--- zzzz-none-000/linux-3.10.107/fs/nfsd/nfs4recover.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/fs/nfsd/nfs4recover.c	2021-02-04 17:41:59.000000000 +0000
@@ -58,7 +58,7 @@
 	void (*create)(struct nfs4_client *);
 	void (*remove)(struct nfs4_client *);
 	int (*check)(struct nfs4_client *);
-	void (*grace_done)(struct nfsd_net *, time_t);
+	void (*grace_done)(struct nfsd_net *);
 };
 
 /* Globals */
@@ -173,8 +173,6 @@
 	int status;
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 
-	dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
-
 	if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
 		return;
 	if (!nn->rec_file)
@@ -190,18 +188,18 @@
 
 	status = mnt_want_write_file(nn->rec_file);
 	if (status)
-		return;
+		goto out_creds;
 
 	dir = nn->rec_file->f_path.dentry;
 	/* lock the parent */
-	mutex_lock(&dir->d_inode->i_mutex);
+	mutex_lock(&d_inode(dir)->i_mutex);
 
 	dentry = lookup_one_len(dname, dir, HEXDIR_LEN-1);
 	if (IS_ERR(dentry)) {
 		status = PTR_ERR(dentry);
 		goto out_unlock;
 	}
-	if (dentry->d_inode)
+	if (d_really_is_positive(dentry))
 		/*
 		 * In the 4.1 case, where we're called from
 		 * reclaim_complete(), records from the previous reboot
@@ -211,11 +209,11 @@
 		 * as well be forgiving and just succeed silently.
 		 */
 		goto out_put;
-	status = vfs_mkdir(dir->d_inode, dentry, S_IRWXU);
+	status = vfs_mkdir(d_inode(dir), dentry, S_IRWXU);
 out_put:
 	dput(dentry);
 out_unlock:
-	mutex_unlock(&dir->d_inode->i_mutex);
+	mutex_unlock(&d_inode(dir)->i_mutex);
 	if (status == 0) {
 		if (nn->in_grace) {
 			crp = nfs4_client_to_reclaim(dname, nn);
@@ -230,6 +228,7 @@
 				user_recovery_dirname);
 	}
 	mnt_drop_write_file(nn->rec_file);
+out_creds:
 	nfs4_reset_creds(original_cred);
 }
 
@@ -240,11 +239,17 @@
 	struct list_head list;
 };
 
+struct nfs4_dir_ctx {
+	struct dir_context ctx;
+	struct list_head names;
+};
+
 static int
-nfsd4_build_namelist(void *arg, const char *name, int namlen,
+nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct list_head *names = arg;
+	struct nfs4_dir_ctx *ctx =
+		container_of(__ctx, struct nfs4_dir_ctx, ctx);
 	struct name_list *entry;
 
 	if (namlen != HEXDIR_LEN - 1)
@@ -254,7 +259,7 @@
 		return -ENOMEM;
 	memcpy(entry->name, name, HEXDIR_LEN - 1);
 	entry->name[HEXDIR_LEN - 1] = '\0';
-	list_add(&entry->list, names);
+	list_add(&entry->list, &ctx->names);
 	return 0;
 }
 
@@ -263,7 +268,11 @@
 {
 	const struct cred *original_cred;
 	struct dentry *dir = nn->rec_file->f_path.dentry;
-	LIST_HEAD(names);
+	struct nfs4_dir_ctx ctx = {
+		.ctx.actor = nfsd4_build_namelist,
+		.names = LIST_HEAD_INIT(ctx.names)
+	};
+	struct name_list *entry, *tmp;
 	int status;
 
 	status = nfs4_save_creds(&original_cred);
@@ -276,11 +285,10 @@
 		return status;
 	}
 
-	status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names);
-	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
-	while (!list_empty(&names)) {
-		struct name_list *entry;
-		entry = list_entry(names.next, struct name_list, list);
+	status = iterate_dir(nn->rec_file, &ctx.ctx);
+	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
+
+	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
 		if (!status) {
 			struct dentry *dentry;
 			dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1);
@@ -294,8 +302,14 @@
 		list_del(&entry->list);
 		kfree(entry);
 	}
-	mutex_unlock(&dir->d_inode->i_mutex);
+	mutex_unlock(&d_inode(dir)->i_mutex);
 	nfs4_reset_creds(original_cred);
+
+	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
+		dprintk("NFSD: %s. Left entry %s\n", __func__, entry->name);
+		list_del(&entry->list);
+		kfree(entry);
+	}
 	return status;
 }
 
@@ -308,20 +322,20 @@
 	dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
 
 	dir = nn->rec_file->f_path.dentry;
-	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
+	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_one_len(name, dir, namlen);
 	if (IS_ERR(dentry)) {
 		status = PTR_ERR(dentry);
 		goto out_unlock;
 	}
 	status = -ENOENT;
-	if (!dentry->d_inode)
+	if (d_really_is_negative(dentry))
 		goto out;
-	status = vfs_rmdir(dir->d_inode, dentry);
+	status = vfs_rmdir(d_inode(dir), dentry);
 out:
 	dput(dentry);
 out_unlock:
-	mutex_unlock(&dir->d_inode->i_mutex);
+	mutex_unlock(&d_inode(dir)->i_mutex);
 	return status;
 }
 
@@ -377,16 +391,16 @@
 	if (nfs4_has_reclaimed_state(child->d_name.name, nn))
 		return 0;
 
-	status = vfs_rmdir(parent->d_inode, child);
+	status = vfs_rmdir(d_inode(parent), child);
 	if (status)
-		printk("failed to remove client recovery directory %s\n",
-				child->d_name.name);
+		printk("failed to remove client recovery directory %pd\n",
+				child);
 	/* Keep trying, success or failure: */
 	return 0;
 }
 
 static void
-nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time)
+nfsd4_recdir_purge_old(struct nfsd_net *nn)
 {
 	int status;
 
@@ -404,15 +418,15 @@
 	nfs4_release_reclaim(nn);
 	if (status)
 		printk("nfsd4: failed to purge old clients from recovery"
-			" directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
+			" directory %pD\n", nn->rec_file);
 }
 
 static int
 load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
 {
 	if (child->d_name.len != HEXDIR_LEN - 1) {
-		printk("nfsd4: illegal name %s in recovery directory\n",
-				child->d_name.name);
+		printk("nfsd4: illegal name %pd in recovery directory\n",
+				child);
 		/* Keep trying; maybe the others are OK: */
 		return 0;
 	}
@@ -431,7 +445,7 @@
 	status = nfsd4_list_rec_dir(load_recdir, nn);
 	if (status)
 		printk("nfsd4: failed loading clients from recovery"
-			" directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
+			" directory %pD\n", nn->rec_file);
 	return status;
 }
 
@@ -473,6 +487,16 @@
 	return status;
 }
 
+static void
+nfsd4_shutdown_recdir(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (!nn->rec_file)
+		return;
+	fput(nn->rec_file);
+	nn->rec_file = NULL;
+}
 
 static int
 nfs4_legacy_state_init(struct net *net)
@@ -506,10 +530,13 @@
 	int status;
 
 	status = nfsd4_init_recdir(net);
-	if (!status)
-		status = nfsd4_recdir_load(net);
 	if (status)
-		printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+		return status;
+
+	status = nfsd4_recdir_load(net);
+	if (status)
+		nfsd4_shutdown_recdir(net);
+
 	return status;
 }
 
@@ -520,8 +547,7 @@
 
 	/* XXX: The legacy code won't work in a container */
 	if (net != &init_net) {
-		WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
-			"tracking in a container!\n");
+		pr_warn("NFSD: attempt to initialize legacy client tracking in a container ignored.\n");
 		return -EINVAL;
 	}
 
@@ -540,21 +566,12 @@
 }
 
 static void
-nfsd4_shutdown_recdir(struct nfsd_net *nn)
-{
-	if (!nn->rec_file)
-		return;
-	fput(nn->rec_file);
-	nn->rec_file = NULL;
-}
-
-static void
 nfsd4_legacy_tracking_exit(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	nfs4_release_reclaim(nn);
-	nfsd4_shutdown_recdir(nn);
+	nfsd4_shutdown_recdir(net);
 	nfs4_legacy_state_shutdown(net);
 }
 
@@ -571,7 +588,7 @@
 	if (status)
 		return status;
 	status = -ENOTDIR;
-	if (S_ISDIR(path.dentry->d_inode->i_mode)) {
+	if (d_is_dir(path.dentry)) {
 		strcpy(user_recovery_dirname, recdir);
 		status = 0;
 	}
@@ -664,7 +681,6 @@
 	}
 
 	schedule();
-	set_current_state(TASK_RUNNING);
 
 	if (msg.errno < 0)
 		ret = msg.errno;
@@ -694,7 +710,7 @@
 	struct cld_upcall *tmp, *cup;
 	struct cld_msg __user *cmsg = (struct cld_msg __user *)src;
 	uint32_t xid;
-	struct nfsd_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+	struct nfsd_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info,
 						nfsd_net_id);
 	struct cld_net *cn = nn->cld_net;
 
@@ -1010,7 +1026,7 @@
 }
 
 static void
-nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
+nfsd4_cld_grace_done(struct nfsd_net *nn)
 {
 	int ret;
 	struct cld_upcall *cup;
@@ -1023,7 +1039,7 @@
 	}
 
 	cup->cu_msg.cm_cmd = Cld_GraceDone;
-	cup->cu_msg.cm_u.cm_gracetime = (int64_t)boot_time;
+	cup->cu_msg.cm_u.cm_gracetime = (int64_t)nn->boot_time;
 	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
 	if (!ret)
 		ret = cup->cu_msg.cm_status;
@@ -1056,6 +1072,8 @@
 
 #define LEGACY_TOPDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_TOPDIR="
 #define LEGACY_RECDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_RECDIR="
+#define HAS_SESSION_ENV_PREFIX "NFSDCLTRACK_CLIENT_HAS_SESSION="
+#define GRACE_START_ENV_PREFIX "NFSDCLTRACK_GRACE_START="
 
 static char *
 nfsd4_cltrack_legacy_topdir(void)
@@ -1120,10 +1138,60 @@
 	return result;
 }
 
+static char *
+nfsd4_cltrack_client_has_session(struct nfs4_client *clp)
+{
+	int copied;
+	size_t len;
+	char *result;
+
+	/* prefix + Y/N character + terminating NULL */
+	len = strlen(HAS_SESSION_ENV_PREFIX) + 1 + 1;
+
+	result = kmalloc(len, GFP_KERNEL);
+	if (!result)
+		return result;
+
+	copied = snprintf(result, len, HAS_SESSION_ENV_PREFIX "%c",
+				clp->cl_minorversion ? 'Y' : 'N');
+	if (copied >= len) {
+		/* just return nothing if output was truncated */
+		kfree(result);
+		return NULL;
+	}
+
+	return result;
+}
+
+static char *
+nfsd4_cltrack_grace_start(time_t grace_start)
+{
+	int copied;
+	size_t len;
+	char *result;
+
+	/* prefix + max width of int64_t string + terminating NULL */
+	len = strlen(GRACE_START_ENV_PREFIX) + 22 + 1;
+
+	result = kmalloc(len, GFP_KERNEL);
+	if (!result)
+		return result;
+
+	copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%ld",
+				grace_start);
+	if (copied >= len) {
+		/* just return nothing if output was truncated */
+		kfree(result);
+		return NULL;
+	}
+
+	return result;
+}
+
 static int
-nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
+nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *env0, char *env1)
 {
-	char *envp[2];
+	char *envp[3];
 	char *argv[4];
 	int ret;
 
@@ -1134,10 +1202,12 @@
 
 	dprintk("%s: cmd: %s\n", __func__, cmd);
 	dprintk("%s: arg: %s\n", __func__, arg ? arg : "(null)");
-	dprintk("%s: legacy: %s\n", __func__, legacy ? legacy : "(null)");
+	dprintk("%s: env0: %s\n", __func__, env0 ? env0 : "(null)");
+	dprintk("%s: env1: %s\n", __func__, env1 ? env1 : "(null)");
 
-	envp[0] = legacy;
-	envp[1] = NULL;
+	envp[0] = env0;
+	envp[1] = env1;
+	envp[2] = NULL;
 
 	argv[0] = (char *)cltrack_prog;
 	argv[1] = cmd;
@@ -1181,28 +1251,77 @@
 }
 
 static int
-nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
+nfsd4_umh_cltrack_init(struct net *net)
 {
+	int ret;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	char *grace_start = nfsd4_cltrack_grace_start(nn->boot_time);
+
 	/* XXX: The usermode helper s not working in container yet. */
 	if (net != &init_net) {
-		WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
-			"tracking in a container!\n");
+		pr_warn("NFSD: attempt to initialize umh client tracking in a container ignored.\n");
 		return -EINVAL;
 	}
-	return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
+
+	ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL);
+	kfree(grace_start);
+	return ret;
+}
+
+static void
+nfsd4_cltrack_upcall_lock(struct nfs4_client *clp)
+{
+	wait_on_bit_lock(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK,
+			 TASK_UNINTERRUPTIBLE);
+}
+
+static void
+nfsd4_cltrack_upcall_unlock(struct nfs4_client *clp)
+{
+	smp_mb__before_atomic();
+	clear_bit(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK);
 }
 
 static void
 nfsd4_umh_cltrack_create(struct nfs4_client *clp)
 {
-	char *hexid;
+	char *hexid, *has_session, *grace_start;
+	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+	/*
+	 * With v4.0 clients, there's little difference in outcome between a
+	 * create and check operation, and we can end up calling into this
+	 * function multiple times per client (once for each openowner). So,
+	 * for v4.0 clients skip upcalling once the client has been recorded
+	 * on stable storage.
+	 *
+	 * For v4.1+ clients, the outcome of the two operations is different,
+	 * so we must ensure that we upcall for the create operation. v4.1+
+	 * clients call this on RECLAIM_COMPLETE though, so we should only end
+	 * up doing a single create upcall per client.
+	 */
+	if (clp->cl_minorversion == 0 &&
+	    test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
 
 	hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
 	if (!hexid) {
 		dprintk("%s: can't allocate memory for upcall!\n", __func__);
 		return;
 	}
-	nfsd4_umh_cltrack_upcall("create", hexid, NULL);
+
+	has_session = nfsd4_cltrack_client_has_session(clp);
+	grace_start = nfsd4_cltrack_grace_start(nn->boot_time);
+
+	nfsd4_cltrack_upcall_lock(clp);
+	if (!nfsd4_umh_cltrack_upcall("create", hexid, has_session, grace_start))
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	nfsd4_cltrack_upcall_unlock(clp);
+
+	kfree(has_session);
+	kfree(grace_start);
 	kfree(hexid);
 }
 
@@ -1211,12 +1330,21 @@
 {
 	char *hexid;
 
+	if (!test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
+
 	hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
 	if (!hexid) {
 		dprintk("%s: can't allocate memory for upcall!\n", __func__);
 		return;
 	}
-	nfsd4_umh_cltrack_upcall("remove", hexid, NULL);
+
+	nfsd4_cltrack_upcall_lock(clp);
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags) &&
+	    nfsd4_umh_cltrack_upcall("remove", hexid, NULL, NULL) == 0)
+		clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	nfsd4_cltrack_upcall_unlock(clp);
+
 	kfree(hexid);
 }
 
@@ -1224,30 +1352,45 @@
 nfsd4_umh_cltrack_check(struct nfs4_client *clp)
 {
 	int ret;
-	char *hexid, *legacy;
+	char *hexid, *has_session, *legacy;
+
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return 0;
 
 	hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
 	if (!hexid) {
 		dprintk("%s: can't allocate memory for upcall!\n", __func__);
 		return -ENOMEM;
 	}
+
+	has_session = nfsd4_cltrack_client_has_session(clp);
 	legacy = nfsd4_cltrack_legacy_recdir(&clp->cl_name);
-	ret = nfsd4_umh_cltrack_upcall("check", hexid, legacy);
+
+	nfsd4_cltrack_upcall_lock(clp);
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) {
+		ret = 0;
+	} else {
+		ret = nfsd4_umh_cltrack_upcall("check", hexid, has_session, legacy);
+		if (ret == 0)
+			set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+	nfsd4_cltrack_upcall_unlock(clp);
+	kfree(has_session);
 	kfree(legacy);
 	kfree(hexid);
+
 	return ret;
 }
 
 static void
-nfsd4_umh_cltrack_grace_done(struct nfsd_net __attribute__((unused)) *nn,
-				time_t boot_time)
+nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
 {
 	char *legacy;
 	char timestr[22]; /* FIXME: better way to determine max size? */
 
-	sprintf(timestr, "%ld", boot_time);
+	sprintf(timestr, "%ld", nn->boot_time);
 	legacy = nfsd4_cltrack_legacy_topdir();
-	nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy);
+	nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy, NULL);
 	kfree(legacy);
 }
 
@@ -1287,7 +1430,7 @@
 	nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
 	status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
 	if (!status) {
-		status = S_ISDIR(path.dentry->d_inode->i_mode);
+		status = d_is_dir(path.dentry);
 		path_put(&path);
 		if (status)
 			goto do_init;
@@ -1350,10 +1493,10 @@
 }
 
 void
-nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time)
+nfsd4_record_grace_done(struct nfsd_net *nn)
 {
 	if (nn->client_tracking_ops)
-		nn->client_tracking_ops->grace_done(nn, boot_time);
+		nn->client_tracking_ops->grace_done(nn);
 }
 
 static int