Merge tag 'nfs-for-3.15-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

   - Stable fix for a use after free issue in the NFSv4.1 open code
   - Fix the SUNRPC bi-directional RPC code to account for TCP segmentation
   - Optimise usage of readdirplus when confronted with 'ls -l' situations
   - Soft mount bugfixes
   - NFS over RDMA bugfixes
   - NFSv4 close locking fixes
   - Various NFSv4.x client state management optimisations
   - Rename/unlink code cleanups"

* tag 'nfs-for-3.15-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (28 commits)
  nfs: pass string length to pr_notice message about readdir loops
  NFSv4: Fix a use-after-free problem in open()
  SUNRPC: rpc_restart_call/rpc_restart_call_prepare should clear task->tk_status
  SUNRPC: Don't let rpc_delay() clobber non-timeout errors
  SUNRPC: Ensure call_connect_status() deals correctly with SOFTCONN tasks
  SUNRPC: Ensure call_status() deals correctly with SOFTCONN tasks
  NFSv4: Ensure we respect soft mount timeouts during trunking discovery
  NFSv4: Schedule recovery if nfs40_walk_client_list() is interrupted
  NFS: advertise only supported callback netids
  SUNRPC: remove KERN_INFO from dprintk() call sites
  SUNRPC: Fix large reads on NFS/RDMA
  NFS: Clean up: revert increase in READDIR RPC buffer max size
  SUNRPC: Ensure that call_bind times out correctly
  SUNRPC: Ensure that call_connect times out correctly
  nfs: emit a fsnotify_nameremove call in sillyrename codepath
  nfs: remove synchronous rename code
  nfs: convert nfs_rename to use async_rename infrastructure
  nfs: make nfs_async_rename non-static
  nfs: abstract out code needed to complete a sillyrename
  NFSv4: Clear the open state flags if the new stateid does not match
  ...

fs/nfs/callback_proc.c

@@ -112,7 +112,8 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
  * TODO: keep track of all layouts (and delegations) in a hash table
  * hashed by filehandle.
  */
-static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp, struct nfs_fh *fh)
+static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
+		struct nfs_fh *fh, nfs4_stateid *stateid)
 {
 	struct nfs_server *server;
 	struct inode *ino;
@@ -120,17 +121,19 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
 
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (!nfs4_stateid_match_other(&lo->plh_stateid, stateid))
+				continue;
 			if (nfs_compare_fh(fh, &NFS_I(lo->plh_inode)->fh))
 				continue;
 			ino = igrab(lo->plh_inode);
 			if (!ino)
-				continue;
+				break;
 			spin_lock(&ino->i_lock);
 			/* Is this layout in the process of being freed? */
 			if (NFS_I(ino)->layout != lo) {
 				spin_unlock(&ino->i_lock);
 				iput(ino);
-				continue;
+				break;
 			}
 			pnfs_get_layout_hdr(lo);
 			spin_unlock(&ino->i_lock);
@@ -141,13 +144,14 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
 	return NULL;
 }
 
-static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, struct nfs_fh *fh)
+static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp,
+		struct nfs_fh *fh, nfs4_stateid *stateid)
 {
 	struct pnfs_layout_hdr *lo;
 
 	spin_lock(&clp->cl_lock);
 	rcu_read_lock();
-	lo = get_layout_by_fh_locked(clp, fh);
+	lo = get_layout_by_fh_locked(clp, fh, stateid);
 	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
 
@@ -162,9 +166,9 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
 	LIST_HEAD(free_me_list);
 
-	lo = get_layout_by_fh(clp, &args->cbl_fh);
+	lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid);
 	if (!lo)
-		return NFS4ERR_NOMATCHING_LAYOUT;
+		goto out;
 
 	ino = lo->plh_inode;
 	spin_lock(&ino->i_lock);
@@ -179,6 +183,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	pnfs_free_lseg_list(&free_me_list);
 	pnfs_put_layout_hdr(lo);
 	iput(ino);
+out:
 	return rv;
 }
 

fs/nfs/dir.c

@@ -69,21 +69,28 @@ const struct address_space_operations nfs_dir_aops = {
 
 static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
+	struct nfs_inode *nfsi = NFS_I(dir);
 	struct nfs_open_dir_context *ctx;
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx != NULL) {
 		ctx->duped = 0;
-		ctx->attr_gencount = NFS_I(dir)->attr_gencount;
+		ctx->attr_gencount = nfsi->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
 		ctx->cred = get_rpccred(cred);
+		spin_lock(&dir->i_lock);
+		list_add(&ctx->list, &nfsi->open_files);
+		spin_unlock(&dir->i_lock);
 		return ctx;
 	}
 	return  ERR_PTR(-ENOMEM);
 }
 
-static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx)
+static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
 {
+	spin_lock(&dir->i_lock);
+	list_del(&ctx->list);
+	spin_unlock(&dir->i_lock);
 	put_rpccred(ctx->cred);
 	kfree(ctx);
 }
@@ -126,7 +133,7 @@ nfs_opendir(struct inode *inode, struct file *filp)
 static int
 nfs_closedir(struct inode *inode, struct file *filp)
 {
-	put_nfs_open_dir_context(filp->private_data);
+	put_nfs_open_dir_context(filp->f_path.dentry->d_inode, filp->private_data);
 	return 0;
 }
 
@@ -306,10 +313,9 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 					if (printk_ratelimit()) {
 						pr_notice("NFS: directory %pD2 contains a readdir loop."
 								"Please contact your server vendor.  "
-								"The file: %s has duplicate cookie %llu\n",
-								desc->file,
-								array->array[i].string.name,
-								*desc->dir_cookie);
+								"The file: %.*s has duplicate cookie %llu\n",
+								desc->file, array->array[i].string.len,
+								array->array[i].string.name, *desc->dir_cookie);
 					}
 					status = -ELOOP;
 					goto out;
@@ -437,6 +443,22 @@ void nfs_advise_use_readdirplus(struct inode *dir)
 	set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags);
 }
 
+/*
+ * This function is mainly for use by nfs_getattr().
+ *
+ * If this is an 'ls -l', we want to force use of readdirplus.
+ * Do this by checking if there is an active file descriptor
+ * and calling nfs_advise_use_readdirplus, then forcing a
+ * cache flush.
+ */
+void nfs_force_use_readdirplus(struct inode *dir)
+{
+	if (!list_empty(&NFS_I(dir)->open_files)) {
+		nfs_advise_use_readdirplus(dir);
+		nfs_zap_mapping(dir, dir->i_mapping);
+	}
+}
+
 static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
@@ -815,6 +837,17 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
 	goto out;
 }
 
+static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
+{
+	struct nfs_inode *nfsi = NFS_I(dir);
+
+	if (nfs_attribute_cache_expired(dir))
+		return true;
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		return true;
+	return false;
+}
+
 /* The file offset position represents the dirent entry number.  A
    last cookie cache takes care of the common case of reading the
    whole directory.
@@ -847,7 +880,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
 
 	nfs_block_sillyrename(dentry);
-	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
+	if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
 	if (res < 0)
 		goto out;
@@ -1911,6 +1944,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct inode *old_inode = old_dentry->d_inode;
 	struct inode *new_inode = new_dentry->d_inode;
 	struct dentry *dentry = NULL, *rehash = NULL;
+	struct rpc_task *task;
 	int error = -EBUSY;
 
 	dfprintk(VFS, "NFS: rename(%pd2 -> %pd2, ct=%d)\n",
@@ -1958,8 +1992,16 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (new_inode != NULL)
 		NFS_PROTO(new_inode)->return_delegation(new_inode);
 
-	error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
-					   new_dir, &new_dentry->d_name);
+	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL);
+	if (IS_ERR(task)) {
+		error = PTR_ERR(task);
+		goto out;
+	}
+
+	error = rpc_wait_for_completion_task(task);
+	if (error == 0)
+		error = task->tk_status;
+	rpc_put_task(task);
 	nfs_mark_for_revalidate(old_inode);
 out:
 	if (rehash)

fs/nfs/inode.c

@@ -588,6 +588,25 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
+static void nfs_request_parent_use_readdirplus(struct dentry *dentry)
+{
+	struct dentry *parent;
+
+	parent = dget_parent(dentry);
+	nfs_force_use_readdirplus(parent->d_inode);
+	dput(parent);
+}
+
+static bool nfs_need_revalidate_inode(struct inode *inode)
+{
+	if (NFS_I(inode)->cache_validity &
+			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
+		return true;
+	if (nfs_attribute_cache_expired(inode))
+		return true;
+	return false;
+}
+
 int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
@@ -616,10 +635,13 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
  	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
 		need_atime = 0;
 
-	if (need_atime)
-		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
-	else
-		err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	if (need_atime || nfs_need_revalidate_inode(inode)) {
+		struct nfs_server *server = NFS_SERVER(inode);
+
+		if (server->caps & NFS_CAP_READDIRPLUS)
+			nfs_request_parent_use_readdirplus(dentry);
+		err = __nfs_revalidate_inode(server, inode);
+	}
 	if (!err) {
 		generic_fillattr(inode, stat);
 		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
@@ -961,9 +983,7 @@ int nfs_attribute_cache_expired(struct inode *inode)
  */
 int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 {
-	if (!(NFS_I(inode)->cache_validity &
-			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
-			&& !nfs_attribute_cache_expired(inode))
+	if (!nfs_need_revalidate_inode(inode))
 		return NFS_STALE(inode) ? -ESTALE : 0;
 	return __nfs_revalidate_inode(server, inode);
 }

fs/nfs/internal.h

@@ -301,6 +301,7 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 			   const char *ip_addr);
 
 /* dir.c */
+extern void nfs_force_use_readdirplus(struct inode *dir);
 extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
 					    struct shrink_control *sc);
 extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
@@ -474,6 +475,13 @@ extern int nfs_migrate_page(struct address_space *,
 #define nfs_migrate_page NULL
 #endif
 
+/* unlink.c */
+extern struct rpc_task *
+nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
+		 struct dentry *old_dentry, struct dentry *new_dentry,
+		 void (*complete)(struct rpc_task *, struct nfs_renamedata *));
+extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
+
 /* direct.c */
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq);

fs/nfs/nfs3proc.c

@@ -478,41 +478,6 @@ nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 	return 1;
 }
 
-static int
-nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
-		 struct inode *new_dir, struct qstr *new_name)
-{
-	struct nfs_renameargs	arg = {
-		.old_dir	= NFS_FH(old_dir),
-		.old_name	= old_name,
-		.new_dir	= NFS_FH(new_dir),
-		.new_name	= new_name,
-	};
-	struct nfs_renameres res;
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs3_procedures[NFS3PROC_RENAME],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
-	};
-	int status = -ENOMEM;
-
-	dprintk("NFS call  rename %s -> %s\n", old_name->name, new_name->name);
-
-	res.old_fattr = nfs_alloc_fattr();
-	res.new_fattr = nfs_alloc_fattr();
-	if (res.old_fattr == NULL || res.new_fattr == NULL)
-		goto out;
-
-	status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
-	nfs_post_op_update_inode(old_dir, res.old_fattr);
-	nfs_post_op_update_inode(new_dir, res.new_fattr);
-out:
-	nfs_free_fattr(res.old_fattr);
-	nfs_free_fattr(res.new_fattr);
-	dprintk("NFS reply rename: %d\n", status);
-	return status;
-}
-
 static int
 nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 {
@@ -968,7 +933,6 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.unlink_setup	= nfs3_proc_unlink_setup,
 	.unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
 	.unlink_done	= nfs3_proc_unlink_done,
-	.rename		= nfs3_proc_rename,
 	.rename_setup	= nfs3_proc_rename_setup,
 	.rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
 	.rename_done	= nfs3_proc_rename_done,

fs/nfs/nfs4_fs.h

@@ -427,6 +427,7 @@ extern void nfs4_close_sync(struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs_inode_find_state_and_recover(struct inode *inode,
 		const nfs4_stateid *stateid);
+extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *, struct nfs4_state *);
 extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern int nfs4_wait_clnt_recover(struct nfs_client *clp);
 extern int nfs4_client_recover_expired_lease(struct nfs_client *clp);
@@ -500,6 +501,16 @@ static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_statei
 	return memcmp(dst, src, sizeof(*dst)) == 0;
 }
 
+static inline bool nfs4_stateid_match_other(const nfs4_stateid *dst, const nfs4_stateid *src)
+{
+	return memcmp(dst->other, src->other, NFS4_STATEID_OTHER_SIZE) == 0;
+}
+
+static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stateid *s2)
+{
+	return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
+}
+
 static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state)
 {
 	return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0;

fs/nfs/nfs4client.c

@@ -531,6 +531,13 @@ int nfs40_walk_client_list(struct nfs_client *new,
 			*result = pos;
 			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
 				__func__, pos, atomic_read(&pos->cl_count));
+			goto out;
+		case -ERESTARTSYS:
+		case -ETIMEDOUT:
+			/* The callback path may have been inadvertently
+			 * changed. Schedule recovery!
+			 */
+			nfs4_schedule_path_down_recovery(pos);
 		default:
 			goto out;
 		}

fs/nfs/nfs4state.c

@@ -1316,7 +1316,7 @@ static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_st
 	return 1;
 }
 
-static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
+int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
 {
 	set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
 	clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
@@ -2075,8 +2075,10 @@ int nfs4_discover_server_trunking(struct nfs_client *clp,
 	switch (status) {
 	case 0:
 		break;
-	case -NFS4ERR_DELAY:
 	case -ETIMEDOUT:
+		if (clnt->cl_softrtry)
+			break;
+	case -NFS4ERR_DELAY:
 	case -EAGAIN:
 		ssleep(1);
 	case -NFS4ERR_STALE_CLIENTID:

fs/nfs/nfs4xdr.c

@@ -203,8 +203,7 @@ static int nfs4_stat_to_errno(int);
 				 2 + encode_verifier_maxsz + 5 + \
 				nfs4_label_maxsz)
 #define decode_readdir_maxsz	(op_decode_hdr_maxsz + \
-				 decode_verifier_maxsz + \
-				nfs4_label_maxsz + nfs4_fattr_maxsz)
+				 decode_verifier_maxsz)
 #define encode_readlink_maxsz	(op_encode_hdr_maxsz)
 #define decode_readlink_maxsz	(op_decode_hdr_maxsz + 1)
 #define encode_write_maxsz	(op_encode_hdr_maxsz + \

fs/nfs/pnfs.c

@@ -662,7 +662,18 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
  */
 static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
 {
-	return (s32)s1 - (s32)s2 > 0;
+	return (s32)(s1 - s2) > 0;
+}
+
+static void
+pnfs_verify_layout_stateid(struct pnfs_layout_hdr *lo,
+		const nfs4_stateid *new,
+		struct list_head *free_me_list)
+{
+	if (nfs4_stateid_match_other(&lo->plh_stateid, new))
+		return;
+	/* Layout is new! Kill existing layout segments */
+	pnfs_mark_matching_lsegs_invalid(lo, free_me_list, NULL);
 }
 
 /* update lo->plh_stateid with new if is more recent */
@@ -1315,6 +1326,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 	struct nfs4_layoutget_res *res = &lgp->res;
 	struct pnfs_layout_segment *lseg;
 	struct inode *ino = lo->plh_inode;
+	LIST_HEAD(free_me);
 	int status = 0;
 
 	/* Inject layout blob into I/O device driver */
@@ -1341,6 +1353,8 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget_reply;
 	}
 
+	/* Check that the new stateid matches the old stateid */
+	pnfs_verify_layout_stateid(lo, &res->stateid, &free_me);
 	/* Done processing layoutget. Set the layout stateid */
 	pnfs_set_layout_stateid(lo, &res->stateid, false);
 
@@ -1355,6 +1369,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 	}
 
 	spin_unlock(&ino->i_lock);
+	pnfs_free_lseg_list(&free_me);
 	return lseg;
 out:
 	return ERR_PTR(status);

fs/nfs/proc.c

@@ -356,30 +356,6 @@ nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 	return 1;
 }
 
-static int
-nfs_proc_rename(struct inode *old_dir, struct qstr *old_name,
-		struct inode *new_dir, struct qstr *new_name)
-{
-	struct nfs_renameargs	arg = {
-		.old_dir	= NFS_FH(old_dir),
-		.old_name	= old_name,
-		.new_dir	= NFS_FH(new_dir),
-		.new_name	= new_name,
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs_procedures[NFSPROC_RENAME],
-		.rpc_argp	= &arg,
-	};
-	int			status;
-
-	dprintk("NFS call  rename %s -> %s\n", old_name->name, new_name->name);
-	status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
-	nfs_mark_for_revalidate(old_dir);
-	nfs_mark_for_revalidate(new_dir);
-	dprintk("NFS reply rename: %d\n", status);
-	return status;
-}
-
 static int
 nfs_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 {
@@ -745,7 +721,6 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.unlink_setup	= nfs_proc_unlink_setup,
 	.unlink_rpc_prepare = nfs_proc_unlink_rpc_prepare,
 	.unlink_done	= nfs_proc_unlink_done,
-	.rename		= nfs_proc_rename,
 	.rename_setup	= nfs_proc_rename_setup,
 	.rename_rpc_prepare = nfs_proc_rename_rpc_prepare,
 	.rename_done	= nfs_proc_rename_done,

fs/nfs/unlink.c

@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/namei.h>
+#include <linux/fsnotify.h>
 
 #include "internal.h"
 #include "nfs4_fs.h"
@@ -353,8 +354,8 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 		return;
 	}
 
-	if (task->tk_status != 0)
-		nfs_cancel_async_unlink(old_dentry);
+	if (data->complete)
+		data->complete(task, data);
 }
 
 /**
@@ -399,9 +400,10 @@ static const struct rpc_call_ops nfs_rename_ops = {
  *
  * It's expected that valid references to the dentries and inodes are held
  */
-static struct rpc_task *
+struct rpc_task *
 nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
-		 struct dentry *old_dentry, struct dentry *new_dentry)
+		 struct dentry *old_dentry, struct dentry *new_dentry,
+		 void (*complete)(struct rpc_task *, struct nfs_renamedata *))
 {
 	struct nfs_renamedata *data;
 	struct rpc_message msg = { };
@@ -438,6 +440,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 	data->new_dentry = dget(new_dentry);
 	nfs_fattr_init(&data->old_fattr);
 	nfs_fattr_init(&data->new_fattr);
+	data->complete = complete;
 
 	/* set up nfs_renameargs */
 	data->args.old_dir = NFS_FH(old_dir);
@@ -456,6 +459,27 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 	return rpc_run_task(&task_setup_data);
 }
 
+/*
+ * Perform tasks needed when a sillyrename is done such as cancelling the
+ * queued async unlink if it failed.
+ */
+static void
+nfs_complete_sillyrename(struct rpc_task *task, struct nfs_renamedata *data)
+{
+	struct dentry *dentry = data->old_dentry;
+
+	if (task->tk_status != 0) {
+		nfs_cancel_async_unlink(dentry);
+		return;
+	}
+
+	/*
+	 * vfs_unlink and the like do not issue this when a file is
+	 * sillyrenamed, so do it here.
+	 */
+	fsnotify_nameremove(dentry, 0);
+}
+
 #define SILLYNAME_PREFIX ".nfs"
 #define SILLYNAME_PREFIX_LEN ((unsigned)sizeof(SILLYNAME_PREFIX) - 1)
 #define SILLYNAME_FILEID_LEN ((unsigned)sizeof(u64) << 1)
@@ -548,7 +572,8 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 	}
 
 	/* run the rename task, undo unlink if it fails */
-	task = nfs_async_rename(dir, dir, dentry, sdentry);
+	task = nfs_async_rename(dir, dir, dentry, sdentry,
+					nfs_complete_sillyrename);
 	if (IS_ERR(task)) {
 		error = -EBUSY;
 		nfs_cancel_async_unlink(dentry);

include/linux/nfs_fs.h

@@ -92,6 +92,7 @@ struct nfs_open_context {
 };
 
 struct nfs_open_dir_context {
+	struct list_head list;
 	struct rpc_cred *cred;
 	unsigned long attr_gencount;
 	__u64 dir_cookie;
@@ -510,7 +511,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
 extern void nfs_wait_on_sillyrename(struct dentry *dentry);
 extern void nfs_block_sillyrename(struct dentry *dentry);
 extern void nfs_unblock_sillyrename(struct dentry *dentry);
-extern int  nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 
 /*
  * linux/fs/nfs/write.c

include/linux/nfs_xdr.h

@@ -1402,6 +1402,7 @@ struct nfs_renamedata {
 	struct inode		*new_dir;
 	struct dentry		*new_dentry;
 	struct nfs_fattr	new_fattr;
+	void (*complete)(struct rpc_task *, struct nfs_renamedata *);
 };
 
 struct nfs_access_entry;
@@ -1444,8 +1445,6 @@ struct nfs_rpc_ops {
 	void	(*unlink_setup)  (struct rpc_message *, struct inode *dir);
 	void	(*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *);
 	int	(*unlink_done) (struct rpc_task *, struct inode *);
-	int	(*rename)  (struct inode *, struct qstr *,
-			    struct inode *, struct qstr *);
 	void	(*rename_setup)  (struct rpc_message *msg, struct inode *dir);
 	void	(*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *);
 	int	(*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir);

include/linux/sunrpc/bc_xprt.h

@@ -32,7 +32,8 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <linux/sunrpc/sched.h>
 
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
-struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt);
+struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid);
+void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);

net/sunrpc/backchannel_rqst.c

@@ -212,39 +212,23 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs)
 }
 EXPORT_SYMBOL_GPL(xprt_destroy_backchannel);
 
-/*
- * One or more rpc_rqst structure have been preallocated during the
- * backchannel setup.  Buffer space for the send and private XDR buffers
- * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
- * to this request.  Use xprt_free_bc_request to return it.
- *
- * We know that we're called in soft interrupt context, grab the spin_lock
- * since there is no need to grab the bottom half spin_lock.
- *
- * Return an available rpc_rqst, otherwise NULL if non are available.
- */
-struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt)
+static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid)
 {
-	struct rpc_rqst *req;
+	struct rpc_rqst *req = NULL;
 
 	dprintk("RPC:       allocate a backchannel request\n");
-	spin_lock(&xprt->bc_pa_lock);
-	if (!list_empty(&xprt->bc_pa_list)) {
-		req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
-				rq_bc_pa_list);
-		list_del(&req->rq_bc_pa_list);
-	} else {
-		req = NULL;
-	}
-	spin_unlock(&xprt->bc_pa_lock);
+	if (list_empty(&xprt->bc_pa_list))
+		goto not_found;
 
-	if (req != NULL) {
-		set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
-		req->rq_reply_bytes_recvd = 0;
-		req->rq_bytes_sent = 0;
-		memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
+	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
+				rq_bc_pa_list);
+	req->rq_reply_bytes_recvd = 0;
+	req->rq_bytes_sent = 0;
+	memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
 			sizeof(req->rq_private_buf));
-	}
+	req->rq_xid = xid;
+	req->rq_connect_cookie = xprt->connect_cookie;
+not_found:
 	dprintk("RPC:       backchannel req=%p\n", req);
 	return req;
 }
@@ -259,6 +243,7 @@ void xprt_free_bc_request(struct rpc_rqst *req)
 
 	dprintk("RPC:       free backchannel req=%p\n", req);
 
+	req->rq_connect_cookie = xprt->connect_cookie - 1;
 	smp_mb__before_clear_bit();
 	WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
 	clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
@@ -281,7 +266,57 @@ void xprt_free_bc_request(struct rpc_rqst *req)
 	 * may be reused by a new callback request.
 	 */
 	spin_lock_bh(&xprt->bc_pa_lock);
-	list_add(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+	list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
 	spin_unlock_bh(&xprt->bc_pa_lock);
 }
 
+/*
+ * One or more rpc_rqst structure have been preallocated during the
+ * backchannel setup.  Buffer space for the send and private XDR buffers
+ * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
+ * to this request.  Use xprt_free_bc_request to return it.
+ *
+ * We know that we're called in soft interrupt context, grab the spin_lock
+ * since there is no need to grab the bottom half spin_lock.
+ *
+ * Return an available rpc_rqst, otherwise NULL if non are available.
+ */
+struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid)
+{
+	struct rpc_rqst *req;
+
+	spin_lock(&xprt->bc_pa_lock);
+	list_for_each_entry(req, &xprt->bc_pa_list, rq_bc_pa_list) {
+		if (req->rq_connect_cookie != xprt->connect_cookie)
+			continue;
+		if (req->rq_xid == xid)
+			goto found;
+	}
+	req = xprt_alloc_bc_request(xprt, xid);
+found:
+	spin_unlock(&xprt->bc_pa_lock);
+	return req;
+}
+
+/*
+ * Add callback request to callback list.  The callback
+ * service sleeps on the sv_cb_waitq waiting for new
+ * requests.  Wake it up after adding enqueing the
+ * request.
+ */
+void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
+{
+	struct rpc_xprt *xprt = req->rq_xprt;
+	struct svc_serv *bc_serv = xprt->bc_serv;
+
+	req->rq_private_buf.len = copied;
+	set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
+
+	dprintk("RPC:       add callback request to list\n");
+	spin_lock(&bc_serv->sv_cb_lock);
+	list_del(&req->rq_bc_pa_list);
+	list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
+	wake_up(&bc_serv->sv_cb_waitq);
+	spin_unlock(&bc_serv->sv_cb_lock);
+}
+

net/sunrpc/clnt.c

@@ -1363,6 +1363,7 @@ rpc_restart_call_prepare(struct rpc_task *task)
 	if (RPC_ASSASSINATED(task))
 		return 0;
 	task->tk_action = call_start;
+	task->tk_status = 0;
 	if (task->tk_ops->rpc_call_prepare != NULL)
 		task->tk_action = rpc_prepare_task;
 	return 1;
@@ -1379,6 +1380,7 @@ rpc_restart_call(struct rpc_task *task)
 	if (RPC_ASSASSINATED(task))
 		return 0;
 	task->tk_action = call_start;
+	task->tk_status = 0;
 	return 1;
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call);
@@ -1728,9 +1730,7 @@ call_bind_status(struct rpc_task *task)
 	case -EPROTONOSUPPORT:
 		dprintk("RPC: %5u remote rpcbind version unavailable, retrying\n",
 				task->tk_pid);
-		task->tk_status = 0;
-		task->tk_action = call_bind;
-		return;
+		goto retry_timeout;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
 	case -ECONNABORTED:
@@ -1756,6 +1756,7 @@ call_bind_status(struct rpc_task *task)
 	return;
 
 retry_timeout:
+	task->tk_status = 0;
 	task->tk_action = call_timeout;
 }
 
@@ -1798,21 +1799,19 @@ call_connect_status(struct rpc_task *task)
 	trace_rpc_connect_status(task, status);
 	task->tk_status = 0;
 	switch (status) {
-		/* if soft mounted, test if we've timed out */
-	case -ETIMEDOUT:
-		task->tk_action = call_timeout;
-		return;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
-		/* retry with existing socket, after a delay */
-		rpc_delay(task, 3*HZ);
 		if (RPC_IS_SOFTCONN(task))
 			break;
+		/* retry with existing socket, after a delay */
+		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
-		task->tk_action = call_bind;
+		/* Check for timeouts before looping back to call_bind */
+	case -ETIMEDOUT:
+		task->tk_action = call_timeout;
 		return;
 	case 0:
 		clnt->cl_stats->netreconn++;
@@ -2007,6 +2006,10 @@ call_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+		if (RPC_IS_SOFTCONN(task)) {
+			rpc_exit(task, status);
+			break;
+		}
 		/*
 		 * Delay any retries for 3 seconds, then handle as if it
 		 * were a timeout.

net/sunrpc/sched.c

@@ -637,7 +637,8 @@ static void __rpc_queue_timer_fn(unsigned long ptr)
 
 static void __rpc_atrun(struct rpc_task *task)
 {
-	task->tk_status = 0;
+	if (task->tk_status == -ETIMEDOUT)
+		task->tk_status = 0;
 }
 
 /*

net/sunrpc/xprtrdma/rpc_rdma.c

@@ -649,9 +649,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 				break;
 			page_base = 0;
 		}
-		rqst->rq_rcv_buf.page_len = olen - copy_len;
-	} else
-		rqst->rq_rcv_buf.page_len = 0;
+	}
 
 	if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) {
 		curlen = copy_len;

net/sunrpc/xprtrdma/transport.c

@@ -733,7 +733,7 @@ static void __exit xprt_rdma_cleanup(void)
 {
 	int rc;
 
-	dprintk(KERN_INFO "RPCRDMA Module Removed, deregister RPC RDMA transport\n");
+	dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n");
 #ifdef RPC_DEBUG
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
@@ -755,14 +755,14 @@ static int __init xprt_rdma_init(void)
 	if (rc)
 		return rc;
 
-	dprintk(KERN_INFO "RPCRDMA Module Init, register RPC RDMA transport\n");
+	dprintk("RPCRDMA Module Init, register RPC RDMA transport\n");
 
-	dprintk(KERN_INFO "Defaults:\n");
-	dprintk(KERN_INFO "\tSlots %d\n"
+	dprintk("Defaults:\n");
+	dprintk("\tSlots %d\n"
 		"\tMaxInlineRead %d\n\tMaxInlineWrite %d\n",
 		xprt_rdma_slot_table_entries,
 		xprt_rdma_max_inline_read, xprt_rdma_max_inline_write);
-	dprintk(KERN_INFO "\tPadding %d\n\tMemreg %d\n",
+	dprintk("\tPadding %d\n\tMemreg %d\n",
 		xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy);
 
 #ifdef RPC_DEBUG

net/sunrpc/xprtsock.c

@@ -1306,41 +1306,29 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
  * If we're unable to obtain the rpc_rqst we schedule the closing of the
  * connection and return -1.
  */
-static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
+static int xs_tcp_read_callback(struct rpc_xprt *xprt,
 				       struct xdr_skb_reader *desc)
 {
 	struct sock_xprt *transport =
 				container_of(xprt, struct sock_xprt, xprt);
 	struct rpc_rqst *req;
 
-	req = xprt_alloc_bc_request(xprt);
+	/* Look up and lock the request corresponding to the given XID */
+	spin_lock(&xprt->transport_lock);
+	req = xprt_lookup_bc_request(xprt, transport->tcp_xid);
 	if (req == NULL) {
+		spin_unlock(&xprt->transport_lock);
 		printk(KERN_WARNING "Callback slot table overflowed\n");
 		xprt_force_disconnect(xprt);
 		return -1;
 	}
 
-	req->rq_xid = transport->tcp_xid;
 	dprintk("RPC:       read callback  XID %08x\n", ntohl(req->rq_xid));
 	xs_tcp_read_common(xprt, desc, req);
 
-	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
-		struct svc_serv *bc_serv = xprt->bc_serv;
-
-		/*
-		 * Add callback request to callback list.  The callback
-		 * service sleeps on the sv_cb_waitq waiting for new
-		 * requests.  Wake it up after adding enqueing the
-		 * request.
-		 */
-		dprintk("RPC:       add callback request to list\n");
-		spin_lock(&bc_serv->sv_cb_lock);
-		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
-		spin_unlock(&bc_serv->sv_cb_lock);
-		wake_up(&bc_serv->sv_cb_waitq);
-	}
-
-	req->rq_private_buf.len = transport->tcp_copied;
+	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
+		xprt_complete_bc_request(req, transport->tcp_copied);
+	spin_unlock(&xprt->transport_lock);
 
 	return 0;
 }