1 files changed, 179 insertions, 81 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4435e5e1f904..1ff76acc7e98 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -49,6 +49,9 @@
 #include <linux/mount.h>
 #include <linux/module.h>
 #include <linux/sunrpc/bc_xprt.h>
+#include <linux/xattr.h>
+#include <linux/utsname.h>
+#include <linux/mm.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -355,9 +358,9 @@ nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *free_slot)
 }
 
 /*
- * Signal state manager thread if session is drained
+ * Signal state manager thread if session fore channel is drained
  */
-static void nfs41_check_drain_session_complete(struct nfs4_session *ses)
+static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
 {
 	struct rpc_task *task;
 
@@ -371,8 +374,20 @@ static void nfs41_check_drain_session_complete(struct nfs4_session *ses)
 	if (ses->fc_slot_table.highest_used_slotid != -1)
 		return;
 
-	dprintk("%s COMPLETE: Session Drained\n", __func__);
-	complete(&ses->complete);
+	dprintk("%s COMPLETE: Session Fore Channel Drained\n", __func__);
+	complete(&ses->fc_slot_table.complete);
+}
+
+/*
+ * Signal state manager thread if session back channel is drained
+ */
+void nfs4_check_drain_bc_complete(struct nfs4_session *ses)
+{
+	if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state) ||
+	    ses->bc_slot_table.highest_used_slotid != -1)
+		return;
+	dprintk("%s COMPLETE: Session Back Channel Drained\n", __func__);
+	complete(&ses->bc_slot_table.complete);
 }
 
 static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
@@ -389,7 +404,7 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 
 	spin_lock(&tbl->slot_tbl_lock);
 	nfs4_free_slot(tbl, res->sr_slot);
-	nfs41_check_drain_session_complete(res->sr_session);
+	nfs4_check_drain_fc_complete(res->sr_session);
 	spin_unlock(&tbl->slot_tbl_lock);
 	res->sr_slot = NULL;
 }
@@ -1826,6 +1841,8 @@ struct nfs4_closedata {
 	struct nfs_closeres res;
 	struct nfs_fattr fattr;
 	unsigned long timestamp;
+	bool roc;
+	u32 roc_barrier;
 };
 
 static void nfs4_free_closedata(void *data)
@@ -1833,6 +1850,8 @@ static void nfs4_free_closedata(void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state_owner *sp = calldata->state->owner;
 
+	if (calldata->roc)
+		pnfs_roc_release(calldata->state->inode);
 	nfs4_put_open_state(calldata->state);
 	nfs_free_seqid(calldata->arg.seqid);
 	nfs4_put_state_owner(sp);
@@ -1865,6 +1884,9 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	 */
 	switch (task->tk_status) {
 		case 0:
+			if (calldata->roc)
+				pnfs_roc_set_barrier(state->inode,
+						     calldata->roc_barrier);
 			nfs_set_open_stateid(state, &calldata->res.stateid, 0);
 			renew_lease(server, calldata->timestamp);
 			nfs4_close_clear_stateid_flags(state,
@@ -1917,8 +1939,15 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		return;
 	}
 
-	if (calldata->arg.fmode == 0)
+	if (calldata->arg.fmode == 0) {
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
+		if (calldata->roc &&
+		    pnfs_roc_drain(calldata->inode, &calldata->roc_barrier)) {
+			rpc_sleep_on(&NFS_SERVER(calldata->inode)->roc_rpcwaitq,
+				     task, NULL);
+			return;
+		}
+	}
 
 	nfs_fattr_init(calldata->res.fattr);
 	calldata->timestamp = jiffies;
@@ -1946,7 +1975,7 @@ static const struct rpc_call_ops nfs4_close_ops = {
  *
  * NOTE: Caller must be holding the sp->so_owner semaphore!
  */
-int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, int wait)
+int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs4_closedata *calldata;
@@ -1981,11 +2010,12 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, i
 	calldata->res.fattr = &calldata->fattr;
 	calldata->res.seqid = calldata->arg.seqid;
 	calldata->res.server = server;
+	calldata->roc = roc;
 	path_get(path);
 	calldata->path = *path;
 
-	msg.rpc_argp = &calldata->arg,
-	msg.rpc_resp = &calldata->res,
+	msg.rpc_argp = &calldata->arg;
+	msg.rpc_resp = &calldata->res;
 	task_setup_data.callback_data = calldata;
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
@@ -1998,6 +2028,8 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, i
 out_free_calldata:
 	kfree(calldata);
 out:
+	if (roc)
+		pnfs_roc_release(state->inode);
 	nfs4_put_open_state(state);
 	nfs4_put_state_owner(sp);
 	return status;
@@ -2486,6 +2518,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		path = &ctx->path;
 		fmode = ctx->mode;
 	}
+	sattr->ia_mode &= ~current_umask();
 	state = nfs4_do_open(dir, path, fmode, flags, sattr, cred);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
@@ -2816,6 +2849,8 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 {
 	struct nfs4_exception exception = { };
 	int err;
+
+	sattr->ia_mode &= ~current_umask();
 	do {
 		err = nfs4_handle_exception(NFS_SERVER(dir),
 				_nfs4_proc_mkdir(dir, dentry, sattr),
@@ -2916,6 +2951,8 @@ static int nfs4_proc_mknod(struct inode *dir, struct dentry *dentry,
 {
 	struct nfs4_exception exception = { };
 	int err;
+
+	sattr->ia_mode &= ~current_umask();
 	do {
 		err = nfs4_handle_exception(NFS_SERVER(dir),
 				_nfs4_proc_mknod(dir, dentry, sattr, rdev),
@@ -3216,6 +3253,35 @@ static void buf_to_pages(const void *buf, size_t buflen,
 	}
 }
 
+static int buf_to_pages_noslab(const void *buf, size_t buflen,
+		struct page **pages, unsigned int *pgbase)
+{
+	struct page *newpage, **spages;
+	int rc = 0;
+	size_t len;
+	spages = pages;
+
+	do {
+		len = min(PAGE_CACHE_SIZE, buflen);
+		newpage = alloc_page(GFP_KERNEL);
+
+		if (newpage == NULL)
+			goto unwind;
+		memcpy(page_address(newpage), buf, len);
+                buf += len;
+                buflen -= len;
+		*pages++ = newpage;
+		rc++;
+	} while (buflen != 0);
+
+	return rc;
+
+unwind:
+	for(; rc > 0; rc--)
+		__free_page(spages[rc-1]);
+	return -ENOMEM;
+}
+
 struct nfs4_cached_acl {
 	int cached;
 	size_t len;
@@ -3384,13 +3450,23 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		.rpc_argp	= &arg,
 		.rpc_resp	= &res,
 	};
-	int ret;
+	int ret, i;
 
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
+	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
+	if (i < 0)
+		return i;
 	nfs_inode_return_delegation(inode);
-	buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	ret = nfs4_call_sync(server, &msg, &arg, &res, 1);
+
+	/*
+	 * Free each page after tx, so the only ref left is
+	 * held by the network stack
+	 */
+	for (; i > 0; i--)
+		put_page(pages[i-1]);
+
 	/*
 	 * Acl update can result in inode attribute update.
 	 * so mark the attribute cache invalid.
@@ -3478,6 +3554,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 	struct nfs4_setclientid setclientid = {
 		.sc_verifier = &sc_verifier,
 		.sc_prog = program,
+		.sc_cb_ident = clp->cl_cb_ident,
 	};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID],
@@ -3517,7 +3594,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		if (signalled())
 			break;
 		if (loop++ & 1)
-			ssleep(clp->cl_lease_time + 1);
+			ssleep(clp->cl_lease_time / HZ + 1);
 		else
 			if (++clp->cl_id_uniquifier == 0)
 				break;
@@ -3663,8 +3740,8 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	data->rpc_status = 0;
 
 	task_setup_data.callback_data = data;
-	msg.rpc_argp = &data->args,
-	msg.rpc_resp = &data->res,
+	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -3743,6 +3820,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 		goto out;
 	lsp = request->fl_u.nfs4_fl.owner;
 	arg.lock_owner.id = lsp->ls_id.id;
+	arg.lock_owner.s_dev = server->s_dev;
 	status = nfs4_call_sync(server, &msg, &arg, &res, 1);
 	switch (status) {
 		case 0:
@@ -3908,8 +3986,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	msg.rpc_argp = &data->arg,
-	msg.rpc_resp = &data->res,
+	msg.rpc_argp = &data->arg;
+	msg.rpc_resp = &data->res;
 	task_setup_data.callback_data = data;
 	return rpc_run_task(&task_setup_data);
 }
@@ -3988,6 +4066,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->arg.lock_stateid = &lsp->ls_stateid;
 	p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
 	p->arg.lock_owner.id = lsp->ls_id.id;
+	p->arg.lock_owner.s_dev = server->s_dev;
 	p->res.lock_seqid = p->arg.lock_seqid;
 	p->lsp = lsp;
 	p->server = server;
@@ -4145,8 +4224,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 			data->arg.reclaim = NFS_LOCK_RECLAIM;
 		task_setup_data.callback_ops = &nfs4_recover_lock_ops;
 	}
-	msg.rpc_argp = &data->arg,
-	msg.rpc_resp = &data->res,
+	msg.rpc_argp = &data->arg;
+	msg.rpc_resp = &data->res;
 	task_setup_data.callback_data = data;
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
@@ -4392,48 +4471,43 @@ void nfs4_release_lockowner(const struct nfs4_lock_state *lsp)
 		return;
 	args->lock_owner.clientid = server->nfs_client->cl_clientid;
 	args->lock_owner.id = lsp->ls_id.id;
+	args->lock_owner.s_dev = server->s_dev;
 	msg.rpc_argp = args;
 	rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, args);
 }
 
 #define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
 
-int nfs4_setxattr(struct dentry *dentry, const char *key, const void *buf,
-		size_t buflen, int flags)
+static int nfs4_xattr_set_nfs4_acl(struct dentry *dentry, const char *key,
+				   const void *buf, size_t buflen,
+				   int flags, int type)
 {
-	struct inode *inode = dentry->d_inode;
-
-	if (strcmp(key, XATTR_NAME_NFSV4_ACL) != 0)
-		return -EOPNOTSUPP;
+	if (strcmp(key, "") != 0)
+		return -EINVAL;
 
-	return nfs4_proc_set_acl(inode, buf, buflen);
+	return nfs4_proc_set_acl(dentry->d_inode, buf, buflen);
 }
 
-/* The getxattr man page suggests returning -ENODATA for unknown attributes,
- * and that's what we'll do for e.g. user attributes that haven't been set.
- * But we'll follow ext2/ext3's lead by returning -EOPNOTSUPP for unsupported
- * attributes in kernel-managed attribute namespaces. */
-ssize_t nfs4_getxattr(struct dentry *dentry, const char *key, void *buf,
-		size_t buflen)
+static int nfs4_xattr_get_nfs4_acl(struct dentry *dentry, const char *key,
+				   void *buf, size_t buflen, int type)
 {
-	struct inode *inode = dentry->d_inode;
-
-	if (strcmp(key, XATTR_NAME_NFSV4_ACL) != 0)
-		return -EOPNOTSUPP;
+	if (strcmp(key, "") != 0)
+		return -EINVAL;
 
-	return nfs4_proc_get_acl(inode, buf, buflen);
+	return nfs4_proc_get_acl(dentry->d_inode, buf, buflen);
 }
 
-ssize_t nfs4_listxattr(struct dentry *dentry, char *buf, size_t buflen)
+static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list,
+				       size_t list_len, const char *name,
+				       size_t name_len, int type)
 {
-	size_t len = strlen(XATTR_NAME_NFSV4_ACL) + 1;
+	size_t len = sizeof(XATTR_NAME_NFSV4_ACL);
 
 	if (!nfs4_server_supports_acls(NFS_SERVER(dentry->d_inode)))
 		return 0;
-	if (buf && buflen < len)
-		return -ERANGE;
-	if (buf)
-		memcpy(buf, XATTR_NAME_NFSV4_ACL, len);
+
+	if (list && len <= list_len)
+		memcpy(list, XATTR_NAME_NFSV4_ACL, len);
 	return len;
 }
 
@@ -4486,6 +4560,25 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 
 #ifdef CONFIG_NFS_V4_1
 /*
+ * Check the exchange flags returned by the server for invalid flags, having
+ * 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)
+{
+	if (flags & ~EXCHGID4_FLAG_MASK_R)
+		goto out_inval;
+	if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) &&
+	    (flags & EXCHGID4_FLAG_USE_NON_PNFS))
+		goto out_inval;
+	if (!(flags & (EXCHGID4_FLAG_MASK_PNFS)))
+		goto out_inval;
+	return NFS_OK;
+out_inval:
+	return -NFS4ERR_INVAL;
+}
+
+/*
  * nfs4_proc_exchange_id()
  *
  * Since the clientid has expired, all compounds using sessions
@@ -4498,7 +4591,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	nfs4_verifier verifier;
 	struct nfs41_exchange_id_args args = {
 		.client = clp,
-		.flags = clp->cl_exchange_flags,
+		.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER,
 	};
 	struct nfs41_exchange_id_res res = {
 		.client = clp,
@@ -4515,34 +4608,21 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	dprintk("--> %s\n", __func__);
 	BUG_ON(clp == NULL);
 
-	/* Remove server-only flags */
-	args.flags &= ~EXCHGID4_FLAG_CONFIRMED_R;
-
 	p = (u32 *)verifier.data;
 	*p++ = htonl((u32)clp->cl_boot_time.tv_sec);
 	*p = htonl((u32)clp->cl_boot_time.tv_nsec);
 	args.verifier = &verifier;
 
-	while (1) {
-		args.id_len = scnprintf(args.id, sizeof(args.id),
-					"%s/%s %u",
-					clp->cl_ipaddr,
-					rpc_peeraddr2str(clp->cl_rpcclient,
-							 RPC_DISPLAY_ADDR),
-					clp->cl_id_uniquifier);
-
-		status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
-
-		if (status != -NFS4ERR_CLID_INUSE)
-			break;
-
-		if (signalled())
-			break;
-
-		if (++clp->cl_id_uniquifier == 0)
-			break;
-	}
+	args.id_len = scnprintf(args.id, sizeof(args.id),
+				"%s/%s.%s/%u",
+				clp->cl_ipaddr,
+				init_utsname()->nodename,
+				init_utsname()->domainname,
+				clp->cl_rpcclient->cl_auth->au_flavor);
 
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
+	if (!status)
+		status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
 	dprintk("<-- %s status= %d\n", __func__, status);
 	return status;
 }
@@ -4776,17 +4856,17 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
 	if (!session)
 		return NULL;
 
-	init_completion(&session->complete);
-
 	tbl = &session->fc_slot_table;
 	tbl->highest_used_slotid = -1;
 	spin_lock_init(&tbl->slot_tbl_lock);
 	rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
+	init_completion(&tbl->complete);
 
 	tbl = &session->bc_slot_table;
 	tbl->highest_used_slotid = -1;
 	spin_lock_init(&tbl->slot_tbl_lock);
 	rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
+	init_completion(&tbl->complete);
 
 	session->session_state = 1<<NFS4_SESSION_INITING;
 
@@ -5280,13 +5360,23 @@ static void
 nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
-	struct inode *ino = lgp->args.inode;
-	struct nfs_server *server = NFS_SERVER(ino);
+	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
 
 	dprintk("--> %s\n", __func__);
+	/* Note the is a race here, where a CB_LAYOUTRECALL can come in
+	 * right now covering the LAYOUTGET we are about to send.
+	 * However, that is not so catastrophic, and there seems
+	 * to be no way to prevent it completely.
+	 */
 	if (nfs4_setup_sequence(server, &lgp->args.seq_args,
 				&lgp->res.seq_res, 0, task))
 		return;
+	if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
+					  NFS_I(lgp->args.inode)->layout,
+					  lgp->args.ctx->state)) {
+		rpc_exit(task, NFS4_OK);
+		return;
+	}
 	rpc_call_start(task);
 }
 
@@ -5313,7 +5403,6 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			return;
 		}
 	}
-	lgp->status = task->tk_status;
 	dprintk("<-- %s\n", __func__);
 }
 
@@ -5322,7 +5411,6 @@ static void nfs4_layoutget_release(void *calldata)
 	struct nfs4_layoutget *lgp = calldata;
 
 	dprintk("--> %s\n", __func__);
-	put_layout_hdr(lgp->args.inode);
 	if (lgp->res.layout.buf != NULL)
 		free_page((unsigned long) lgp->res.layout.buf);
 	put_nfs_open_context(lgp->args.ctx);
@@ -5367,13 +5455,10 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 	if (IS_ERR(task))
 		return PTR_ERR(task);
 	status = nfs4_wait_for_completion_rpc_task(task);
-	if (status != 0)
-		goto out;
-	status = lgp->status;
-	if (status != 0)
-		goto out;
-	status = pnfs_layout_process(lgp);
-out:
+	if (status == 0)
+		status = task->tk_status;
+	if (status == 0)
+		status = pnfs_layout_process(lgp);
 	rpc_put_task(task);
 	dprintk("<-- %s status=%d\n", __func__, status);
 	return status;
@@ -5504,9 +5589,10 @@ static const struct inode_operations nfs4_file_inode_operations = {
 	.permission	= nfs_permission,
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
-	.getxattr	= nfs4_getxattr,
-	.setxattr	= nfs4_setxattr,
-	.listxattr	= nfs4_listxattr,
+	.getxattr	= generic_getxattr,
+	.setxattr	= generic_setxattr,
+	.listxattr	= generic_listxattr,
+	.removexattr	= generic_removexattr,
 };
 
 const struct nfs_rpc_ops nfs_v4_clientops = {
@@ -5551,6 +5637,18 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.open_context	= nfs4_atomic_open,
 };
 
+static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
+	.prefix	= XATTR_NAME_NFSV4_ACL,
+	.list	= nfs4_xattr_list_nfs4_acl,
+	.get	= nfs4_xattr_get_nfs4_acl,
+	.set	= nfs4_xattr_set_nfs4_acl,
+};
+
+const struct xattr_handler *nfs4_xattr_handlers[] = {
+	&nfs4_xattr_nfs4_acl_handler,
+	NULL
+};
+
 /*
  * Local variables:
  *  c-basic-offset: 8