Merge tag 'nfs-for-3.18-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

   - stable patches to fix NFSv4.x delegation reclaim error paths
   - fix a bug whereby we were advertising NFSv4.1 but using NFSv4.2
     features
   - fix a use-after-free problem with pNFS block layouts
   - fix a memory leak in the pNFS files O_DIRECT code
   - replace an intrusive and Oops-prone performance fix in the NFSv4
     atomic open code with a safer one-line version and revert the two
     original patches"

* tag 'nfs-for-3.18-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  sunrpc: fix sleeping under rcu_read_lock in gss_stringify_acceptor
  NFS: Don't try to reclaim delegation open state if recovery failed
  NFSv4: Ensure that we call FREE_STATEID when NFSv4.x stateids are revoked
  NFSv4: Fix races between nfs_remove_bad_delegation() and delegation return
  NFSv4.1: nfs41_clear_delegation_stateid shouldn't trust NFS_DELEGATED_STATE
  NFSv4: Ensure that we remove NFSv4.0 delegations when state has expired
  NFS: SEEK is an NFS v4.2 feature
  nfs: Fix use of uninitialized variable in nfs_getattr()
  nfs: Remove bogus assignment
  nfs: remove spurious WARN_ON_ONCE in write path
  pnfs/blocklayout: serialize GETDEVICEINFO calls
  nfs: fix pnfs direct write memory leak
  Revert "NFS: nfs4_do_open should add negative results to the dcache."
  Revert "NFS: remove BUG possibility in nfs4_open_and_get_state"
  NFSv4: Ensure nfs_atomic_open set the dentry verifier on ENOENT

13 files changed, 124 insertions, 69 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 5228f201d3d5..4f46f7a05289 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -378,7 +378,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 	loff_t offset = header->args.offset;
 	size_t count = header->args.count;
 	struct page **pages = header->args.pages;
-	int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+	int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
 	unsigned int pg_len;
 	struct blk_plug plug;
 	int i;
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index e966c023b1b7..acbf9ca4018c 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -65,17 +65,18 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 
 	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
 
+	mutex_lock(&nn->bl_mutex);
 	bl_pipe_msg.bl_wq = &nn->bl_wq;
 
 	b->simple.len += 4;	/* single volume */
 	if (b->simple.len > PAGE_SIZE)
-		return -EIO;
+		goto out_unlock;
 
 	memset(msg, 0, sizeof(*msg));
 	msg->len = sizeof(*bl_msg) + b->simple.len;
 	msg->data = kzalloc(msg->len, gfp_mask);
 	if (!msg->data)
-		goto out;
+		goto out_free_data;
 
 	bl_msg = msg->data;
 	bl_msg->type = BL_DEVICE_MOUNT,
@@ -87,7 +88,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 	rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
 	if (rc < 0) {
 		remove_wait_queue(&nn->bl_wq, &wq);
-		goto out;
+		goto out_free_data;
 	}
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
@@ -97,12 +98,14 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 	if (reply->status != BL_DEVICE_REQUEST_PROC) {
 		printk(KERN_WARNING "%s failed to decode device: %d\n",
 			__func__, reply->status);
-		goto out;
+		goto out_free_data;
 	}
 
 	dev = MKDEV(reply->major, reply->minor);
-out:
+out_free_data:
 	kfree(msg->data);
+out_unlock:
+	mutex_unlock(&nn->bl_mutex);
 	return dev;
 }
 
@@ -232,6 +235,7 @@ static int nfs4blocklayout_net_init(struct net *net)
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	struct dentry *dentry;
 
+	mutex_init(&nn->bl_mutex);
 	init_waitqueue_head(&nn->bl_wq);
 	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
 	if (IS_ERR(nn->bl_device_pipe))
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5853f53db732..7f3f60641344 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -125,6 +125,8 @@ again:
 			continue;
 		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
 			continue;
+		if (!nfs4_valid_open_stateid(state))
+			continue;
 		if (!nfs4_stateid_match(&state->stateid, stateid))
 			continue;
 		get_nfs_open_context(ctx);
@@ -193,7 +195,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
 {
 	int res = 0;
 
-	res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+		res = nfs4_proc_delegreturn(inode,
+				delegation->cred,
+				&delegation->stateid,
+				issync);
 	nfs_free_delegation(delegation);
 	return res;
 }
@@ -380,11 +386,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	int err;
+	int err = 0;
 
 	if (delegation == NULL)
 		return 0;
 	do {
+		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+			break;
 		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
 		if (!issync || err != -EAGAIN)
 			break;
@@ -605,10 +613,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl
 	rcu_read_unlock();
 }
 
+static void nfs_revoke_delegation(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation != NULL) {
+		set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+		nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+	}
+	rcu_read_unlock();
+}
+
 void nfs_remove_bad_delegation(struct inode *inode)
 {
 	struct nfs_delegation *delegation;
 
+	nfs_revoke_delegation(inode);
 	delegation = nfs_inode_detach_delegation(inode);
 	if (delegation) {
 		nfs_inode_find_state_and_recover(inode, &delegation->stateid);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 5c1cce39297f..e3c20a3ccc93 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@ enum {
 	NFS_DELEGATION_RETURN_IF_CLOSED,
 	NFS_DELEGATION_REFERENCED,
 	NFS_DELEGATION_RETURNING,
+	NFS_DELEGATION_REVOKED,
 };
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 06e8cfcbb670..6e62155abf26 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1527,6 +1527,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		case -ENOENT:
 			d_drop(dentry);
 			d_add(dentry, NULL);
+			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			break;
 		case -EISDIR:
 		case -ENOTDIR:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 20cffc830468..10bf07280f4a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -266,6 +266,7 @@ static void nfs_direct_req_free(struct kref *kref)
 {
 	struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
 
+	nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
 	if (dreq->l_ctx != NULL)
 		nfs_put_lock_context(dreq->l_ctx);
 	if (dreq->ctx != NULL)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 46fab1cb455a..7afb52f6a25a 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -145,9 +145,6 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -NFS4ERR_DELEG_REVOKED:
 	case -NFS4ERR_ADMIN_REVOKED:
 	case -NFS4ERR_BAD_STATEID:
-		if (state == NULL)
-			break;
-		nfs_remove_bad_delegation(state->inode);
 	case -NFS4ERR_OPENMODE:
 		if (state == NULL)
 			break;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 6388a59f2add..00689a8a85e4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -626,7 +626,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
-	int err;
+	int err = 0;
 
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index ef221fb8a183..f0e06e4acbef 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -19,6 +19,7 @@ struct nfs_net {
 	struct rpc_pipe *bl_device_pipe;
 	struct bl_dev_msg bl_mount_reply;
 	wait_queue_head_t bl_wq;
+	struct mutex bl_mutex;
 	struct list_head nfs_client_list;
 	struct list_head nfs_volume_list;
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 405bd95c1f58..69dc20a743f9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -370,11 +370,6 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (inode != NULL && nfs4_have_delegation(inode, FMODE_READ)) {
-				nfs_remove_bad_delegation(inode);
-				exception->retry = 1;
-				break;
-			}
 			if (state == NULL)
 				break;
 			ret = nfs4_schedule_stateid_recovery(server, state);
@@ -1654,7 +1649,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 			nfs_inode_find_state_and_recover(state->inode,
 					stateid);
 			nfs4_schedule_stateid_recovery(server, state);
-			return 0;
+			return -EAGAIN;
 		case -NFS4ERR_DELAY:
 		case -NFS4ERR_GRACE:
 			set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -2109,46 +2104,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+	nfs_remove_bad_delegation(state->inode);
+	write_seqlock(&state->seqlock);
+	nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+	write_sequnlock(&state->seqlock);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+	if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+		nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	/* NFSv4.0 doesn't allow for delegation recovery on open expire */
+	nfs40_clear_delegation_stateid(state);
+	return nfs4_open_expired(sp, state);
+}
+
 #if defined(CONFIG_NFS_V4_1)
-static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
+static void nfs41_check_delegation_stateid(struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
-	nfs4_stateid *stateid = &state->stateid;
+	nfs4_stateid stateid;
 	struct nfs_delegation *delegation;
-	struct rpc_cred *cred = NULL;
-	int status = -NFS4ERR_BAD_STATEID;
-
-	/* If a state reset has been done, test_stateid is unneeded */
-	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
-		return;
+	struct rpc_cred *cred;
+	int status;
 
 	/* Get the delegation credential for use by test/free_stateid */
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(state->inode)->delegation);
-	if (delegation != NULL &&
-	    nfs4_stateid_match(&delegation->stateid, stateid)) {
-		cred = get_rpccred(delegation->cred);
-		rcu_read_unlock();
-		status = nfs41_test_stateid(server, stateid, cred);
-		trace_nfs4_test_delegation_stateid(state, NULL, status);
-	} else
+	if (delegation == NULL) {
 		rcu_read_unlock();
+		return;
+	}
+
+	nfs4_stateid_copy(&stateid, &delegation->stateid);
+	cred = get_rpccred(delegation->cred);
+	rcu_read_unlock();
+	status = nfs41_test_stateid(server, &stateid, cred);
+	trace_nfs4_test_delegation_stateid(state, NULL, status);
 
 	if (status != NFS_OK) {
 		/* Free the stateid unless the server explicitly
 		 * informs us the stateid is unrecognized. */
 		if (status != -NFS4ERR_BAD_STATEID)
-			nfs41_free_stateid(server, stateid, cred);
-		nfs_remove_bad_delegation(state->inode);
-
-		write_seqlock(&state->seqlock);
-		nfs4_stateid_copy(&state->stateid, &state->open_stateid);
-		write_sequnlock(&state->seqlock);
-		clear_bit(NFS_DELEGATED_STATE, &state->flags);
+			nfs41_free_stateid(server, &stateid, cred);
+		nfs_finish_clear_delegation_stateid(state);
 	}
 
-	if (cred != NULL)
-		put_rpccred(cred);
+	put_rpccred(cred);
 }
 
 /**
@@ -2192,7 +2201,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st
 {
 	int status;
 
-	nfs41_clear_delegation_stateid(state);
+	nfs41_check_delegation_stateid(state);
 	status = nfs41_check_open_stateid(state);
 	if (status != NFS_OK)
 		status = nfs4_open_expired(sp, state);
@@ -2231,19 +2240,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
 
 	ret = _nfs4_proc_open(opendata);
-	if (ret != 0) {
-		if (ret == -ENOENT) {
-			dentry = opendata->dentry;
-			if (dentry->d_inode)
-				d_delete(dentry);
-			else if (d_unhashed(dentry))
-				d_add(dentry, NULL);
-
-			nfs_set_verifier(dentry,
-					 nfs_save_change_attribute(opendata->dir->d_inode));
-		}
+	if (ret != 0)
 		goto out;
-	}
 
 	state = nfs4_opendata_to_nfs4_state(opendata);
 	ret = PTR_ERR(state);
@@ -4841,9 +4839,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (state == NULL)
-				break;
-			nfs_remove_bad_delegation(state->inode);
 		case -NFS4ERR_OPENMODE:
 			if (state == NULL)
 				break;
@@ -8341,7 +8336,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
-	.recover_open	= nfs4_open_expired,
+	.recover_open	= nfs40_open_expired,
 	.recover_lock	= nfs4_lock_expired,
 	.establish_clid = nfs4_init_clientid,
 };
@@ -8408,8 +8403,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
-		| NFS_CAP_ATOMIC_OPEN_V1
-		| NFS_CAP_SEEK,
+		| NFS_CAP_ATOMIC_OPEN_V1,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
@@ -8431,7 +8425,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
-		| NFS_CAP_ATOMIC_OPEN_V1,
+		| NFS_CAP_ATOMIC_OPEN_V1
+		| NFS_CAP_SEEK,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 12493846a2d3..f83b02dc9166 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -715,8 +715,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 
 	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
 		nfs_release_request(req);
-	else
-		WARN_ON_ONCE(1);
 }
 
 static void
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 983876f24aed..47ebb4fafd87 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1224,11 +1224,22 @@ struct nfs41_free_stateid_res {
 	unsigned int			status;
 };
 
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+	kfree(cinfo->buckets);
+}
+
 #else
 
 struct pnfs_ds_commit_info {
 };
 
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #ifdef CONFIG_NFS_V4_2
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index afb292cd797d..53ed8d3f8897 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1353,6 +1353,7 @@ gss_stringify_acceptor(struct rpc_cred *cred)
 	char *string = NULL;
 	struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base);
 	struct gss_cl_ctx *ctx;
+	unsigned int len;
 	struct xdr_netobj *acceptor;
 
 	rcu_read_lock();
@@ -1360,15 +1361,39 @@ gss_stringify_acceptor(struct rpc_cred *cred)
 	if (!ctx)
 		goto out;
 
-	acceptor = &ctx->gc_acceptor;
+	len = ctx->gc_acceptor.len;
+	rcu_read_unlock();
 
 	/* no point if there's no string */
-	if (!acceptor->len)
-		goto out;
-
-	string = kmalloc(acceptor->len + 1, GFP_KERNEL);
+	if (!len)
+		return NULL;
+realloc:
+	string = kmalloc(len + 1, GFP_KERNEL);
 	if (!string)
+		return NULL;
+
+	rcu_read_lock();
+	ctx = rcu_dereference(gss_cred->gc_ctx);
+
+	/* did the ctx disappear or was it replaced by one with no acceptor? */
+	if (!ctx || !ctx->gc_acceptor.len) {
+		kfree(string);
+		string = NULL;
 		goto out;
+	}
+
+	acceptor = &ctx->gc_acceptor;
+
+	/*
+	 * Did we find a new acceptor that's longer than the original? Allocate
+	 * a longer buffer and try again.
+	 */
+	if (len < acceptor->len) {
+		len = acceptor->len;
+		rcu_read_unlock();
+		kfree(string);
+		goto realloc;
+	}
 
 	memcpy(string, acceptor->data, acceptor->len);
 	string[acceptor->len] = '\0';