Merge tag 'nfs-for-4.8-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable bugfixes:
   - nfs: don't create zero-length requests

   - several LAYOUTGET bugfixes

  Features:
   - several performance related features

   - more aggressive caching when we can rely on close-to-open
     cache consistency

   - remove serialisation of O_DIRECT reads and writes

   - optimise several code paths to not flush to disk unnecessarily.

     However allow for the idiosyncracies of pNFS for those layout
     types that need to issue a LAYOUTCOMMIT before the metadata can
     be updated on the server.

   - SUNRPC updates to the client data receive path

   - pNFS/SCSI support RH/Fedora dm-mpath device nodes

   - pNFS files/flexfiles can now use unprivileged ports when
     the generic NFS mount options allow it.

  Bugfixes:
   - Don't use RDMA direct data placement together with data
     integrity or privacy security flavours

   - Remove the RDMA ALLPHYSICAL memory registration mode as
     it has potential security holes.

   - Several layout recall fixes to improve NFSv4.1 protocol
     compliance.

   - Fix an Oops in the pNFS files and flexfiles connection
     setup to the DS

   - Allow retry of operations that used a returned delegation
      stateid

   - Don't mark the inode as revalidated if a LAYOUTCOMMIT is
     outstanding

   - Fix writeback races in nfs4_copy_range() and
     nfs42_proc_deallocate()"

* tag 'nfs-for-4.8-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (104 commits)
  pNFS: Actively set attributes as invalid if LAYOUTCOMMIT is outstanding
  NFSv4: Clean up lookup of SECINFO_NO_NAME
  NFSv4.2: Fix warning "variable ‘stateids’ set but not used"
  NFSv4: Fix warning "no previous prototype for ‘nfs4_listxattr’"
  SUNRPC: Fix a compiler warning in fs/nfs/clnt.c
  pNFS: Remove redundant smp_mb() from pnfs_init_lseg()
  pNFS: Cleanup - do layout segment initialisation in one place
  pNFS: Remove redundant stateid invalidation
  pNFS: Remove redundant pnfs_mark_layout_returned_if_empty()
  pNFS: Clear the layout metadata if the server changed the layout stateid
  pNFS: Cleanup - don't open code pnfs_mark_layout_stateid_invalid()
  NFS: pnfs_mark_matching_lsegs_return() should match the layout sequence id
  pNFS: Do not set plh_return_seq for non-callback related layoutreturns
  pNFS: Ensure layoutreturn acts as a completion for layout callbacks
  pNFS: Fix CB_LAYOUTRECALL stateid verification
  pNFS: Always update the layout barrier seqid on LAYOUTGET
  pNFS: Always update the layout stateid if NFS_LAYOUT_INVALID_STID is set
  pNFS: Clear the layout return tracking on layout reinitialisation
  pNFS: LAYOUTRETURN should only update the stateid if the layout is valid
  nfs: don't create zero-length requests
  ...

1 files changed, 80 insertions, 73 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ff416d0e24bc..da5c9e58e907 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -363,6 +363,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state *state = exception->state;
+	const nfs4_stateid *stateid = exception->stateid;
 	struct inode *inode = exception->inode;
 	int ret = errorcode;
 
@@ -376,9 +377,18 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (inode && nfs_async_inode_return_delegation(inode,
-						NULL) == 0)
-				goto wait_on_recovery;
+			if (inode) {
+				int err;
+
+				err = nfs_async_inode_return_delegation(inode,
+						stateid);
+				if (err == 0)
+					goto wait_on_recovery;
+				if (stateid != NULL && stateid->type == NFS4_DELEGATION_STATEID_TYPE) {
+					exception->retry = 1;
+					break;
+				}
+			}
 			if (state == NULL)
 				break;
 			ret = nfs4_schedule_stateid_recovery(server, state);
@@ -427,6 +437,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
 		case -NFS4ERR_GRACE:
+		case -NFS4ERR_LAYOUTTRYLATER:
 		case -NFS4ERR_RECALLCONFLICT:
 			exception->delay = 1;
 			return 0;
@@ -2669,28 +2680,17 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
 	return res;
 }
 
-static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
-			    struct nfs_fattr *fattr, struct iattr *sattr,
-			    struct nfs4_state *state, struct nfs4_label *ilabel,
-			    struct nfs4_label *olabel)
+static int _nfs4_do_setattr(struct inode *inode,
+			    struct nfs_setattrargs *arg,
+			    struct nfs_setattrres *res,
+			    struct rpc_cred *cred,
+			    struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-        struct nfs_setattrargs  arg = {
-                .fh             = NFS_FH(inode),
-                .iap            = sattr,
-		.server		= server,
-		.bitmask = server->attr_bitmask,
-		.label		= ilabel,
-        };
-        struct nfs_setattrres  res = {
-		.fattr		= fattr,
-		.label		= olabel,
-		.server		= server,
-        };
         struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
+		.rpc_argp	= arg,
+		.rpc_resp	= res,
 		.rpc_cred	= cred,
         };
 	struct rpc_cred *delegation_cred = NULL;
@@ -2699,17 +2699,13 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	bool truncate;
 	int status;
 
-	arg.bitmask = nfs4_bitmask(server, ilabel);
-	if (ilabel)
-		arg.bitmask = nfs4_bitmask(server, olabel);
-
-	nfs_fattr_init(fattr);
+	nfs_fattr_init(res->fattr);
 
 	/* Servers should only apply open mode checks for file size changes */
-	truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false;
+	truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false;
 	fmode = truncate ? FMODE_WRITE : FMODE_READ;
 
-	if (nfs4_copy_delegation_stateid(inode, fmode, &arg.stateid, &delegation_cred)) {
+	if (nfs4_copy_delegation_stateid(inode, fmode, &arg->stateid, &delegation_cred)) {
 		/* Use that stateid */
 	} else if (truncate && state != NULL) {
 		struct nfs_lockowner lockowner = {
@@ -2719,19 +2715,19 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 		if (!nfs4_valid_open_stateid(state))
 			return -EBADF;
 		if (nfs4_select_rw_stateid(state, FMODE_WRITE, &lockowner,
-				&arg.stateid, &delegation_cred) == -EIO)
+				&arg->stateid, &delegation_cred) == -EIO)
 			return -EBADF;
 	} else
-		nfs4_stateid_copy(&arg.stateid, &zero_stateid);
+		nfs4_stateid_copy(&arg->stateid, &zero_stateid);
 	if (delegation_cred)
 		msg.rpc_cred = delegation_cred;
 
-	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
+	status = nfs4_call_sync(server->client, server, &msg, &arg->seq_args, &res->seq_res, 1);
 
 	put_rpccred(delegation_cred);
 	if (status == 0 && state != NULL)
 		renew_lease(server, timestamp);
-	trace_nfs4_setattr(inode, &arg.stateid, status);
+	trace_nfs4_setattr(inode, &arg->stateid, status);
 	return status;
 }
 
@@ -2741,13 +2737,31 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 			   struct nfs4_label *olabel)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
+        struct nfs_setattrargs  arg = {
+                .fh             = NFS_FH(inode),
+                .iap            = sattr,
+		.server		= server,
+		.bitmask = server->attr_bitmask,
+		.label		= ilabel,
+        };
+        struct nfs_setattrres  res = {
+		.fattr		= fattr,
+		.label		= olabel,
+		.server		= server,
+        };
 	struct nfs4_exception exception = {
 		.state = state,
 		.inode = inode,
+		.stateid = &arg.stateid,
 	};
 	int err;
+
+	arg.bitmask = nfs4_bitmask(server, ilabel);
+	if (ilabel)
+		arg.bitmask = nfs4_bitmask(server, olabel);
+
 	do {
-		err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel);
+		err = _nfs4_do_setattr(inode, &arg, &res, cred, state);
 		switch (err) {
 		case -NFS4ERR_OPENMODE:
 			if (!(sattr->ia_valid & ATTR_SIZE)) {
@@ -3267,13 +3281,6 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	return status;
 }
 
-static int nfs4_do_find_root_sec(struct nfs_server *server,
-		struct nfs_fh *fhandle, struct nfs_fsinfo *info)
-{
-	int mv = server->nfs_client->cl_minorversion;
-	return nfs_v4_minor_ops[mv]->find_root_sec(server, fhandle, info);
-}
-
 /**
  * nfs4_proc_get_rootfh - get file handle for server's pseudoroot
  * @server: initialized nfs_server handle
@@ -3293,7 +3300,8 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
 		status = nfs4_lookup_root(server, fhandle, info);
 
 	if (auth_probe || status == NFS4ERR_WRONGSEC)
-		status = nfs4_do_find_root_sec(server, fhandle, info);
+		status = server->nfs_client->cl_mvops->find_root_sec(server,
+				fhandle, info);
 
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
@@ -4392,7 +4400,8 @@ static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	hdr->timestamp   = jiffies;
-	hdr->pgio_done_cb = nfs4_read_done_cb;
+	if (!hdr->pgio_done_cb)
+		hdr->pgio_done_cb = nfs4_read_done_cb;
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0);
 }
@@ -7869,11 +7878,13 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 	struct inode *inode = lgp->args.inode;
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
-	int status = task->tk_status;
+	int nfs4err = task->tk_status;
+	int err, status = 0;
+	LIST_HEAD(head);
 
 	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
-	switch (status) {
+	switch (nfs4err) {
 	case 0:
 		goto out;
 
@@ -7905,45 +7916,42 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 			status = -EOVERFLOW;
 			goto out;
 		}
-		/* Fallthrough */
+		status = -EBUSY;
+		break;
 	case -NFS4ERR_RECALLCONFLICT:
-		nfs4_handle_exception(server, -NFS4ERR_RECALLCONFLICT,
-					exception);
 		status = -ERECALLCONFLICT;
-		goto out;
+		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
 		exception->timeout = 0;
 		spin_lock(&inode->i_lock);
-		if (nfs4_stateid_match(&lgp->args.stateid,
+		lo = NFS_I(inode)->layout;
+		/* If the open stateid was bad, then recover it. */
+		if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) ||
+		    nfs4_stateid_match_other(&lgp->args.stateid,
 					&lgp->args.ctx->state->stateid)) {
 			spin_unlock(&inode->i_lock);
-			/* If the open stateid was bad, then recover it. */
 			exception->state = lgp->args.ctx->state;
 			break;
 		}
-		lo = NFS_I(inode)->layout;
-		if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) &&
-		    nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
-			LIST_HEAD(head);
-
-			/*
-			 * Mark the bad layout state as invalid, then retry
-			 * with the current stateid.
-			 */
-			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
-			spin_unlock(&inode->i_lock);
-			pnfs_free_lseg_list(&head);
-			status = -EAGAIN;
-			goto out;
-		} else
-			spin_unlock(&inode->i_lock);
-	}
 
-	status = nfs4_handle_exception(server, status, exception);
-	if (exception->retry)
+		/*
+		 * Mark the bad layout state as invalid, then retry
+		 */
+		pnfs_mark_layout_stateid_invalid(lo, &head);
+		spin_unlock(&inode->i_lock);
+		pnfs_free_lseg_list(&head);
 		status = -EAGAIN;
+		goto out;
+	}
+
+	err = nfs4_handle_exception(server, nfs4err, exception);
+	if (!status) {
+		if (exception->retry)
+			status = -EAGAIN;
+		else
+			status = err;
+	}
 out:
 	dprintk("<-- %s\n", __func__);
 	return status;
@@ -8129,8 +8137,7 @@ static void nfs4_layoutreturn_release(void *calldata)
 	spin_lock(&lo->plh_inode->i_lock);
 	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
 			be32_to_cpu(lrp->args.stateid.seqid));
-	pnfs_mark_layout_returned_if_empty(lo);
-	if (lrp->res.lrs_present)
+	if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
 	pnfs_clear_layoutreturn_waitbit(lo);
 	spin_unlock(&lo->plh_inode->i_lock);
@@ -8835,7 +8842,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 #endif
 };
 
-ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
+static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
 	ssize_t error, error2;