1 files changed, 120 insertions, 62 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 00435556db0c..ba4a03a69fbf 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -359,6 +359,14 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 	kunmap_atomic(start);
 }
 
+static void nfs4_fattr_set_prechange(struct nfs_fattr *fattr, u64 version)
+{
+	if (!(fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) {
+		fattr->pre_change_attr = version;
+		fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
+	}
+}
+
 static void nfs4_test_and_free_stateid(struct nfs_server *server,
 		nfs4_stateid *stateid,
 		const struct cred *cred)
@@ -581,6 +589,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
 		goto out_retry;
 	}
 	if (exception->recovering) {
+		if (exception->task_is_privileged)
+			return -EDEADLOCK;
 		ret = nfs4_wait_clnt_recover(clp);
 		if (test_bit(NFS_MIG_FAILED, &server->mig_status))
 			return -EIO;
@@ -606,6 +616,8 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
 		goto out_retry;
 	}
 	if (exception->recovering) {
+		if (exception->task_is_privileged)
+			return -EDEADLOCK;
 		rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
 		if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
 			rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
@@ -1515,19 +1527,6 @@ static void nfs_state_log_update_open_stateid(struct nfs4_state *state)
 		wake_up_all(&state->waitq);
 }
 
-static void nfs_state_log_out_of_order_open_stateid(struct nfs4_state *state,
-		const nfs4_stateid *stateid)
-{
-	u32 state_seqid = be32_to_cpu(state->open_stateid.seqid);
-	u32 stateid_seqid = be32_to_cpu(stateid->seqid);
-
-	if (stateid_seqid == state_seqid + 1U ||
-	    (stateid_seqid == 1U && state_seqid == 0xffffffffU))
-		nfs_state_log_update_open_stateid(state);
-	else
-		set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
-}
-
 static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
 {
 	struct nfs_client *clp = state->owner->so_server->nfs_client;
@@ -1553,22 +1552,21 @@ static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
  * i.e. The stateid seqids have to be initialised to 1, and
  * are then incremented on every state transition.
  */
-static bool nfs_need_update_open_stateid(struct nfs4_state *state,
+static bool nfs_stateid_is_sequential(struct nfs4_state *state,
 		const nfs4_stateid *stateid)
 {
-	if (test_bit(NFS_OPEN_STATE, &state->flags) == 0 ||
-	    !nfs4_stateid_match_other(stateid, &state->open_stateid)) {
-		if (stateid->seqid == cpu_to_be32(1))
-			nfs_state_log_update_open_stateid(state);
-		else
-			set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
-		return true;
+	if (test_bit(NFS_OPEN_STATE, &state->flags)) {
+		/* The common case - we're updating to a new sequence number */
+		if (nfs4_stateid_match_other(stateid, &state->open_stateid)) {
+			if (nfs4_stateid_is_next(&state->open_stateid, stateid))
+				return true;
+			return false;
+		}
+		/* The server returned a new stateid */
 	}
-
-	if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) {
-		nfs_state_log_out_of_order_open_stateid(state, stateid);
+	/* This is the first OPEN in this generation */
+	if (stateid->seqid == cpu_to_be32(1))
 		return true;
-	}
 	return false;
 }
 
@@ -1641,16 +1639,16 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state,
 	int status = 0;
 	for (;;) {
 
-		if (!nfs_need_update_open_stateid(state, stateid))
-			return;
-		if (!test_bit(NFS_STATE_CHANGE_WAIT, &state->flags))
+		if (nfs_stateid_is_sequential(state, stateid))
 			break;
+
 		if (status)
 			break;
 		/* Rely on seqids for serialisation with NFSv4.0 */
 		if (!nfs4_has_session(NFS_SERVER(state->inode)->nfs_client))
 			break;
 
+		set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
 		prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE);
 		/*
 		 * Ensure we process the state changes in the same order
@@ -1661,7 +1659,8 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state,
 		spin_unlock(&state->owner->so_lock);
 		rcu_read_unlock();
 		trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0);
-		if (!signal_pending(current)) {
+
+		if (!fatal_signal_pending(current)) {
 			if (schedule_timeout(5*HZ) == 0)
 				status = -EAGAIN;
 			else
@@ -3042,6 +3041,10 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	}
 
 out:
+	if (opendata->lgp) {
+		nfs4_lgopen_release(opendata->lgp);
+		opendata->lgp = NULL;
+	}
 	if (!opendata->cancelled)
 		nfs4_sequence_free_slot(&opendata->o_res.seq_res);
 	return ret;
@@ -3397,7 +3400,8 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst,
 	__be32 seqid_open;
 	u32 dst_seqid;
 	bool ret;
-	int seq;
+	int seq, status = -EAGAIN;
+	DEFINE_WAIT(wait);
 
 	for (;;) {
 		ret = false;
@@ -3409,15 +3413,41 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst,
 				continue;
 			break;
 		}
+
+		write_seqlock(&state->seqlock);
 		seqid_open = state->open_stateid.seqid;
-		if (read_seqretry(&state->seqlock, seq))
-			continue;
 
 		dst_seqid = be32_to_cpu(dst->seqid);
-		if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) >= 0)
-			dst->seqid = cpu_to_be32(dst_seqid + 1);
-		else
+
+		/* Did another OPEN bump the state's seqid?  try again: */
+		if ((s32)(be32_to_cpu(seqid_open) - dst_seqid) > 0) {
 			dst->seqid = seqid_open;
+			write_sequnlock(&state->seqlock);
+			ret = true;
+			break;
+		}
+
+		/* server says we're behind but we haven't seen the update yet */
+		set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
+		prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE);
+		write_sequnlock(&state->seqlock);
+		trace_nfs4_close_stateid_update_wait(state->inode, dst, 0);
+
+		if (fatal_signal_pending(current))
+			status = -EINTR;
+		else
+			if (schedule_timeout(5*HZ) != 0)
+				status = 0;
+
+		finish_wait(&state->waitq, &wait);
+
+		if (!status)
+			continue;
+		if (status == -EINTR)
+			break;
+
+		/* we slept the whole 5 seconds, we must have lost a seqid */
+		dst->seqid = cpu_to_be32(dst_seqid + 1);
 		ret = true;
 		break;
 	}
@@ -3475,10 +3505,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
 
 	/* Handle Layoutreturn errors */
-	if (pnfs_roc_done(task, calldata->inode,
-				&calldata->arg.lr_args,
-				&calldata->res.lr_res,
-				&calldata->res.lr_ret) == -EAGAIN)
+	if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res,
+			  &calldata->res.lr_ret) == -EAGAIN)
 		goto out_restart;
 
 	/* hmm. we are done with the inode, and in the process of freeing
@@ -4886,12 +4914,12 @@ static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
 		u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
+	struct nfs_server	*server = NFS_SERVER(dir);
 	struct nfs4_readdir_arg args = {
 		.fh = NFS_FH(dir),
 		.pages = pages,
 		.pgbase = 0,
 		.count = count,
-		.bitmask = NFS_SERVER(d_inode(dentry))->attr_bitmask,
 		.plus = plus,
 	};
 	struct nfs4_readdir_res res;
@@ -4906,9 +4934,15 @@ static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
 	dprintk("%s: dentry = %pd2, cookie = %Lu\n", __func__,
 			dentry,
 			(unsigned long long)cookie);
+	if (!(server->caps & NFS_CAP_SECURITY_LABEL))
+		args.bitmask = server->attr_bitmask_nl;
+	else
+		args.bitmask = server->attr_bitmask;
+
 	nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args);
 	res.pgbase = args.pgbase;
-	status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0);
+	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
+			&res.seq_res, 0);
 	if (status >= 0) {
 		memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE);
 		status += args.pgbase;
@@ -5737,6 +5771,9 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
 	int ret, i;
 
+	/* You can't remove system.nfs4_acl: */
+	if (buflen == 0)
+		return -EINVAL;
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
 	if (npages > ARRAY_SIZE(pages))
@@ -5775,6 +5812,14 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen
 	do {
 		err = __nfs4_proc_set_acl(inode, buf, buflen);
 		trace_nfs4_set_acl(inode, err);
+		if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
+			/*
+			 * no need to retry since the kernel
+			 * isn't involved in encoding the ACEs.
+			 */
+			err = -EINVAL;
+			break;
+		}
 		err = nfs4_handle_exception(NFS_SERVER(inode), err,
 				&exception);
 	} while (exception.retry);
@@ -5813,7 +5858,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 		return ret;
 	if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
 		return -ENOENT;
-	return 0;
+	return label.len;
 }
 
 static int nfs4_get_security_label(struct inode *inode, void *buf,
@@ -6211,6 +6256,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 	struct nfs4_exception exception = {
 		.inode = data->inode,
 		.stateid = &data->stateid,
+		.task_is_privileged = data->args.seq_args.sa_privileged,
 	};
 
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
@@ -6219,10 +6265,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 	trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
 
 	/* Handle Layoutreturn errors */
-	if (pnfs_roc_done(task, data->inode,
-				&data->args.lr_args,
-				&data->res.lr_res,
-				&data->res.lr_ret) == -EAGAIN)
+	if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res,
+			  &data->res.lr_ret) == -EAGAIN)
 		goto out_restart;
 
 	switch (task->tk_status) {
@@ -6271,11 +6315,13 @@ static void nfs4_delegreturn_release(void *calldata)
 	struct nfs4_delegreturndata *data = calldata;
 	struct inode *inode = data->inode;
 
+	if (data->lr.roc)
+		pnfs_roc_release(&data->lr.arg, &data->lr.res,
+				 data->res.lr_ret);
 	if (inode) {
-		if (data->lr.roc)
-			pnfs_roc_release(&data->lr.arg, &data->lr.res,
-					data->res.lr_ret);
-		nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
+		nfs4_fattr_set_prechange(&data->fattr,
+					 inode_peek_iversion_raw(inode));
+		nfs_refresh_inode(inode, &data->fattr);
 		nfs_iput_and_deactive(inode);
 	}
 	kfree(calldata);
@@ -6331,7 +6377,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	data = kzalloc(sizeof(*data), GFP_NOFS);
 	if (data == NULL)
 		return -ENOMEM;
-	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0);
 
 	nfs4_state_protect(server->nfs_client,
 			NFS_SP4_MACH_CRED_CLEANUP,
@@ -6349,18 +6394,22 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	nfs_fattr_init(data->res.fattr);
 	data->timestamp = jiffies;
 	data->rpc_status = 0;
-	data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred);
 	data->inode = nfs_igrab_and_active(inode);
-	if (data->inode) {
+	if (data->inode || issync) {
+		data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res,
+					cred);
 		if (data->lr.roc) {
 			data->args.lr_args = &data->lr.arg;
 			data->res.lr_res = &data->lr.res;
 		}
-	} else if (data->lr.roc) {
-		pnfs_roc_release(&data->lr.arg, &data->lr.res, 0);
-		data->lr.roc = false;
 	}
 
+	if (!data->inode)
+		nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+				   1);
+	else
+		nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+				   0);
 	task_setup_data.callback_data = data;
 	msg.rpc_argp = &data->args;
 	msg.rpc_resp = &data->res;
@@ -6940,9 +6989,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 					data->arg.new_lock_owner, ret);
 	} else
 		data->cancelled = true;
+	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
 	rpc_put_task(task);
 	dprintk("%s: done, ret = %d!\n", __func__, ret);
-	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
 	return ret;
 }
 
@@ -7846,9 +7895,11 @@ int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
  * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or
  * DS flags set.
  */
-static int nfs4_check_cl_exchange_flags(u32 flags)
+static int nfs4_check_cl_exchange_flags(u32 flags, u32 version)
 {
-	if (flags & ~EXCHGID4_FLAG_MASK_R)
+	if (version >= 2 && (flags & ~EXCHGID4_2_FLAG_MASK_R))
+		goto out_inval;
+	else if (version < 2 && (flags & ~EXCHGID4_FLAG_MASK_R))
 		goto out_inval;
 	if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) &&
 	    (flags & EXCHGID4_FLAG_USE_NON_PNFS))
@@ -7881,6 +7932,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 	case -NFS4ERR_DEADSESSION:
 		nfs4_schedule_session_recovery(clp->cl_session,
 				task->tk_status);
+		return;
 	}
 	if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
 			res->dir != NFS4_CDFS4_BOTH) {
@@ -8261,7 +8313,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
 	if (status  != 0)
 		goto out;
 
-	status = nfs4_check_cl_exchange_flags(resp->flags);
+	status = nfs4_check_cl_exchange_flags(resp->flags,
+			clp->cl_mvops->minor_version);
 	if (status  != 0)
 		goto out;
 
@@ -9313,15 +9366,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
 			&task_setup_data.rpc_client, &msg);
 
 	dprintk("--> %s\n", __func__);
+	lrp->inode = nfs_igrab_and_active(lrp->args.inode);
 	if (!sync) {
-		lrp->inode = nfs_igrab_and_active(lrp->args.inode);
 		if (!lrp->inode) {
 			nfs4_layoutreturn_release(lrp);
 			return -EAGAIN;
 		}
 		task_setup_data.flags |= RPC_TASK_ASYNC;
 	}
-	nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0);
+	if (!lrp->inode)
+		nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1,
+				   1);
+	else
+		nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1,
+				   0);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);