Merge tag 'nfs-for-6.15-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:

 - NFS: Fix a couple of missed handlers for the ENETDOWN and ENETUNREACH
   transport errors

 - NFS: Handle Oopsable failure of nfs_get_lock_context in the unlock
   path

 - NFSv4: Fix a race in nfs_local_open_fh()

 - NFSv4/pNFS: Fix a couple of layout segment leaks in layoutreturn

 - NFSv4/pNFS Avoid sharing pNFS DS connections between net namespaces
   since IP addresses are not guaranteed to refer to the same nodes

 - NFS: Don't flush file data while holding multiple directory locks in
   nfs_rename()

* tag 'nfs-for-6.15-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: Avoid flushing data while holding directory locks in nfs_rename()
  NFS/pnfs: Fix the error path in pnfs_layoutreturn_retry_later_locked()
  NFSv4/pnfs: Reset the layout state after a layoutreturn
  NFS/localio: Fix a race in nfs_local_open_fh()
  nfs: nfs3acl: drop useless assignment in nfs3_get_acl()
  nfs: direct: drop useless initializer in nfs_direct_write_completion()
  nfs: move the nfs4_data_server_cache into struct nfs_net
  nfs: don't share pNFS DS connections between net namespaces
  nfs: handle failure of nfs_get_lock_context in unlock path
  pNFS/flexfiles: Record the RPC errors in the I/O tracepoints
  NFSv4/pnfs: Layoutreturn on close must handle fatal networking errors
  NFSv4: Handle fatal ENETDOWN and ENETUNREACH errors

fs/nfs/client.c

@@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc)
 		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
 			server->namelen = NFS2_MAXNAMLEN;
 	}
+	/* Linux 'subtree_check' borkenness mandates this setting */
+	server->fh_expire_type = NFS_FH_VOL_RENAME;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
 		error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh,
@@ -1199,6 +1201,10 @@ void nfs_clients_init(struct net *net)
 	INIT_LIST_HEAD(&nn->nfs_volume_list);
 #if IS_ENABLED(CONFIG_NFS_V4)
 	idr_init(&nn->cb_ident_idr);
+#endif
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	INIT_LIST_HEAD(&nn->nfs4_data_server_cache);
+	spin_lock_init(&nn->nfs4_data_server_lock);
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
 	nn->boot_time = ktime_get_real();
@@ -1216,6 +1222,9 @@ void nfs_clients_exit(struct net *net)
 	nfs_cleanup_cb_ident_idr(net);
 	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
 	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache));
+#endif
 }
 
 #ifdef CONFIG_PROC_FS

fs/nfs/dir.c

@@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
 	unblock_revalidate(new_dentry);
 }
 
+static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry,
+					   struct dentry *new_dentry)
+{
+	struct nfs_server *server = NFS_SB(old_dentry->d_sb);
+
+	if (old_dentry->d_parent != new_dentry->d_parent)
+		return false;
+	if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE)
+		return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN);
+	return true;
+}
+
 /*
  * RENAME
  * FIXME: Some nfsds, like the Linux user space nfsd, may generate a
@@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 
 	}
 
-	if (S_ISREG(old_inode->i_mode))
+	if (S_ISREG(old_inode->i_mode) &&
+	    nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry))
 		nfs_sync_inode(old_inode);
 	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
 				must_unblock ? nfs_unblock_rename : NULL);

fs/nfs/direct.c

@@ -757,7 +757,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;
 	struct nfs_commit_info cinfo;
-	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 	struct inode *inode = dreq->inode;
 	int flags = NFS_ODIRECT_DONE;
 
@@ -786,6 +785,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	spin_unlock(&inode->i_lock);
 
 	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req;
 
 		req = nfs_list_entry(hdr->pages.next);
 		nfs_list_remove_request(req);

fs/nfs/filelayout/filelayoutdev.c

@@ -76,6 +76,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct page *scratch;
 	struct list_head dsaddrs;
 	struct nfs4_pnfs_ds_addr *da;
+	struct net *net = server->nfs_client->cl_net;
 
 	/* set up xdr stream */
 	scratch = alloc_page(gfp_flags);
@@ -159,8 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-						    &stream, gfp_flags);
+			da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
 		}
@@ -170,7 +170,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 			goto out_err_free_deviceid;
 		}
 
-		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
 		if (!dsaddr->ds_list[i])
 			goto out_err_drain_dsaddrs;
 		trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr);

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -1329,7 +1329,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_READ,
 					    task->tk_status);
-		trace_ff_layout_read_error(hdr);
+		trace_ff_layout_read_error(hdr, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1502,7 +1502,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_WRITE,
 					    task->tk_status);
-		trace_ff_layout_write_error(hdr);
+		trace_ff_layout_write_error(hdr, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1551,7 +1551,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 					    data->args.offset, data->args.count,
 					    &data->res.op_status, OP_COMMIT,
 					    task->tk_status);
-		trace_ff_layout_commit_error(data);
+		trace_ff_layout_commit_error(data, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,

fs/nfs/flexfilelayout/flexfilelayoutdev.c

@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct nfs4_pnfs_ds_addr *da;
 	struct nfs4_ff_layout_ds *new_ds = NULL;
 	struct nfs4_ff_ds_version *ds_versions = NULL;
+	struct net *net = server->nfs_client->cl_net;
 	u32 mp_count;
 	u32 version_count;
 	__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 	for (i = 0; i < mp_count; i++) {
 		/* multipath ds */
-		da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-					    &stream, gfp_flags);
+		da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 		if (da)
 			list_add_tail(&da->da_node, &dsaddrs);
 	}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	new_ds->ds_versions = ds_versions;
 	new_ds->ds_versions_cnt = version_count;
 
-	new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+	new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
 	if (!new_ds->ds)
 		goto out_err_drain_dsaddrs;
 

fs/nfs/localio.c

@@ -278,6 +278,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
 		if (IS_ERR(new))
 			return NULL;
+		rcu_read_lock();
 		/* try to swap in the pointer */
 		spin_lock(&clp->cl_uuid.lock);
 		nf = rcu_dereference_protected(*pnf, 1);
@@ -287,7 +288,6 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 			rcu_assign_pointer(*pnf, nf);
 		}
 		spin_unlock(&clp->cl_uuid.lock);
-		rcu_read_lock();
 	}
 	nf = nfs_local_file_get(nf);
 	rcu_read_unlock();

fs/nfs/netns.h

@@ -31,7 +31,11 @@ struct nfs_net {
 	unsigned short nfs_callback_tcpport;
 	unsigned short nfs_callback_tcpport6;
 	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
-#endif
+#endif /* CONFIG_NFS_V4 */
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	struct list_head nfs4_data_server_cache;
+	spinlock_t nfs4_data_server_lock;
+#endif /* CONFIG_NFS_V4_1 */
 	struct nfs_netns_client *nfs_client;
 	spinlock_t nfs_client_lock;
 	ktime_t boot_time;

fs/nfs/nfs3acl.c

@@ -104,7 +104,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu)
 
 	switch (status) {
 		case 0:
-			status = nfs_refresh_inode(inode, res.fattr);
+			nfs_refresh_inode(inode, res.fattr);
 			break;
 		case -EPFNOSUPPORT:
 		case -EPROTONOSUPPORT:

fs/nfs/nfs4proc.c

@@ -671,6 +671,15 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
 	struct nfs_client *clp = server->nfs_client;
 	int ret;
 
+	if ((task->tk_rpc_status == -ENETDOWN ||
+	     task->tk_rpc_status == -ENETUNREACH) &&
+	    task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+		exception->delay = 0;
+		exception->recovering = 0;
+		exception->retry = 0;
+		return -EIO;
+	}
+
 	ret = nfs4_do_handle_exception(server, errorcode, exception);
 	if (exception->delay) {
 		int ret2 = nfs4_exception_should_retrans(server, exception);
@@ -7074,10 +7083,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	struct nfs4_unlockdata *p;
 	struct nfs4_state *state = lsp->ls_state;
 	struct inode *inode = state->inode;
+	struct nfs_lock_context *l_ctx;
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (p == NULL)
 		return NULL;
+	l_ctx = nfs_get_lock_context(ctx);
+	if (!IS_ERR(l_ctx)) {
+		p->l_ctx = l_ctx;
+	} else {
+		kfree(p);
+		return NULL;
+	}
 	p->arg.fh = NFS_FH(inode);
 	p->arg.fl = &p->fl;
 	p->arg.seqid = seqid;
@@ -7085,7 +7102,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	p->lsp = lsp;
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
-	p->l_ctx = nfs_get_lock_context(ctx);
 	locks_init_lock(&p->fl);
 	locks_copy_lock(&p->fl, fl);
 	p->server = NFS_SERVER(inode);

fs/nfs/nfs4trace.h

@@ -2051,13 +2051,15 @@ TRACE_EVENT(fl_getdevinfo,
 
 DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 		TP_PROTO(
-			const struct nfs_pgio_header *hdr
+			const struct nfs_pgio_header *hdr,
+			int error
 		),
 
-		TP_ARGS(hdr),
+		TP_ARGS(hdr, error),
 
 		TP_STRUCT__entry(
 			__field(unsigned long, error)
+			__field(unsigned long, nfs_error)
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
@@ -2073,7 +2075,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 		TP_fast_assign(
 			const struct inode *inode = hdr->inode;
 
-			__entry->error = hdr->res.op_status;
+			__entry->error = -error;
+			__entry->nfs_error = hdr->res.op_status;
 			__entry->fhandle = nfs_fhandle_hash(hdr->args.fh);
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->dev = inode->i_sb->s_dev;
@@ -2088,7 +2091,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s",
+			"offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s "
+			"nfs_error=%lu (%s)",
 			-__entry->error,
 			show_nfs4_status(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -2096,28 +2100,32 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 			__entry->fhandle,
 			__entry->offset, __entry->count,
 			__entry->stateid_seq, __entry->stateid_hash,
-			__get_str(dstaddr)
+			__get_str(dstaddr), __entry->nfs_error,
+			show_nfs4_status(__entry->nfs_error)
 		)
 );
 
 #define DEFINE_NFS4_FLEXFILES_IO_EVENT(name) \
 	DEFINE_EVENT(nfs4_flexfiles_io_event, name, \
 			TP_PROTO( \
-				const struct nfs_pgio_header *hdr \
+				const struct nfs_pgio_header *hdr, \
+				int error \
 			), \
-			TP_ARGS(hdr))
+			TP_ARGS(hdr, error))
 DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_read_error);
 DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_write_error);
 
 TRACE_EVENT(ff_layout_commit_error,
 		TP_PROTO(
-			const struct nfs_commit_data *data
+			const struct nfs_commit_data *data,
+			int error
 		),
 
-		TP_ARGS(data),
+		TP_ARGS(data, error),
 
 		TP_STRUCT__entry(
 			__field(unsigned long, error)
+			__field(unsigned long, nfs_error)
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
@@ -2131,7 +2139,8 @@ TRACE_EVENT(ff_layout_commit_error,
 		TP_fast_assign(
 			const struct inode *inode = data->inode;
 
-			__entry->error = data->res.op_status;
+			__entry->error = -error;
+			__entry->nfs_error = data->res.op_status;
 			__entry->fhandle = nfs_fhandle_hash(data->args.fh);
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->dev = inode->i_sb->s_dev;
@@ -2142,14 +2151,15 @@ TRACE_EVENT(ff_layout_commit_error,
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%llu count=%u dstaddr=%s",
+			"offset=%llu count=%u dstaddr=%s nfs_error=%lu (%s)",
 			-__entry->error,
 			show_nfs4_status(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			__entry->offset, __entry->count,
-			__get_str(dstaddr)
+			__get_str(dstaddr), __entry->nfs_error,
+			show_nfs4_status(__entry->nfs_error)
 		)
 );
 

fs/nfs/pnfs.c

@@ -745,6 +745,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 	return remaining;
 }
 
+static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo)
+{
+	struct pnfs_layout_segment *lseg;
+
+	list_for_each_entry(lseg, &lo->plh_return_segs, pls_list)
+		pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
+}
+
 static void
 pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo,
 		struct list_head *free_me,
@@ -1246,21 +1254,15 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
 static void
 pnfs_layoutreturn_retry_later_locked(struct pnfs_layout_hdr *lo,
 				     const nfs4_stateid *arg_stateid,
-				     const struct pnfs_layout_range *range)
+				     const struct pnfs_layout_range *range,
+				     struct list_head *freeme)
 {
-	const struct pnfs_layout_segment *lseg;
-	u32 seq = be32_to_cpu(arg_stateid->seqid);
-
 	if (pnfs_layout_is_valid(lo) &&
-	    nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) {
-		list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) {
-			if (pnfs_seqid_is_newer(lseg->pls_seq, seq) ||
-			    !pnfs_should_free_range(&lseg->pls_range, range))
-				continue;
-			pnfs_set_plh_return_info(lo, range->iomode, seq);
-			break;
-		}
-	}
+	    nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+		pnfs_reset_return_info(lo);
+	else
+		pnfs_mark_layout_stateid_invalid(lo, freeme);
+	pnfs_clear_layoutreturn_waitbit(lo);
 }
 
 void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
@@ -1268,11 +1270,12 @@ void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
 				   const struct pnfs_layout_range *range)
 {
 	struct inode *inode = lo->plh_inode;
+	LIST_HEAD(freeme);
 
 	spin_lock(&inode->i_lock);
-	pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range);
-	pnfs_clear_layoutreturn_waitbit(lo);
+	pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range, &freeme);
 	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&freeme);
 }
 
 void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
@@ -1292,6 +1295,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
 		pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
 		pnfs_free_returned_lsegs(lo, &freeme, range, seq);
 		pnfs_set_layout_stateid(lo, stateid, NULL, true);
+		pnfs_reset_return_info(lo);
 	} else
 		pnfs_mark_layout_stateid_invalid(lo, &freeme);
 out_unlock:
@@ -1661,6 +1665,18 @@ int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
 		/* Was there an RPC level error? If not, retry */
 		if (task->tk_rpc_status == 0)
 			break;
+		/*
+		 * Is there a fatal network level error?
+		 * If so release the layout, but flag the error.
+		 */
+		if ((task->tk_rpc_status == -ENETDOWN ||
+		     task->tk_rpc_status == -ENETUNREACH) &&
+		    task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+			*ret = 0;
+			(*respp)->lrs_present = 0;
+			retval = -EIO;
+			break;
+		}
 		/* If the call was not sent, let caller handle it */
 		if (!RPC_WAS_SENT(task))
 			return 0;
@@ -1695,6 +1711,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	struct inode *inode = args->inode;
 	const nfs4_stateid *res_stateid = NULL;
 	struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
+	LIST_HEAD(freeme);
 
 	switch (ret) {
 	case -NFS4ERR_BADSESSION:
@@ -1703,9 +1720,9 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	case -NFS4ERR_NOMATCHING_LAYOUT:
 		spin_lock(&inode->i_lock);
 		pnfs_layoutreturn_retry_later_locked(lo, &args->stateid,
-						     &args->range);
-		pnfs_clear_layoutreturn_waitbit(lo);
+						     &args->range, &freeme);
 		spin_unlock(&inode->i_lock);
+		pnfs_free_lseg_list(&freeme);
 		break;
 	case 0:
 		if (res->lrs_present)

fs/nfs/pnfs.h

@@ -60,6 +60,7 @@ struct nfs4_pnfs_ds {
 	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
 	char			*ds_remotestr;	/* comma sep list of addrs */
 	struct list_head	ds_addrs;
+	const struct net	*ds_net;
 	struct nfs_client	*ds_clp;
 	refcount_t		ds_count;
 	unsigned long		ds_state;
@@ -415,7 +416,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode,
 int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
 void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
-struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net,
+				      struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
 void nfs4_pnfs_v3_ds_connect_unload(void);
 int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,

fs/nfs/pnfs_nfs.c

@@ -16,6 +16,7 @@
 #include "nfs4session.h"
 #include "internal.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
 
@@ -504,14 +505,14 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
 /*
  * Data server cache
  *
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
+ * Data servers can be mapped to different device ids, but should
+ * never be shared between net namespaces.
+ *
+ * nfs4_pnfs_ds reference counting:
  *   - set to 1 on allocation
  *   - incremented when a device id maps a data server already in the cache.
  *   - decremented when deviceid is removed from the cache.
  */
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
 
 /* Debug routines */
 static void
@@ -604,11 +605,11 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1,
  * Lookup DS by addresses.  nfs4_ds_cache_lock is held
  */
 static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
+_data_server_lookup_locked(const struct nfs_net *nn, const struct list_head *dsaddrs)
 {
 	struct nfs4_pnfs_ds *ds;
 
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+	list_for_each_entry(ds, &nn->nfs4_data_server_cache, ds_node)
 		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
 			return ds;
 	return NULL;
@@ -653,10 +654,11 @@ static void destroy_ds(struct nfs4_pnfs_ds *ds)
 
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
 {
-	if (refcount_dec_and_lock(&ds->ds_count,
-				&nfs4_ds_cache_lock)) {
+	struct nfs_net *nn = net_generic(ds->ds_net, nfs_net_id);
+
+	if (refcount_dec_and_lock(&ds->ds_count, &nn->nfs4_data_server_lock)) {
 		list_del_init(&ds->ds_node);
-		spin_unlock(&nfs4_ds_cache_lock);
+		spin_unlock(&nn->nfs4_data_server_lock);
 		destroy_ds(ds);
 	}
 }
@@ -716,8 +718,9 @@ out_err:
  * uncached and return cached struct nfs4_pnfs_ds.
  */
 struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
+nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags)
 {
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
 	char *remotestr;
 
@@ -733,16 +736,17 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 	/* this is only used for debugging, so it's ok if its NULL */
 	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
 
-	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(dsaddrs);
+	spin_lock(&nn->nfs4_data_server_lock);
+	tmp_ds = _data_server_lookup_locked(nn, dsaddrs);
 	if (tmp_ds == NULL) {
 		INIT_LIST_HEAD(&ds->ds_addrs);
 		list_splice_init(dsaddrs, &ds->ds_addrs);
 		ds->ds_remotestr = remotestr;
 		refcount_set(&ds->ds_count, 1);
 		INIT_LIST_HEAD(&ds->ds_node);
+		ds->ds_net = net;
 		ds->ds_clp = NULL;
-		list_add(&ds->ds_node, &nfs4_data_server_cache);
+		list_add(&ds->ds_node, &nn->nfs4_data_server_cache);
 		dprintk("%s add new data server %s\n", __func__,
 			ds->ds_remotestr);
 	} else {
@@ -754,7 +758,7 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 			refcount_read(&tmp_ds->ds_count));
 		ds = tmp_ds;
 	}
-	spin_unlock(&nfs4_ds_cache_lock);
+	spin_unlock(&nn->nfs4_data_server_lock);
 out:
 	return ds;
 }

include/linux/nfs_fs_sb.h

@@ -213,6 +213,15 @@ struct nfs_server {
 	char			*fscache_uniq;	/* Uniquifier (or NULL) */
 #endif
 
+	/* The following #defines numerically match the NFSv4 equivalents */
+#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1)
+#define NFS_FH_VOLATILE_ANY (0x2)
+#define NFS_FH_VOL_MIGRATION (0x4)
+#define NFS_FH_VOL_RENAME (0x8)
+#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME)
+	u32			fh_expire_type;	/* V4 bitmask representing file
+						   handle volatility type for
+						   this filesystem */
 	u32			pnfs_blksize;	/* layout_blksize attr */
 #if IS_ENABLED(CONFIG_NFS_V4)
 	u32			attr_bitmask[3];/* V4 bitmask representing the set
@@ -236,9 +245,6 @@ struct nfs_server {
 	u32			acl_bitmask;	/* V4 bitmask representing the ACEs
 						   that are supported on this
 						   filesystem */
-	u32			fh_expire_type;	/* V4 bitmask representing file
-						   handle volatility type for
-						   this filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
 	void			*pnfs_ld_data;	/* per mount point data */