
 		if (ret)
 			goto out_socks;
-		nn->lockd_up = 1;
+		nn->lockd_up = true;
 	}
 
-	ret = nfs4_state_start_net(net);
+	ret = nfsd_file_cache_start_net(net);
 	if (ret)
 		goto out_lockd;
+	ret = nfs4_state_start_net(net);
+	if (ret)
+		goto out_filecache;
 
 	nn->nfsd_net_up = true;
 	return 0;
 
+out_filecache:
+	nfsd_file_cache_shutdown_net(net);
 out_lockd:
 	if (nn->lockd_up) {
 		lockd_down(net);
-		nn->lockd_up = 0;
+		nn->lockd_up = false;
 	}
 out_socks:
 	nfsd_shutdown_generic();
@@ -415,11 +426,11 @@ static void nfsd_shutdown_net(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	nfsd_file_cache_purge(net);
+	nfsd_file_cache_shutdown_net(net);
 	nfs4_state_shutdown_net(net);
 	if (nn->lockd_up) {
 		lockd_down(net);
-		nn->lockd_up = 0;
+		nn->lockd_up = false;
 	}
 	nn->nfsd_net_up = false;
 	nfsd_shutdown_generic();

fs/nfsd/state.h

@@ -56,6 +56,14 @@ typedef struct {
 	stateid_opaque_t        si_opaque;
 } stateid_t;
 
+typedef struct {
+	stateid_t		stid;
+#define NFS4_COPY_STID 1
+#define NFS4_COPYNOTIFY_STID 2
+	unsigned char		sc_type;
+	refcount_t		sc_count;
+} copy_stateid_t;
+
 #define STATEID_FMT	"(%08x/%08x/%08x/%08x)"
 #define STATEID_VAL(s) \
 	(s)->si_opaque.so_clid.cl_boot, \
@@ -96,6 +104,7 @@ struct nfs4_stid {
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
 #define NFS4_LAYOUT_STID 64
+	struct list_head	sc_cp_list;
 	unsigned char		sc_type;
 	stateid_t		sc_stateid;
 	spinlock_t		sc_lock;
@@ -104,6 +113,17 @@ struct nfs4_stid {
 	void			(*sc_free)(struct nfs4_stid *);
 };
 
+/* Keep a list of stateids issued by the COPY_NOTIFY, associate it with the
+ * parent OPEN/LOCK/DELEG stateid.
+ */
+struct nfs4_cpntf_state {
+	copy_stateid_t		cp_stateid;
+	struct list_head	cp_list;	/* per parent nfs4_stid */
+	stateid_t		cp_p_stateid;	/* copy of parent's stateid */
+	clientid_t		cp_p_clid;	/* copy of parent's clid */
+	time64_t		cpntf_time;	/* last time stateid used */
+};
+
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -132,7 +152,7 @@ struct nfs4_delegation {
 	struct list_head	dl_recall_lru;  /* delegation recalled */
 	struct nfs4_clnt_odstate *dl_clnt_odstate;
 	u32			dl_type;
-	time_t			dl_time;
+	time64_t		dl_time;
 /* For recall: */
 	int			dl_retries;
 	struct nfsd4_callback	dl_recall;
@@ -310,7 +330,7 @@ struct nfs4_client {
 #endif
 	struct xdr_netobj	cl_name; 	/* id generated by client */
 	nfs4_verifier		cl_verifier; 	/* generated by client */
-	time_t                  cl_time;        /* time of last lease renewal */
+	time64_t		cl_time;	/* time of last lease renewal */
 	struct sockaddr_storage	cl_addr; 	/* client ipaddress */
 	bool			cl_mach_cred;	/* SP4_MACH_CRED in force */
 	struct svc_cred		cl_cred; 	/* setclientid principal */
@@ -320,7 +340,7 @@ struct nfs4_client {
 	/* NFSv4.1 client implementation id: */
 	struct xdr_netobj	cl_nii_domain;
 	struct xdr_netobj	cl_nii_name;
-	struct timespec		cl_nii_time;
+	struct timespec64	cl_nii_time;
 
 	/* for v4.0 and v4.1 callbacks: */
 	struct nfs4_cb_conn	cl_cb_conn;
@@ -449,7 +469,7 @@ struct nfs4_openowner {
 	 */
 	struct list_head	oo_close_lru;
 	struct nfs4_ol_stateid *oo_last_closed_stid;
-	time_t			oo_time; /* time of placement on so_close_lru */
+	time64_t		oo_time; /* time of placement on so_close_lru */
 #define NFS4_OO_CONFIRMED   1
 	unsigned char		oo_flags;
 };
@@ -606,7 +626,7 @@ static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b)
 struct nfsd4_blocked_lock {
 	struct list_head	nbl_list;
 	struct list_head	nbl_lru;
-	unsigned long		nbl_time;
+	time64_t		nbl_time;
 	struct file_lock	nbl_lock;
 	struct knfsd_fh		nbl_fh;
 	struct nfsd4_callback	nbl_cb;
@@ -618,14 +638,17 @@ struct nfsd4_copy;
 
 extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
-		stateid_t *stateid, int flags, struct nfsd_file **filp);
+		stateid_t *stateid, int flags, struct nfsd_file **filp,
+		struct nfs4_stid **cstid);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
 struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
 				  void (*sc_free)(struct nfs4_stid *));
-int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
-void nfs4_free_cp_state(struct nfsd4_copy *copy);
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
+void nfs4_free_copy_state(struct nfsd4_copy *copy);
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+			struct nfs4_stid *p_stid);
 void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
@@ -655,6 +678,11 @@ void put_nfs4_file(struct nfs4_file *fi);
 extern void nfs4_put_copy(struct nfsd4_copy *copy);
 extern struct nfsd4_copy *
 find_async_copy(struct nfs4_client *clp, stateid_t *staetid);
+extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
+				 struct nfs4_cpntf_state *cps);
+extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+				 struct nfs4_client *clp,
+				 struct nfs4_cpntf_state **cps);
 static inline void get_nfs4_file(struct nfs4_file *fi)
 {
 	refcount_inc(&fi->fi_ref);

fs/nfsd/trace.h

@@ -166,6 +166,12 @@ DEFINE_STATEID_EVENT(layout_recall_done);
 DEFINE_STATEID_EVENT(layout_recall_fail);
 DEFINE_STATEID_EVENT(layout_recall_release);
 
+TRACE_DEFINE_ENUM(NFSD_FILE_HASHED);
+TRACE_DEFINE_ENUM(NFSD_FILE_PENDING);
+TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ);
+TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_WRITE);
+TRACE_DEFINE_ENUM(NFSD_FILE_REFERENCED);
+
 #define show_nf_flags(val)						\
 	__print_flags(val, "|",						\
 		{ 1 << NFSD_FILE_HASHED,	"HASHED" },		\
@@ -195,7 +201,7 @@ DECLARE_EVENT_CLASS(nfsd_file_class,
 	TP_fast_assign(
 		__entry->nf_hashval = nf->nf_hashval;
 		__entry->nf_inode = nf->nf_inode;
-		__entry->nf_ref = atomic_read(&nf->nf_ref);
+		__entry->nf_ref = refcount_read(&nf->nf_ref);
 		__entry->nf_flags = nf->nf_flags;
 		__entry->nf_may = nf->nf_may;
 		__entry->nf_file = nf->nf_file;
@@ -228,7 +234,7 @@ TRACE_EVENT(nfsd_file_acquire,
 	TP_ARGS(rqstp, hash, inode, may_flags, nf, status),
 
 	TP_STRUCT__entry(
-		__field(__be32, xid)
+		__field(u32, xid)
 		__field(unsigned int, hash)
 		__field(void *, inode)
 		__field(unsigned int, may_flags)
@@ -236,27 +242,27 @@ TRACE_EVENT(nfsd_file_acquire,
 		__field(unsigned long, nf_flags)
 		__field(unsigned char, nf_may)
 		__field(struct file *, nf_file)
-		__field(__be32, status)
+		__field(u32, status)
 	),
 
 	TP_fast_assign(
-		__entry->xid = rqstp->rq_xid;
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
 		__entry->hash = hash;
 		__entry->inode = inode;
 		__entry->may_flags = may_flags;
-		__entry->nf_ref = nf ? atomic_read(&nf->nf_ref) : 0;
+		__entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0;
 		__entry->nf_flags = nf ? nf->nf_flags : 0;
 		__entry->nf_may = nf ? nf->nf_may : 0;
 		__entry->nf_file = nf ? nf->nf_file : NULL;
-		__entry->status = status;
+		__entry->status = be32_to_cpu(status);
 	),
 
 	TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u",
-			be32_to_cpu(__entry->xid), __entry->hash, __entry->inode,
+			__entry->xid, __entry->hash, __entry->inode,
 			show_nf_may(__entry->may_flags), __entry->nf_ref,
 			show_nf_flags(__entry->nf_flags),
 			show_nf_may(__entry->nf_may), __entry->nf_file,
-			be32_to_cpu(__entry->status))
+			__entry->status)
 );
 
 DECLARE_EVENT_CLASS(nfsd_file_search_class,

fs/nfsd/vfs.c

@@ -280,19 +280,25 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
  * Commit metadata changes to stable storage.
  */
 static int
-commit_metadata(struct svc_fh *fhp)
+commit_inode_metadata(struct inode *inode)
 {
-	struct inode *inode = d_inode(fhp->fh_dentry);
 	const struct export_operations *export_ops = inode->i_sb->s_export_op;
 
-	if (!EX_ISSYNC(fhp->fh_export))
-		return 0;
-
 	if (export_ops->commit_metadata)
 		return export_ops->commit_metadata(inode);
 	return sync_inode_metadata(inode, 1);
 }
 
+static int
+commit_metadata(struct svc_fh *fhp)
+{
+	struct inode *inode = d_inode(fhp->fh_dentry);
+
+	if (!EX_ISSYNC(fhp->fh_export))
+		return 0;
+	return commit_inode_metadata(inode);
+}
+
 /*
  * Go over the attributes and take care of the small differences between
  * NFS semantics and what Linux expects.
@@ -358,7 +364,7 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
  */
 __be32
 nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
-	     int check_guard, time_t guardtime)
+	     int check_guard, time64_t guardtime)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -524,23 +530,39 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
 }
 #endif
 
-__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
-		u64 dst_pos, u64 count, bool sync)
+__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
+		struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync)
 {
+	struct file *src = nf_src->nf_file;
+	struct file *dst = nf_dst->nf_file;
 	loff_t cloned;
+	__be32 ret = 0;
 
+	down_write(&nf_dst->nf_rwsem);
 	cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
-	if (cloned < 0)
-		return nfserrno(cloned);
-	if (count && cloned != count)
-		return nfserrno(-EINVAL);
+	if (cloned < 0) {
+		ret = nfserrno(cloned);
+		goto out_err;
+	}
+	if (count && cloned != count) {
+		ret = nfserrno(-EINVAL);
+		goto out_err;
+	}
 	if (sync) {
 		loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX;
 		int status = vfs_fsync_range(dst, dst_pos, dst_end, 0);
-		if (status < 0)
-			return nfserrno(status);
+
+		if (!status)
+			status = commit_inode_metadata(file_inode(src));
+		if (status < 0) {
+			nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net,
+						 nfsd_net_id));
+			ret = nfserrno(status);
+		}
 	}
-	return 0;
+out_err:
+	up_write(&nf_dst->nf_rwsem);
+	return ret;
 }
 
 ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
@@ -938,10 +960,12 @@ static int wait_for_concurrent_writes(struct file *file)
 }
 
 __be32
-nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
+nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 				loff_t offset, struct kvec *vec, int vlen,
-				unsigned long *cnt, int stable)
+				unsigned long *cnt, int stable,
+				__be32 *verf)
 {
+	struct file		*file = nf->nf_file;
 	struct svc_export	*exp;
 	struct iov_iter		iter;
 	__be32			nfserr;
@@ -972,9 +996,28 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 		flags |= RWF_SYNC;
 
 	iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt);
-	host_err = vfs_iter_write(file, &iter, &pos, flags);
-	if (host_err < 0)
+	if (flags & RWF_SYNC) {
+		down_write(&nf->nf_rwsem);
+		host_err = vfs_iter_write(file, &iter, &pos, flags);
+		if (host_err < 0)
+			nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
+						 nfsd_net_id));
+		up_write(&nf->nf_rwsem);
+	} else {
+		down_read(&nf->nf_rwsem);
+		if (verf)
+			nfsd_copy_boot_verifier(verf,
+					net_generic(SVC_NET(rqstp),
+					nfsd_net_id));
+		host_err = vfs_iter_write(file, &iter, &pos, flags);
+		up_read(&nf->nf_rwsem);
+	}
+	if (host_err < 0) {
+		nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
+					 nfsd_net_id));
 		goto out_nfserr;
+	}
+	*cnt = host_err;
 	nfsdstats.io_write += *cnt;
 	fsnotify_modify(file);
 
@@ -1036,7 +1079,8 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
  */
 __be32
 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
-	   struct kvec *vec, int vlen, unsigned long *cnt, int stable)
+	   struct kvec *vec, int vlen, unsigned long *cnt, int stable,
+	   __be32 *verf)
 {
 	struct nfsd_file *nf;
 	__be32 err;
@@ -1047,8 +1091,8 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
 	if (err)
 		goto out;
 
-	err = nfsd_vfs_write(rqstp, fhp, nf->nf_file, offset, vec,
-			vlen, cnt, stable);
+	err = nfsd_vfs_write(rqstp, fhp, nf, offset, vec,
+			vlen, cnt, stable, verf);
 	nfsd_file_put(nf);
 out:
 	trace_nfsd_write_done(rqstp, fhp, offset, *cnt);
@@ -1067,7 +1111,7 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
  */
 __be32
 nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
-               loff_t offset, unsigned long count)
+               loff_t offset, unsigned long count, __be32 *verf)
 {
 	struct nfsd_file	*nf;
 	loff_t			end = LLONG_MAX;
@@ -1086,10 +1130,14 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (err)
 		goto out;
 	if (EX_ISSYNC(fhp->fh_export)) {
-		int err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+		int err2;
 
+		down_write(&nf->nf_rwsem);
+		err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
 		switch (err2) {
 		case 0:
+			nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
+						nfsd_net_id));
 			break;
 		case -EINVAL:
 			err = nfserr_notsupp;
@@ -1099,7 +1147,10 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			nfsd_reset_boot_verifier(net_generic(nf->nf_net,
 						 nfsd_net_id));
 		}
-	}
+		up_write(&nf->nf_rwsem);
+	} else
+		nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
+					nfsd_net_id));
 
 	nfsd_file_put(nf);
 out:
@@ -1123,7 +1174,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
 	if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
 		iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
 	if (iap->ia_valid)
-		return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
+		return nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0);
 	/* Callers expect file metadata to be committed here */
 	return nfserrno(commit_metadata(resfhp));
 }
@@ -1386,7 +1437,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			    && d_inode(dchild)->i_atime.tv_sec == v_atime
 			    && d_inode(dchild)->i_size  == 0 ) {
 				if (created)
-					*created = 1;
+					*created = true;
 				break;
 			}
 			/* fall through */
@@ -1395,7 +1446,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			    && d_inode(dchild)->i_atime.tv_sec == v_atime
 			    && d_inode(dchild)->i_size  == 0 ) {
 				if (created)
-					*created = 1;
+					*created = true;
 				goto set_attr;
 			}
 			/* fall through */
@@ -1412,7 +1463,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out_nfserr;
 	}
 	if (created)
-		*created = 1;
+		*created = true;
 
 	nfsd_check_ignore_resizing(iap);
 

fs/nfsd/vfs.h

@@ -34,6 +34,8 @@
 #define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
 
+struct nfsd_file;
+
 /*
  * Callback function for readdir
  */
@@ -48,15 +50,16 @@ __be32		 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
 				const char *, unsigned int,
 				struct svc_export **, struct dentry **);
 __be32		nfsd_setattr(struct svc_rqst *, struct svc_fh *,
-				struct iattr *, int, time_t);
+				struct iattr *, int, time64_t);
 int nfsd_mountpoint(struct dentry *, struct svc_export *);
 #ifdef CONFIG_NFSD_V4
 __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);
-__be32		nfsd4_clone_file_range(struct file *, u64, struct file *,
-				       u64, u64, bool);
+__be32		nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
+				       struct nfsd_file *nf_dst, u64 dst_pos,
+				       u64 count, bool sync);
 #endif /* CONFIG_NFSD_V4 */
 __be32		nfsd_create_locked(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct iattr *attrs,
@@ -71,7 +74,7 @@ __be32		do_nfsd_create(struct svc_rqst *, struct svc_fh *,
 				struct svc_fh *res, int createmode,
 				u32 *verifier, bool *truncp, bool *created);
 __be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
-				loff_t, unsigned long);
+				loff_t, unsigned long, __be32 *verf);
 #endif /* CONFIG_NFSD_V3 */
 int 		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
@@ -91,11 +94,12 @@ __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *,
 				loff_t, struct kvec *, int, unsigned long *,
 				u32 *eof);
 __be32 		nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t,
-				struct kvec *, int, unsigned long *, int);
+				struct kvec *, int, unsigned long *,
+				int stable, __be32 *verf);
 __be32		nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
-				struct file *file, loff_t offset,
+				struct nfsd_file *nf, loff_t offset,
 				struct kvec *vec, int vlen, unsigned long *cnt,
-				int stable);
+				int stable, __be32 *verf);
 __be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
 				char *, int *);
 __be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,

fs/nfsd/xdr3.h

@@ -14,7 +14,7 @@ struct nfsd3_sattrargs {
 	struct svc_fh		fh;
 	struct iattr		attrs;
 	int			check_guard;
-	time_t			guardtime;
+	time64_t		guardtime;
 };
 
 struct nfsd3_diropargs {
@@ -159,6 +159,7 @@ struct nfsd3_writeres {
 	struct svc_fh		fh;
 	unsigned long		count;
 	int			committed;
+	__be32			verf[2];
 };
 
 struct nfsd3_renameres {
@@ -223,6 +224,7 @@ struct nfsd3_pathconfres {
 struct nfsd3_commitres {
 	__be32			status;
 	struct svc_fh		fh;
+	__be32			verf[2];
 };
 
 struct nfsd3_getaclres {

fs/nfsd/xdr4.h

@@ -46,9 +46,9 @@
 #define CURRENT_STATE_ID_FLAG (1<<0)
 #define SAVED_STATE_ID_FLAG (1<<1)
 
-#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
-#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
-#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+#define SET_CSTATE_FLAG(c, f) ((c)->sid_flags |= (f))
+#define HAS_CSTATE_FLAG(c, f) ((c)->sid_flags & (f))
+#define CLEAR_CSTATE_FLAG(c, f) ((c)->sid_flags &= ~(f))
 
 struct nfsd4_compound_state {
 	struct svc_fh		current_fh;
@@ -221,6 +221,7 @@ struct nfsd4_lookup {
 struct nfsd4_putfh {
 	u32		pf_fhlen;           /* request */
 	char		*pf_fhval;          /* request */
+	bool		no_verify;	    /* represents foreigh fh */
 };
 
 struct nfsd4_open {
@@ -518,11 +519,13 @@ struct nfsd42_write_res {
 
 struct nfsd4_copy {
 	/* request */
-	stateid_t	cp_src_stateid;
-	stateid_t	cp_dst_stateid;
-	u64		cp_src_pos;
-	u64		cp_dst_pos;
-	u64		cp_count;
+	stateid_t		cp_src_stateid;
+	stateid_t		cp_dst_stateid;
+	u64			cp_src_pos;
+	u64			cp_dst_pos;
+	u64			cp_count;
+	struct nl4_server	cp_src;
+	bool			cp_intra;
 
 	/* both */
 	bool		cp_synchronous;
@@ -540,13 +543,18 @@ struct nfsd4_copy {
 	struct nfsd_file        *nf_src;
 	struct nfsd_file        *nf_dst;
 
-	stateid_t		cp_stateid;
+	copy_stateid_t		cp_stateid;
 
 	struct list_head	copies;
 	struct task_struct	*copy_task;
 	refcount_t		refcount;
 	bool			stopped;
+
+	struct vfsmount		*ss_mnt;
+	struct nfs_fh		c_fh;
+	nfs4_stateid		stateid;
 };
+extern bool inter_copy_offload_enable;
 
 struct nfsd4_seek {
 	/* request */
@@ -568,6 +576,18 @@ struct nfsd4_offload_status {
 	u32		status;
 };
 
+struct nfsd4_copy_notify {
+	/* request */
+	stateid_t		cpn_src_stateid;
+	struct nl4_server	cpn_dst;
+
+	/* response */
+	stateid_t		cpn_cnr_stateid;
+	u64			cpn_sec;
+	u32			cpn_nsec;
+	struct nl4_server	cpn_src;
+};
+
 struct nfsd4_op {
 	int					opnum;
 	const struct nfsd4_operation *		opdesc;
@@ -627,6 +647,7 @@ struct nfsd4_op {
 		struct nfsd4_clone		clone;
 		struct nfsd4_copy		copy;
 		struct nfsd4_offload_status	offload_status;
+		struct nfsd4_copy_notify	copy_notify;
 		struct nfsd4_seek		seek;
 	} u;
 	struct nfs4_replay *			replay;

net/sunrpc/auth_gss/svcauth_gss.c

@@ -1248,6 +1248,7 @@ static int gss_proxy_save_rsc(struct cache_detail *cd,
 		dprintk("RPC:       No creds found!\n");
 		goto out;
 	} else {
+		struct timespec64 boot;
 
 		/* steal creds */
 		rsci.cred = ud->creds;
@@ -1268,6 +1269,9 @@ static int gss_proxy_save_rsc(struct cache_detail *cd,
 						&expiry, GFP_KERNEL);
 		if (status)
 			goto out;
+
+		getboottime64(&boot);
+		expiry -= boot.tv_sec;
 	}
 
 	rsci.h.expiry_time = expiry;

net/sunrpc/cache.c

@@ -77,6 +77,22 @@ static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail,
 	return NULL;
 }
 
+static void sunrpc_begin_cache_remove_entry(struct cache_head *ch,
+					    struct cache_detail *cd)
+{
+	/* Must be called under cd->hash_lock */
+	hlist_del_init_rcu(&ch->cache_list);
+	set_bit(CACHE_CLEANED, &ch->flags);
+	cd->entries --;
+}
+
+static void sunrpc_end_cache_remove_entry(struct cache_head *ch,
+					  struct cache_detail *cd)
+{
+	cache_fresh_unlocked(ch, cd);
+	cache_put(ch, cd);
+}
+
 static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
 						 struct cache_head *key,
 						 int hash)
@@ -100,8 +116,7 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
 	hlist_for_each_entry_rcu(tmp, head, cache_list) {
 		if (detail->match(tmp, key)) {
 			if (cache_is_expired(detail, tmp)) {
-				hlist_del_init_rcu(&tmp->cache_list);
-				detail->entries --;
+				sunrpc_begin_cache_remove_entry(tmp, detail);
 				freeme = tmp;
 				break;
 			}
@@ -117,10 +132,8 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
 	cache_get(new);
 	spin_unlock(&detail->hash_lock);
 
-	if (freeme) {
-		cache_fresh_unlocked(freeme, detail);
-		cache_put(freeme, detail);
-	}
+	if (freeme)
+		sunrpc_end_cache_remove_entry(freeme, detail);
 	return new;
 }
 
@@ -454,8 +467,7 @@ static int cache_clean(void)
 			if (!cache_is_expired(current_detail, ch))
 				continue;
 
-			hlist_del_init_rcu(&ch->cache_list);
-			current_detail->entries--;
+			sunrpc_begin_cache_remove_entry(ch, current_detail);
 			rv = 1;
 			break;
 		}
@@ -465,11 +477,8 @@ static int cache_clean(void)
 		if (!ch)
 			current_index ++;
 		spin_unlock(&cache_list_lock);
-		if (ch) {
-			set_bit(CACHE_CLEANED, &ch->flags);
-			cache_fresh_unlocked(ch, d);
-			cache_put(ch, d);
-		}
+		if (ch)
+			sunrpc_end_cache_remove_entry(ch, d);
 	} else
 		spin_unlock(&cache_list_lock);
 
@@ -525,13 +534,9 @@ void cache_purge(struct cache_detail *detail)
 	for (i = 0; i < detail->hash_size; i++) {
 		head = &detail->hash_table[i];
 		hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
-			hlist_del_init_rcu(&ch->cache_list);
-			detail->entries--;
-
-			set_bit(CACHE_CLEANED, &ch->flags);
+			sunrpc_begin_cache_remove_entry(ch, detail);
 			spin_unlock(&detail->hash_lock);
-			cache_fresh_unlocked(ch, detail);
-			cache_put(ch, detail);
+			sunrpc_end_cache_remove_entry(ch, detail);
 			spin_lock(&detail->hash_lock);
 		}
 	}
@@ -1885,10 +1890,9 @@ void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h)
 {
 	spin_lock(&cd->hash_lock);
 	if (!hlist_unhashed(&h->cache_list)){
-		hlist_del_init_rcu(&h->cache_list);
-		cd->entries--;
+		sunrpc_begin_cache_remove_entry(h, cd);
 		spin_unlock(&cd->hash_lock);
-		cache_put(h, cd);
+		sunrpc_end_cache_remove_entry(h, cd);
 	} else
 		spin_unlock(&cd->hash_lock);
 }