Merge tag 'nfs-for-5.2-1' of git://git.linux-nfs.org/projects/anna/li…

…nux-nfs

Pull NFS client updates from Anna Schumaker:
 "Highlights include:

  Stable bugfixes:
   - Fall back to MDS if no deviceid is found rather than aborting   # v4.11+
   - NFS4: Fix v4.0 client state corruption when mount

  Features:
   - Much improved handling of soft mounts with NFS v4.0:
       - Reduce risk of false positive timeouts
       - Faster failover of reads and writes after a timeout
       - Added a "softerr" mount option to return ETIMEDOUT instead of
         EIO to the application after a timeout
   - Increase number of xprtrdma backchannel requests
   - Add additional xprtrdma tracepoints
   - Improved send completion batching for xprtrdma

  Other bugfixes and cleanups:
   - Return -EINVAL when NFS v4.2 is passed an invalid dedup mode
   - Reduce usage of GFP_ATOMIC pages in SUNRPC
   - Various minor NFS over RDMA cleanups and bugfixes
   - Use the correct container namespace for upcalls
   - Don't share superblocks between user namespaces
   - Various other container fixes
   - Make nfs_match_client() killable to prevent soft lockups
   - Don't mark all open state for recovery when handling recallable
     state revoked flag"

* tag 'nfs-for-5.2-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (69 commits)
  SUNRPC: Rebalance a kref in auth_gss.c
  NFS: Fix a double unlock from nfs_match,get_client
  nfs: pass the correct prototype to read_cache_page
  NFSv4: don't mark all open state for recovery when handling recallable state revoked flag
  SUNRPC: Fix an error code in gss_alloc_msg()
  SUNRPC: task should be exit if encode return EKEYEXPIRED more times
  NFS4: Fix v4.0 client state corruption when mount
  PNFS fallback to MDS if no deviceid found
  NFS: make nfs_match_client killable
  lockd: Store the lockd client credential in struct nlm_host
  NFS: When mounting, don't share filesystems between different user namespaces
  NFS: Convert NFSv2 to use the container user namespace
  NFSv4: Convert the NFS client idmapper to use the container user namespace
  NFS: Convert NFSv3 to use the container user namespace
  SUNRPC: Use namespace of listening daemon in the client AUTH_GSS upcall
  SUNRPC: Use the client user namespace when encoding creds
  NFS: Store the credential of the mount process in the nfs_server
  SUNRPC: Cache cred of process creating the rpc_client
  xprtrdma: Remove stale comment
  xprtrdma: Update comments that reference ib_drain_qp
  ...

fs/lockd/clntlock.c

@@ -63,7 +63,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
 	host = nlmclnt_lookup_host(nlm_init->address, nlm_init->addrlen,
 				   nlm_init->protocol, nlm_version,
 				   nlm_init->hostname, nlm_init->noresvport,
-				   nlm_init->net);
+				   nlm_init->net, nlm_init->cred);
 	if (host == NULL)
 		goto out_nohost;
 	if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)

fs/lockd/clntproc.c

@@ -715,7 +715,7 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 	struct nlm_rqst	*req = data;
 	u32 status = ntohl(req->a_res.status);
 
-	if (RPC_ASSASSINATED(task))
+	if (RPC_SIGNALLED(task))
 		goto die;
 
 	if (task->tk_status < 0) {
@@ -783,7 +783,7 @@ static void nlmclnt_cancel_callback(struct rpc_task *task, void *data)
 	struct nlm_rqst	*req = data;
 	u32 status = ntohl(req->a_res.status);
 
-	if (RPC_ASSASSINATED(task))
+	if (RPC_SIGNALLED(task))
 		goto die;
 
 	if (task->tk_status < 0) {

fs/lockd/host.c

@@ -60,6 +60,7 @@ struct nlm_lookup_host_info {
 	const size_t		hostname_len;	/* it's length */
 	const int		noresvport;	/* use non-priv port */
 	struct net		*net;		/* network namespace to bind */
+	const struct cred	*cred;
 };
 
 /*
@@ -162,6 +163,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
 	host->h_nsmhandle  = nsm;
 	host->h_addrbuf    = nsm->sm_addrbuf;
 	host->net	   = ni->net;
+	host->h_cred	   = get_cred(ni->cred),
 	strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename));
 
 out:
@@ -188,6 +190,7 @@ static void nlm_destroy_host_locked(struct nlm_host *host)
 	clnt = host->h_rpcclnt;
 	if (clnt != NULL)
 		rpc_shutdown_client(clnt);
+	put_cred(host->h_cred);
 	kfree(host);
 
 	ln->nrhosts--;
@@ -202,6 +205,8 @@ static void nlm_destroy_host_locked(struct nlm_host *host)
  * @version: NLM protocol version
  * @hostname: '\0'-terminated hostname of server
  * @noresvport: 1 if non-privileged port should be used
+ * @net: pointer to net namespace
+ * @cred: pointer to cred
  *
  * Returns an nlm_host structure that matches the passed-in
  * [server address, transport protocol, NLM version, server hostname].
@@ -214,7 +219,8 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 				     const u32 version,
 				     const char *hostname,
 				     int noresvport,
-				     struct net *net)
+				     struct net *net,
+				     const struct cred *cred)
 {
 	struct nlm_lookup_host_info ni = {
 		.server		= 0,
@@ -226,6 +232,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 		.hostname_len	= strlen(hostname),
 		.noresvport	= noresvport,
 		.net		= net,
+		.cred		= cred,
 	};
 	struct hlist_head *chain;
 	struct nlm_host	*host;
@@ -458,6 +465,7 @@ nlm_bind_host(struct nlm_host *host)
 			.authflavor	= RPC_AUTH_UNIX,
 			.flags		= (RPC_CLNT_CREATE_NOPING |
 					   RPC_CLNT_CREATE_AUTOBIND),
+			.cred		= host->h_cred,
 		};
 
 		/*

fs/lockd/mon.c

@@ -82,6 +82,7 @@ static struct rpc_clnt *nsm_create(struct net *net, const char *nodename)
 		.version		= NSM_VERSION,
 		.authflavor		= RPC_AUTH_NULL,
 		.flags			= RPC_CLNT_CREATE_NOPING,
+		.cred			= current_cred(),
 	};
 
 	return rpc_create(&args);

fs/nfs/client.c

@@ -284,6 +284,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 	struct nfs_client *clp;
 	const struct sockaddr *sap = data->addr;
 	struct nfs_net *nn = net_generic(data->net, nfs_net_id);
+	int error;
 
 again:
 	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
@@ -296,9 +297,11 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 		if (clp->cl_cons_state > NFS_CS_READY) {
 			refcount_inc(&clp->cl_count);
 			spin_unlock(&nn->nfs_client_lock);
-			nfs_wait_client_init_complete(clp);
+			error = nfs_wait_client_init_complete(clp);
 			nfs_put_client(clp);
 			spin_lock(&nn->nfs_client_lock);
+			if (error < 0)
+				return ERR_PTR(error);
 			goto again;
 		}
 
@@ -407,6 +410,8 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
 		clp = nfs_match_client(cl_init);
 		if (clp) {
 			spin_unlock(&nn->nfs_client_lock);
+			if (IS_ERR(clp))
+				return clp;
 			if (new)
 				new->rpc_ops->free_client(new);
 			return nfs_found_client(cl_init, clp);
@@ -500,6 +505,7 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 		.program	= &nfs_program,
 		.version	= clp->rpc_ops->version,
 		.authflavor	= flavor,
+		.cred		= cl_init->cred,
 	};
 
 	if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags))
@@ -598,6 +604,8 @@ int nfs_init_server_rpcclient(struct nfs_server *server,
 			sizeof(server->client->cl_timeout_default));
 	server->client->cl_timeout = &server->client->cl_timeout_default;
 	server->client->cl_softrtry = 0;
+	if (server->flags & NFS_MOUNT_SOFTERR)
+		server->client->cl_softerr = 1;
 	if (server->flags & NFS_MOUNT_SOFT)
 		server->client->cl_softrtry = 1;
 
@@ -652,6 +660,7 @@ static int nfs_init_server(struct nfs_server *server,
 		.proto = data->nfs_server.protocol,
 		.net = data->net,
 		.timeparms = &timeparms,
+		.cred = server->cred,
 	};
 	struct nfs_client *clp;
 	int error;
@@ -920,6 +929,7 @@ void nfs_free_server(struct nfs_server *server)
 	ida_destroy(&server->lockowner_id);
 	ida_destroy(&server->openowner_id);
 	nfs_free_iostats(server->io_stats);
+	put_cred(server->cred);
 	kfree(server);
 	nfs_release_automount_timer();
 }
@@ -940,6 +950,8 @@ struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info,
 	if (!server)
 		return ERR_PTR(-ENOMEM);
 
+	server->cred = get_cred(current_cred());
+
 	error = -ENOMEM;
 	fattr = nfs_alloc_fattr();
 	if (fattr == NULL)
@@ -1006,6 +1018,8 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	if (!server)
 		return ERR_PTR(-ENOMEM);
 
+	server->cred = get_cred(source->cred);
+
 	error = -ENOMEM;
 	fattr_fsinfo = nfs_alloc_fattr();
 	if (fattr_fsinfo == NULL)

fs/nfs/delegation.c

@@ -1033,6 +1033,18 @@ void nfs_mark_test_expired_all_delegations(struct nfs_client *clp)
 	rcu_read_unlock();
 }
 
+/**
+ * nfs_test_expired_all_delegations - test all delegations for a client
+ * @clp: nfs_client to process
+ *
+ * Helper for handling "recallable state revoked" status from server.
+ */
+void nfs_test_expired_all_delegations(struct nfs_client *clp)
+{
+	nfs_mark_test_expired_all_delegations(clp);
+	nfs4_schedule_state_manager(clp);
+}
+
 /**
  * nfs_reap_expired_delegations - reap expired delegations
  * @clp: nfs_client to process

fs/nfs/delegation.h

@@ -58,6 +58,7 @@ void nfs_delegation_mark_reclaim(struct nfs_client *clp);
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 
 void nfs_mark_test_expired_all_delegations(struct nfs_client *clp);
+void nfs_test_expired_all_delegations(struct nfs_client *clp);
 void nfs_reap_expired_delegations(struct nfs_client *clp);
 
 /* NFSv4 delegation-related procedures */

fs/nfs/dir.c

@@ -714,8 +714,9 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
  * We only need to convert from xdr once so future lookups are much simpler
  */
 static
-int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
+int nfs_readdir_filler(void *data, struct page* page)
 {
+	nfs_readdir_descriptor_t *desc = data;
 	struct inode	*inode = file_inode(desc->file);
 	int ret;
 
@@ -762,8 +763,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
 static
 struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
 {
-	return read_cache_page(desc->file->f_mapping,
-			desc->page_index, (filler_t *)nfs_readdir_filler, desc);
+	return read_cache_page(desc->file->f_mapping, desc->page_index,
+			nfs_readdir_filler, desc);
 }
 
 /*

fs/nfs/direct.c

@@ -492,7 +492,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 			struct nfs_page *req;
 			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
 			/* XXX do we need to do the eof zeroing found in async_filler? */
-			req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+			req = nfs_create_request(dreq->ctx, pagevec[i],
 						 pgbase, req_len);
 			if (IS_ERR(req)) {
 				result = PTR_ERR(req);
@@ -663,6 +663,8 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	}
 
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
+		/* Bump the transmission count */
+		req->wb_nio++;
 		if (!nfs_pageio_add_request(&desc, req)) {
 			nfs_list_move_request(req, &failed);
 			spin_lock(&cinfo.inode->i_lock);
@@ -703,6 +705,11 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 		req = nfs_list_entry(data->pages.next);
 		nfs_list_remove_request(req);
 		if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
+			/*
+			 * Despite the reboot, the write was successful,
+			 * so reset wb_nio.
+			 */
+			req->wb_nio = 0;
 			/* Note the rewrite will go through mds */
 			nfs_mark_request_commit(req, NULL, &cinfo, 0);
 		} else
@@ -899,7 +906,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			struct nfs_page *req;
 			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
 
-			req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+			req = nfs_create_request(dreq->ctx, pagevec[i],
 						 pgbase, req_len);
 			if (IS_ERR(req)) {
 				result = PTR_ERR(req);

fs/nfs/file.c

@@ -147,7 +147,7 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 		return 0;
 
 	/* Flush writes to the server and return any errors */
-	return vfs_fsync(file, 0);
+	return nfs_wb_all(inode);
 }
 
 ssize_t
@@ -199,13 +199,6 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap);
  * Flush any dirty pages for this process, and check for write errors.
  * The return status from this call provides a reliable indication of
  * whether any write errors occurred for this process.
- *
- * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
- * disk, but it retrieves and clears ctx->error after synching, despite
- * the two being set at the same time in nfs_context_set_write_error().
- * This is because the former is used to notify the _next_ call to
- * nfs_file_write() that a write error occurred, and hence cause it to
- * fall back to doing a synchronous write.
  */
 static int
 nfs_file_fsync_commit(struct file *file, int datasync)
@@ -220,11 +213,8 @@ nfs_file_fsync_commit(struct file *file, int datasync)
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
-	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) {
-		ret = xchg(&ctx->error, 0);
-		if (ret)
-			goto out;
-	}
+	if (status == 0)
+		status = file_check_and_advance_wb_err(file);
 	if (status < 0) {
 		ret = status;
 		goto out;
@@ -245,13 +235,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	trace_nfs_fsync_enter(inode);
 
 	do {
-		struct nfs_open_context *ctx = nfs_file_open_context(file);
-		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-		if (test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) {
-			int ret2 = xchg(&ctx->error, 0);
-			if (ret2)
-				ret = ret2;
-		}
+		ret = file_write_and_wait_range(file, start, end);
 		if (ret != 0)
 			break;
 		ret = nfs_file_fsync_commit(file, datasync);
@@ -600,8 +584,7 @@ static int nfs_need_check_write(struct file *filp, struct inode *inode)
 	struct nfs_open_context *ctx;
 
 	ctx = nfs_file_open_context(filp);
-	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) ||
-	    nfs_ctx_key_to_expire(ctx, inode))
+	if (nfs_ctx_key_to_expire(ctx, inode))
 		return 1;
 	return 0;
 }
@@ -655,7 +638,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 
 	/* Return error values */
 	if (nfs_need_check_write(file, inode)) {
-		int err = vfs_fsync(file, 0);
+		int err = nfs_wb_all(inode);
 		if (err < 0)
 			result = err;
 	}
@@ -709,7 +692,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * Flush all pending writes before doing anything
 	 * with locks..
 	 */
-	vfs_fsync(filp, 0);
+	nfs_wb_all(inode);
 
 	l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
 	if (!IS_ERR(l_ctx)) {

fs/nfs/filelayout/filelayout.c

@@ -904,7 +904,7 @@ fl_pnfs_update_layout(struct inode *ino,
 	status = filelayout_check_deviceid(lo, fl, gfp_flags);
 	if (status) {
 		pnfs_put_lseg(lseg);
-		lseg = ERR_PTR(status);
+		lseg = NULL;
 	}
 out:
 	return lseg;
@@ -917,7 +917,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	pnfs_generic_pg_check_layout(pgio);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
-						      req->wb_context,
+						      nfs_req_openctx(req),
 						      0,
 						      NFS4_MAX_UINT64,
 						      IOMODE_READ,
@@ -944,7 +944,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	pnfs_generic_pg_check_layout(pgio);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
-						      req->wb_context,
+						      nfs_req_openctx(req),
 						      0,
 						      NFS4_MAX_UINT64,
 						      IOMODE_RW,