Merge tag 'nfs-for-4.12-1' of git://git.linux-nfs.org/projects/trondm…

…y/linux-nfs

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

  Stable bugfixes:
   - Fix use after free in write error path
   - Use GFP_NOIO for two allocations in writeback
   - Fix a hang in OPEN related to server reboot
   - Check the result of nfs4_pnfs_ds_connect
   - Fix an rcu lock leak

  Features:
   - Removal of the unmaintained and unused OSD pNFS layout
   - Cleanup and removal of lots of unnecessary dprintk()s
   - Cleanup and removal of some memory failure paths now that GFP_NOFS
     is guaranteed to never fail.
   - Remove the v3-only data server limitation on pNFS/flexfiles

  Bugfixes:
   - RPC/RDMA connection handling bugfixes
   - Copy offload: fixes to ensure the copied data is COMMITed to disk.
   - Readdir: switch back to using the ->iterate VFS interface
   - File locking fixes from Ben Coddington
   - Various use-after-free and deadlock issues in pNFS
   - Write path bugfixes"

* tag 'nfs-for-4.12-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (89 commits)
  pNFS/flexfiles: Always attempt to call layoutstats when flexfiles is enabled
  NFSv4.1: Work around a Linux server bug...
  NFS append COMMIT after synchronous COPY
  NFSv4: Fix exclusive create attributes encoding
  NFSv4: Fix an rcu lock leak
  nfs: use kmap/kunmap directly
  NFS: always treat the invocation of nfs_getattr as cache hit when noac is on
  Fix nfs_client refcounting if kmalloc fails in nfs4_proc_exchange_id and nfs4_proc_async_renew
  NFSv4.1: RECLAIM_COMPLETE must handle NFS4ERR_CONN_NOT_BOUND_TO_SESSION
  pNFS: Fix NULL dereference in pnfs_generic_alloc_ds_commits
  pNFS: Fix a typo in pnfs_generic_alloc_ds_commits
  pNFS: Fix a deadlock when coalescing writes and returning the layout
  pNFS: Don't clear the layout return info if there are segments to return
  pNFS: Ensure we commit the layout if it has been invalidated
  pNFS: Don't send COMMITs to the DSes if the server invalidated our layout
  pNFS/flexfiles: Fix up the ff_layout_write_pagelist failure path
  pNFS: Ensure we check layout validity before marking it for return
  NFS4.1 handle interrupted slot reuse from ERR_DELAY
  NFSv4: check return value of xdr_inline_decode
  nfs/filelayout: fix NULL pointer dereference in fl_pnfs_update_layout()
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -2434,12 +2434,6 @@
 			and gids from such clients.  This is intended to ease
 			migration from NFSv2/v3.
 
-	objlayoutdriver.osd_login_prog=
-			[NFS] [OBJLAYOUT] sets the pathname to the program which
-			is used to automatically discover and login into new
-			osd-targets. Please see:
-			Documentation/filesystems/pnfs.txt for more explanations
-
 	nmi_debug=	[KNL,SH] Specify one or more actions to take
 			when a NMI is triggered.
 			Format: [state][,regs][,debounce][,die]

Documentation/filesystems/nfs/pnfs.txt

@@ -64,46 +64,9 @@ table which are called by the nfs-client pnfs-core to implement the
 different layout types.
 
 Files-layout-driver code is in: fs/nfs/filelayout/.. directory
-Objects-layout-driver code is in: fs/nfs/objlayout/.. directory
 Blocks-layout-driver code is in: fs/nfs/blocklayout/.. directory
 Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
 
-objects-layout setup
---------------------
-
-As part of the full STD implementation the objlayoutdriver.ko needs, at times,
-to automatically login to yet undiscovered iscsi/osd devices. For this the
-driver makes up-calles to a user-mode script called *osd_login*
-
-The path_name of the script to use is by default:
-	/sbin/osd_login.
-This name can be overridden by the Kernel module parameter:
-	objlayoutdriver.osd_login_prog
-
-If Kernel does not find the osd_login_prog path it will zero it out
-and will not attempt farther logins. An admin can then write new value
-to the objlayoutdriver.osd_login_prog Kernel parameter to re-enable it.
-
-The /sbin/osd_login is part of the nfs-utils package, and should usually
-be installed on distributions that support this Kernel version.
-
-The API to the login script is as follows:
-	Usage: $0 -u <URI> -o <OSDNAME> -s <SYSTEMID>
-	Options:
-		-u		target uri e.g. iscsi://<ip>:<port>
-				(always exists)
-				(More protocols can be defined in the future.
-				 The client does not interpret this string it is
-				 passed unchanged as received from the Server)
-		-o		osdname of the requested target OSD
-				(Might be empty)
-				(A string which denotes the OSD name, there is a
-				 limit of 64 chars on this string)
-		-s 		systemid of the requested target OSD
-				(Might be empty)
-				(This string, if not empty is always an hex
-				 representation of the 20 bytes osd_system_id)
-
 blocks-layout setup
 -------------------
 

fs/fuse/file.c

@@ -2177,7 +2177,7 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	}
 
 	/* Unlock on close is handled by the flush method */
-	if (fl->fl_flags & FL_CLOSE)
+	if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
 		return 0;
 
 	if (pid && pid_nr == 0)

fs/lockd/clntlock.c

@@ -69,6 +69,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
 	if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
 		goto out_nobind;
 
+	host->h_nlmclnt_ops = nlm_init->nlmclnt_ops;
 	return host;
 out_nobind:
 	nlmclnt_release_host(host);

fs/lockd/clntproc.c

@@ -150,17 +150,22 @@ static void nlmclnt_release_lockargs(struct nlm_rqst *req)
  * @host: address of a valid nlm_host context representing the NLM server
  * @cmd: fcntl-style file lock operation to perform
  * @fl: address of arguments for the lock operation
+ * @data: address of data to be sent to callback operations
  *
  */
-int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
+int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *data)
 {
 	struct nlm_rqst		*call;
 	int			status;
+	const struct nlmclnt_operations *nlmclnt_ops = host->h_nlmclnt_ops;
 
 	call = nlm_alloc_call(host);
 	if (call == NULL)
 		return -ENOMEM;
 
+	if (nlmclnt_ops && nlmclnt_ops->nlmclnt_alloc_call)
+		nlmclnt_ops->nlmclnt_alloc_call(data);
+
 	nlmclnt_locks_init_private(fl, host);
 	if (!fl->fl_u.nfs_fl.owner) {
 		/* lockowner allocation has failed */
@@ -169,6 +174,7 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 	}
 	/* Set up the argument struct */
 	nlmclnt_setlockargs(call, fl);
+	call->a_callback_data = data;
 
 	if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
 		if (fl->fl_type != F_UNLCK) {
@@ -214,8 +220,12 @@ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host)
 
 void nlmclnt_release_call(struct nlm_rqst *call)
 {
+	const struct nlmclnt_operations *nlmclnt_ops = call->a_host->h_nlmclnt_ops;
+
 	if (!atomic_dec_and_test(&call->a_count))
 		return;
+	if (nlmclnt_ops && nlmclnt_ops->nlmclnt_release_call)
+		nlmclnt_ops->nlmclnt_release_call(call->a_callback_data);
 	nlmclnt_release_host(call->a_host);
 	nlmclnt_release_lockargs(call);
 	kfree(call);
@@ -687,6 +697,19 @@ nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl)
 	return status;
 }
 
+static void nlmclnt_unlock_prepare(struct rpc_task *task, void *data)
+{
+	struct nlm_rqst	*req = data;
+	const struct nlmclnt_operations *nlmclnt_ops = req->a_host->h_nlmclnt_ops;
+	bool defer_call = false;
+
+	if (nlmclnt_ops && nlmclnt_ops->nlmclnt_unlock_prepare)
+		defer_call = nlmclnt_ops->nlmclnt_unlock_prepare(task, req->a_callback_data);
+
+	if (!defer_call)
+		rpc_call_start(task);
+}
+
 static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 {
 	struct nlm_rqst	*req = data;
@@ -720,6 +743,7 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 }
 
 static const struct rpc_call_ops nlmclnt_unlock_ops = {
+	.rpc_call_prepare = nlmclnt_unlock_prepare,
 	.rpc_call_done = nlmclnt_unlock_callback,
 	.rpc_release = nlmclnt_rpc_release,
 };

fs/locks.c

@@ -2504,7 +2504,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
 		.fl_owner = filp,
 		.fl_pid = current->tgid,
 		.fl_file = filp,
-		.fl_flags = FL_FLOCK,
+		.fl_flags = FL_FLOCK | FL_CLOSE,
 		.fl_type = F_UNLCK,
 		.fl_end = OFFSET_MAX,
 	};

fs/nfs/Kconfig

@@ -123,11 +123,6 @@ config PNFS_BLOCK
 	depends on NFS_V4_1 && BLK_DEV_DM
 	default NFS_V4
 
-config PNFS_OBJLAYOUT
-	tristate
-	depends on NFS_V4_1 && SCSI_OSD_ULD
-	default NFS_V4
-
 config PNFS_FLEXFILE_LAYOUT
 	tristate
 	depends on NFS_V4_1 && NFS_V3

fs/nfs/Makefile

@@ -31,6 +31,5 @@ nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
 nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
 obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/

fs/nfs/callback_proc.c

@@ -131,10 +131,11 @@ static struct inode *nfs_layout_find_inode_by_stateid(struct nfs_client *clp,
 			if (!inode)
 				continue;
 			if (!nfs_sb_active(inode->i_sb)) {
-				rcu_read_lock();
+				rcu_read_unlock();
 				spin_unlock(&clp->cl_lock);
 				iput(inode);
 				spin_lock(&clp->cl_lock);
+				rcu_read_lock();
 				goto restart;
 			}
 			return inode;
@@ -170,10 +171,11 @@ static struct inode *nfs_layout_find_inode_by_fh(struct nfs_client *clp,
 			if (!inode)
 				continue;
 			if (!nfs_sb_active(inode->i_sb)) {
-				rcu_read_lock();
+				rcu_read_unlock();
 				spin_unlock(&clp->cl_lock);
 				iput(inode);
 				spin_lock(&clp->cl_lock);
+				rcu_read_lock();
 				goto restart;
 			}
 			return inode;
@@ -317,31 +319,18 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 static u32 do_callback_layoutrecall(struct nfs_client *clp,
 				    struct cb_layoutrecallargs *args)
 {
-	u32 res;
-
-	dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type);
 	if (args->cbl_recall_type == RETURN_FILE)
-		res = initiate_file_draining(clp, args);
-	else
-		res = initiate_bulk_draining(clp, args);
-	dprintk("%s returning %i\n", __func__, res);
-	return res;
-
+		return initiate_file_draining(clp, args);
+	return initiate_bulk_draining(clp, args);
 }
 
 __be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args,
 				  void *dummy, struct cb_process_state *cps)
 {
-	u32 res;
-
-	dprintk("%s: -->\n", __func__);
+	u32 res = NFS4ERR_OP_NOT_IN_SESSION;
 
 	if (cps->clp)
 		res = do_callback_layoutrecall(cps->clp, args);
-	else
-		res = NFS4ERR_OP_NOT_IN_SESSION;
-
-	dprintk("%s: exit with status = %d\n", __func__, res);
 	return cpu_to_be32(res);
 }
 
@@ -364,8 +353,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
 	struct nfs_client *clp = cps->clp;
 	struct nfs_server *server = NULL;
 
-	dprintk("%s: -->\n", __func__);
-
 	if (!clp) {
 		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
 		goto out;
@@ -384,8 +371,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
 					goto found;
 				}
 			rcu_read_unlock();
-			dprintk("%s: layout type %u not found\n",
-				__func__, dev->cbd_layout_type);
 			continue;
 		}
 
@@ -395,8 +380,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
 
 out:
 	kfree(args->devs);
-	dprintk("%s: exit with status = %u\n",
-		__func__, be32_to_cpu(res));
 	return res;
 }
 
@@ -417,16 +400,11 @@ static __be32
 validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
 		const struct cb_sequenceargs * args)
 {
-	dprintk("%s enter. slotid %u seqid %u, slot table seqid: %u\n",
-		__func__, args->csa_slotid, args->csa_sequenceid, slot->seq_nr);
-
 	if (args->csa_slotid > tbl->server_highest_slotid)
 		return htonl(NFS4ERR_BADSLOT);
 
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
-		dprintk("%s seqid %u is a replay\n",
-			__func__, args->csa_sequenceid);
 		if (nfs4_test_locked_slot(tbl, slot->slot_nr))
 			return htonl(NFS4ERR_DELAY);
 		/* Signal process_op to set this error on next op */
@@ -480,15 +458,6 @@ static bool referring_call_exists(struct nfs_client *clp,
 
 		for (j = 0; j < rclist->rcl_nrefcalls; j++) {
 			ref = &rclist->rcl_refcalls[j];
-
-			dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u "
-				"slotid %u\n", __func__,
-				((u32 *)&rclist->rcl_sessionid.data)[0],
-				((u32 *)&rclist->rcl_sessionid.data)[1],
-				((u32 *)&rclist->rcl_sessionid.data)[2],
-				((u32 *)&rclist->rcl_sessionid.data)[3],
-				ref->rc_sequenceid, ref->rc_slotid);
-
 			status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid,
 					ref->rc_sequenceid, HZ >> 1) < 0;
 			if (status)
@@ -593,8 +562,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 		res->csr_status = status;
 
 	trace_nfs4_cb_sequence(args, res, status);
-	dprintk("%s: exit with status = %d res->csr_status %d\n", __func__,
-		ntohl(status), ntohl(res->csr_status));
 	return status;
 }