29 files changed, 428 insertions, 128 deletions

diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 57f91311fdaa..007427ba75e5 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -176,7 +176,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 		}
 	}
 
-	rc = dns_resolve_server_name_to_ip(name, &srvIP);
+	rc = dns_resolve_server_name_to_ip(name, &srvIP, NULL);
 	if (rc < 0) {
 		cifs_dbg(FYI, "%s: Failed to resolve server part of %s to IP: %d\n",
 			 __func__, name, rc);
@@ -211,6 +211,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 		else
 			noff = tkn_e - (sb_mountdata + off) + 1;
 
+		if (strncasecmp(sb_mountdata + off, "cruid=", 6) == 0) {
+			off += noff;
+			continue;
+		}
 		if (strncasecmp(sb_mountdata + off, "unc=", 4) == 0) {
 			off += noff;
 			continue;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 3c2e117bb926..c0bfc2f01030 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -75,6 +75,9 @@
 #define SMB_ECHO_INTERVAL_MAX 600
 #define SMB_ECHO_INTERVAL_DEFAULT 60
 
+/* dns resolution interval in seconds */
+#define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600
+
 /* maximum number of PDUs in one compound */
 #define MAX_COMPOUND 5
 
@@ -646,6 +649,7 @@ struct TCP_Server_Info {
 	/* point to the SMBD connection if RDMA is used instead of socket */
 	struct smbd_connection *smbd_conn;
 	struct delayed_work	echo; /* echo ping workqueue job */
+	struct delayed_work	resolve; /* dns resolution workqueue job */
 	char	*smallbuf;	/* pointer to current "small" buffer */
 	char	*bigbuf;	/* pointer to current "big" buffer */
 	/* Total size of this PDU. Only valid from cifs_demultiplex_thread */
@@ -689,6 +693,9 @@ struct TCP_Server_Info {
 	bool use_swn_dstaddr;
 	struct sockaddr_storage swn_dstaddr;
 #endif
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	bool is_dfs_conn; /* if a dfs connection */
+#endif
 };
 
 struct cifs_credits {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 01dc45178f66..1b04d6ec14dd 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -78,6 +78,8 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	int rc;
 	int len;
 	char *unc, *ipaddr = NULL;
+	time64_t expiry, now;
+	unsigned long ttl = SMB_DNS_RESOLVE_INTERVAL_DEFAULT;
 
 	if (!server->hostname)
 		return -EINVAL;
@@ -91,13 +93,13 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	}
 	scnprintf(unc, len, "\\\\%s", server->hostname);
 
-	rc = dns_resolve_server_name_to_ip(unc, &ipaddr);
+	rc = dns_resolve_server_name_to_ip(unc, &ipaddr, &expiry);
 	kfree(unc);
 
 	if (rc < 0) {
 		cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n",
 			 __func__, server->hostname, rc);
-		return rc;
+		goto requeue_resolve;
 	}
 
 	spin_lock(&cifs_tcp_ses_lock);
@@ -106,7 +108,45 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	spin_unlock(&cifs_tcp_ses_lock);
 	kfree(ipaddr);
 
-	return !rc ? -1 : 0;
+	/* rc == 1 means success here */
+	if (rc) {
+		now = ktime_get_real_seconds();
+		if (expiry && expiry > now)
+			/*
+			 * To make sure we don't use the cached entry, retry 1s
+			 * after expiry.
+			 */
+			ttl = (expiry - now + 1);
+	}
+	rc = !rc ? -1 : 0;
+
+requeue_resolve:
+	cifs_dbg(FYI, "%s: next dns resolution scheduled for %lu seconds in the future\n",
+		 __func__, ttl);
+	mod_delayed_work(cifsiod_wq, &server->resolve, (ttl * HZ));
+
+	return rc;
+}
+
+
+static void cifs_resolve_server(struct work_struct *work)
+{
+	int rc;
+	struct TCP_Server_Info *server = container_of(work,
+					struct TCP_Server_Info, resolve.work);
+
+	mutex_lock(&server->srv_mutex);
+
+	/*
+	 * Resolve the hostname again to make sure that IP address is up-to-date.
+	 */
+	rc = reconn_set_ipaddr_from_hostname(server);
+	if (rc) {
+		cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+				__func__, rc);
+	}
+
+	mutex_unlock(&server->srv_mutex);
 }
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
@@ -680,6 +720,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	cancel_delayed_work_sync(&server->echo);
+	cancel_delayed_work_sync(&server->resolve);
 
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
@@ -1227,6 +1268,16 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx)
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		/*
+		 * DFS failover implementation in cifs_reconnect() requires unique tcp sessions for
+		 * DFS connections to do failover properly, so avoid sharing them with regular
+		 * shares or even links that may connect to same server but having completely
+		 * different failover targets.
+		 */
+		if (server->is_dfs_conn)
+			continue;
+#endif
 		/*
 		 * Skip ses channels since they're only handled in lower layers
 		 * (e.g. cifs_send_recv).
@@ -1254,12 +1305,16 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 		return;
 	}
 
+	/* srv_count can never go negative */
+	WARN_ON(server->srv_count < 0);
+
 	put_net(cifs_net_ns(server));
 
 	list_del_init(&server->tcp_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	cancel_delayed_work_sync(&server->echo);
+	cancel_delayed_work_sync(&server->resolve);
 
 	if (from_reconnect)
 		/*
@@ -1342,6 +1397,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx)
 	INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
 	INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
 	INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);
+	INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server);
 	INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server);
 	mutex_init(&tcp_ses->reconnect_mutex);
 	memcpy(&tcp_ses->srcaddr, &ctx->srcaddr,
@@ -1427,6 +1483,12 @@ smbd_connected:
 	/* queue echo request delayed work */
 	queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval);
 
+	/* queue dns resolution delayed work */
+	cifs_dbg(FYI, "%s: next dns resolution scheduled for %d seconds in the future\n",
+		 __func__, SMB_DNS_RESOLVE_INTERVAL_DEFAULT);
+
+	queue_delayed_work(cifsiod_wq, &tcp_ses->resolve, (SMB_DNS_RESOLVE_INTERVAL_DEFAULT * HZ));
+
 	return tcp_ses;
 
 out_err_crypto_release:
@@ -1605,6 +1667,9 @@ void cifs_put_smb_ses(struct cifs_ses *ses)
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	/* ses_count can never go negative */
+	WARN_ON(ses->ses_count < 0);
+
 	spin_lock(&GlobalMid_Lock);
 	if (ses->status == CifsGood)
 		ses->status = CifsExiting;
@@ -1972,6 +2037,9 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 		return;
 	}
 
+	/* tc_count can never go negative */
+	WARN_ON(tcon->tc_count < 0);
+
 	if (tcon->use_witness) {
 		int rc;
 
@@ -2910,6 +2978,23 @@ static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 }
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
+static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb,
+			       unsigned int *xid, struct TCP_Server_Info **nserver,
+			       struct cifs_ses **nses, struct cifs_tcon **ntcon)
+{
+	int rc;
+
+	ctx->nosharesock = true;
+	rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon);
+	if (*nserver) {
+		cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__);
+		spin_lock(&cifs_tcp_ses_lock);
+		(*nserver)->is_dfs_conn = true;
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
+	return rc;
+}
+
 /*
  * cifs_build_path_to_root returns full path to root when we do not have an
  * existing connection (tcon)
@@ -3105,7 +3190,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_
 			 tmp_ctx.prepath);
 
 		mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon);
-		rc = mount_get_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon);
+		rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon);
 		if (!rc || (*server && *ses)) {
 			/*
 			 * We were able to connect to new target server. Update current context with
@@ -3404,7 +3489,12 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 			goto error;
 	}
 
-	ctx->nosharesock = true;
+	mount_put_conns(cifs_sb, xid, server, ses, tcon);
+	/*
+	 * Ignore error check here because we may failover to other targets from cached a
+	 * referral.
+	 */
+	(void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
 
 	/* Get path of DFS root */
 	ref_path = build_unc_path_to_root(ctx, cifs_sb, false);
@@ -3433,7 +3523,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 		/* Connect to new DFS target only if we were redirected */
 		if (oldmnt != cifs_sb->ctx->mount_options) {
 			mount_put_conns(cifs_sb, xid, server, ses, tcon);
-			rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
+			rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
 		}
 		if (rc && !server && !ses) {
 			/* Failed to connect. Try to connect to other targets in the referral. */
@@ -3459,7 +3549,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 			rc = -ELOOP;
 	} while (rc == -EREMOTE);
 
-	if (rc || !tcon)
+	if (rc || !tcon || !ses)
 		goto error;
 
 	kfree(ref_path);
@@ -4095,7 +4185,8 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 	if (!tree)
 		return -ENOMEM;
 
-	if (!tcon->dfs_path) {
+	/* If it is not dfs or there was no cached dfs referral, then reconnect to same share */
+	if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) {
 		if (tcon->ipc) {
 			scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
 			rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
@@ -4105,9 +4196,6 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 		goto out;
 	}
 
-	rc = dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl);
-	if (rc)
-		goto out;
 	isroot = ref.server_type == DFS_TYPE_ROOT;
 	free_dfs_info_param(&ref);
 
diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c
index d15b82d569ef..8c616aaeb7c4 100644
--- a/fs/cifs/dns_resolve.c
+++ b/fs/cifs/dns_resolve.c
@@ -24,6 +24,7 @@
  * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address.
  * @unc: UNC path specifying the server (with '/' as delimiter)
  * @ip_addr: Where to return the IP address.
+ * @expiry: Where to return the expiry time for the dns record.
  *
  * The IP address will be returned in string form, and the caller is
  * responsible for freeing it.
@@ -31,7 +32,7 @@
  * Returns length of result on success, -ve on error.
  */
 int
-dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
+dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry)
 {
 	struct sockaddr_storage ss;
 	const char *hostname, *sep;
@@ -66,13 +67,14 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
 
 	/* Perform the upcall */
 	rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len,
-		       NULL, ip_addr, NULL, false);
+		       NULL, ip_addr, expiry, false);
 	if (rc < 0)
 		cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n",
 			 __func__, len, len, hostname);
 	else
-		cifs_dbg(FYI, "%s: resolved: %*.*s to %s\n",
-			 __func__, len, len, hostname, *ip_addr);
+		cifs_dbg(FYI, "%s: resolved: %*.*s to %s expiry %llu\n",
+			 __func__, len, len, hostname, *ip_addr,
+			 expiry ? (*expiry) : 0);
 	return rc;
 
 name_is_IP_address:
diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h
index 5be060b82b13..9fa2807ef79e 100644
--- a/fs/cifs/dns_resolve.h
+++ b/fs/cifs/dns_resolve.h
@@ -12,7 +12,7 @@
 #define _DNS_RESOLVE_H
 
 #ifdef __KERNEL__
-extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr);
+extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry);
 #endif /* KERNEL */
 
 #endif /* _DNS_RESOLVE_H */
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 184138b4eb8c..844abeb2b48f 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1187,7 +1187,7 @@ int match_target_ip(struct TCP_Server_Info *server,
 
 	cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2);
 
-	rc = dns_resolve_server_name_to_ip(target, &tip);
+	rc = dns_resolve_server_name_to_ip(target, &tip, NULL);
 	if (rc < 0)
 		goto out;
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index e4c8f603dd58..ba3c58e1f725 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -557,8 +557,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 	p = buf;
 	while (bytes_left >= sizeof(*p)) {
 		info->speed = le64_to_cpu(p->LinkSpeed);
-		info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE);
-		info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE);
+		info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0;
+		info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0;
 
 		cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count);
 		cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed);
@@ -2910,6 +2910,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 		/* ipc tcons are not refcounted */
 		spin_lock(&cifs_tcp_ses_lock);
 		tcon->tc_count--;
+		/* tc_count can never go negative */
+		WARN_ON(tcon->tc_count < 0);
 		spin_unlock(&cifs_tcp_ses_lock);
 	}
 	kfree(utf16_path);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 4b27cb9105fd..e9cac7970b66 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -394,6 +394,7 @@ struct smb2_compression_capabilities_context {
 	__u16	Padding;
 	__u32	Flags;
 	__le16	CompressionAlgorithms[3];
+	__u16	Pad;  /* Some servers require pad to DataLen multiple of 8 */
 	/* Check if pad needed */
 } __packed;
 
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 2f63bf3a7325..5a0be9985bae 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -91,7 +91,10 @@ static ssize_t configfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	}
 	pr_debug("%s: count = %zd, pos = %lld, buf = %s\n",
 		 __func__, iov_iter_count(to), iocb->ki_pos, buffer->page);
-	retval = copy_to_iter(buffer->page, buffer->count, to);
+	if (iocb->ki_pos >= buffer->count)
+		goto out;
+	retval = copy_to_iter(buffer->page + iocb->ki_pos,
+			      buffer->count - iocb->ki_pos, to);
 	iocb->ki_pos += retval;
 	if (retval == 0)
 		retval = -EFAULT;
@@ -162,7 +165,10 @@ static ssize_t configfs_bin_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		buffer->needs_read_fill = 0;
 	}
 
-	retval = copy_to_iter(buffer->bin_buffer, buffer->bin_buffer_size, to);
+	if (iocb->ki_pos >= buffer->bin_buffer_size)
+		goto out;
+	retval = copy_to_iter(buffer->bin_buffer + iocb->ki_pos,
+			      buffer->bin_buffer_size - iocb->ki_pos, to);
 	iocb->ki_pos += retval;
 	if (retval == 0)
 		retval = -EFAULT;
@@ -171,21 +177,28 @@ out:
 	return retval;
 }
 
-static int fill_write_buffer(struct configfs_buffer *buffer,
+/* Fill [buffer, buffer + pos) with data coming from @from. */
+static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos,
 			     struct iov_iter *from)
 {
+	loff_t to_copy;
 	int copied;
+	u8 *to;
 
 	if (!buffer->page)
 		buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0);
 	if (!buffer->page)
 		return -ENOMEM;
 
-	copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from);
+	to_copy = SIMPLE_ATTR_SIZE - 1 - pos;
+	if (to_copy <= 0)
+		return 0;
+	to = buffer->page + pos;
+	copied = copy_from_iter(to, to_copy, from);
 	buffer->needs_read_fill = 1;
 	/* if buf is assumed to contain a string, terminate it by \0,
 	 * so e.g. sscanf() can scan the string easily */
-	buffer->page[copied] = 0;
+	to[copied] = 0;
 	return copied ? : -EFAULT;
 }
 
@@ -217,7 +230,7 @@ static ssize_t configfs_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t len;
 
 	mutex_lock(&buffer->mutex);
-	len = fill_write_buffer(buffer, from);
+	len = fill_write_buffer(buffer, iocb->ki_pos, from);
 	if (len > 0)
 		len = flush_write_buffer(file, buffer, len);
 	if (len > 0)
@@ -272,7 +285,9 @@ static ssize_t configfs_bin_write_iter(struct kiocb *iocb,
 		buffer->bin_buffer_size = end_offset;
 	}
 
-	len = copy_from_iter(buffer->bin_buffer, buffer->bin_buffer_size, from);
+	len = copy_from_iter(buffer->bin_buffer + iocb->ki_pos,
+			     buffer->bin_buffer_size - iocb->ki_pos, from);
+	iocb->ki_pos += len;
 out:
 	mutex_unlock(&buffer->mutex);
 	return len ? : -EFAULT;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index dfc72f15be7f..f946bec8f1f1 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -369,8 +369,8 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	/* 32-bit arches must use fcntl64() */
 	case F_OFD_SETLK:
 	case F_OFD_SETLKW:
-#endif
 		fallthrough;
+#endif
 	case F_SETLK:
 	case F_SETLKW:
 		if (copy_from_user(&flock, argp, sizeof(flock)))
diff --git a/fs/fs_context.c b/fs/fs_context.c
index 2834d1afa6e8..de1985eae535 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -80,6 +80,35 @@ static int vfs_parse_sb_flag(struct fs_context *fc, const char *key)
 }
 
 /**
+ * vfs_parse_fs_param_source - Handle setting "source" via parameter
+ * @fc: The filesystem context to modify
+ * @param: The parameter
+ *
+ * This is a simple helper for filesystems to verify that the "source" they
+ * accept is sane.
+ *
+ * Returns 0 on success, -ENOPARAM if this is not  "source" parameter, and
+ * -EINVAL otherwise. In the event of failure, supplementary error information
+ *  is logged.
+ */
+int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param)
+{
+	if (strcmp(param->key, "source") != 0)
+		return -ENOPARAM;
+
+	if (param->type != fs_value_is_string)
+		return invalf(fc, "Non-string source");
+
+	if (fc->source)
+		return invalf(fc, "Multiple sources");
+
+	fc->source = param->string;
+	param->string = NULL;
+	return 0;
+}
+EXPORT_SYMBOL(vfs_parse_fs_param_source);
+
+/**
  * vfs_parse_fs_param - Add a single parameter to a superblock config
  * @fc: The filesystem context to modify
  * @param: The parameter
@@ -122,15 +151,9 @@ int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param)
 	/* If the filesystem doesn't take any arguments, give it the
 	 * default handling of source.
 	 */
-	if (strcmp(param->key, "source") == 0) {
-		if (param->type != fs_value_is_string)
-			return invalf(fc, "VFS: Non-string source");
-		if (fc->source)
-			return invalf(fc, "VFS: Multiple sources");
-		fc->source = param->string;
-		param->string = NULL;
-		return 0;
-	}
+	ret = vfs_parse_fs_param_source(fc, param);
+	if (ret != -ENOPARAM)
+		return ret;
 
 	return invalf(fc, "%s: Unknown parameter '%s'",
 		      fc->fs_type->name, param->key);
@@ -504,16 +527,11 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	struct legacy_fs_context *ctx = fc->fs_private;
 	unsigned int size = ctx->data_size;
 	size_t len = 0;
+	int ret;
 
-	if (strcmp(param->key, "source") == 0) {
-		if (param->type != fs_value_is_string)
-			return invalf(fc, "VFS: Legacy: Non-string source");
-		if (fc->source)
-			return invalf(fc, "VFS: Legacy: Multiple sources");
-		fc->source = param->string;
-		param->string = NULL;
-		return 0;
-	}
+	ret = vfs_parse_fs_param_source(fc, param);
+	if (ret != -ENOPARAM)
+		return ret;
 
 	if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS)
 		return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options");
diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c
index 4af318fbda77..ef9498a6e88a 100644
--- a/fs/hfs/bfind.c
+++ b/fs/hfs/bfind.c
@@ -25,7 +25,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
 	fd->key = ptr + tree->max_key_len + 2;
 	hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n",
 		tree->cnid, __builtin_return_address(0));
-	mutex_lock(&tree->tree_lock);
+	switch (tree->cnid) {
+	case HFS_CAT_CNID:
+		mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
+		break;
+	case HFS_EXT_CNID:
+		mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
+		break;
+	case HFS_ATTR_CNID:
+		mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
+		break;
+	default:
+		return -EINVAL;
+	}
 	return 0;
 }
 
diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c
index b63a4df7327b..c0a73a6ffb28 100644
--- a/fs/hfs/bnode.c
+++ b/fs/hfs/bnode.c
@@ -15,16 +15,31 @@
 
 #include "btree.h"
 
-void hfs_bnode_read(struct hfs_bnode *node, void *buf,
-		int off, int len)
+void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
 {
 	struct page *page;
+	int pagenum;
+	int bytes_read;
+	int bytes_to_read;
+	void *vaddr;
 
 	off += node->page_offset;
-	page = node->page[0];
+	pagenum = off >> PAGE_SHIFT;
+	off &= ~PAGE_MASK; /* compute page offset for the first page */
 
-	memcpy(buf, kmap(page) + off, len);
-	kunmap(page);
+	for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) {
+		if (pagenum >= node->tree->pages_per_bnode)
+			break;
+		page = node->page[pagenum];
+		bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off);
+
+		vaddr = kmap_atomic(page);
+		memcpy(buf + bytes_read, vaddr + off, bytes_to_read);
+		kunmap_atomic(vaddr);
+
+		pagenum++;
+		off = 0; /* page offset only applies to the first page */
+	}
 }
 
 u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)
diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h
index 4ba45caf5939..0e6baee93245 100644
--- a/fs/hfs/btree.h
+++ b/fs/hfs/btree.h
@@ -13,6 +13,13 @@ typedef int (*btree_keycmp)(const btree_key *, const btree_key *);
 
 #define NODE_HASH_SIZE  256
 
+/* B-tree mutex nested subclasses */
+enum hfs_btree_mutex_classes {
+	CATALOG_BTREE_MUTEX,
+	EXTENTS_BTREE_MUTEX,
+	ATTR_BTREE_MUTEX,
+};
+
 /* A HFS BTree held in memory */
 struct hfs_btree {
 	struct super_block *sb;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 44d07c9e3a7f..12d9bae39363 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -420,14 +420,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!res) {
 		if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) {
 			res =  -EIO;
-			goto bail;
+			goto bail_hfs_find;
 		}
 		hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength);
 	}
-	if (res) {
-		hfs_find_exit(&fd);
-		goto bail_no_root;
-	}
+	if (res)
+		goto bail_hfs_find;
 	res = -EINVAL;
 	root_inode = hfs_iget(sb, &fd.search_key->cat, &rec);
 	hfs_find_exit(&fd);
@@ -443,6 +441,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 	/* everything's okay */
 	return 0;
 
+bail_hfs_find:
+	hfs_find_exit(&fd);
 bail_no_root:
 	pr_err("get root inode failed\n");
 bail:
diff --git a/fs/io_uring.c b/fs/io_uring.c
index d94fb5835a20..0cac361bf6b8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2016,7 +2016,7 @@ static void io_req_task_submit(struct io_kiocb *req)
 
 	/* ctx stays valid until unlock, even if we drop all ours ctx->refs */
 	mutex_lock(&ctx->uring_lock);
-	if (!(current->flags & PF_EXITING) && !current->in_execve)
+	if (!(req->task->flags & PF_EXITING) && !req->task->in_execve)
 		__io_queue_sqe(req);
 	else
 		io_req_complete_failed(req, -EFAULT);
@@ -6019,11 +6019,13 @@ static bool io_drain_req(struct io_kiocb *req)
 
 	ret = io_req_prep_async(req);
 	if (ret)
-		return ret;
+		goto fail;
 	io_prep_async_link(req);
 	de = kmalloc(sizeof(*de), GFP_KERNEL);
 	if (!de) {
-		io_req_complete_failed(req, -ENOMEM);
+		ret = -ENOMEM;
+fail:
+		io_req_complete_failed(req, ret);
 		return true;
 	}
 
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 41da4f14c00b..87ccb3438bec 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -215,6 +215,7 @@ iomap_read_inline_data(struct inode *inode, struct page *page,
 	if (PageUptodate(page))
 		return;
 
+	BUG_ON(page_has_private(page));
 	BUG_ON(page->index);
 	BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
 
@@ -239,7 +240,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 {
 	struct iomap_readpage_ctx *ctx = data;
 	struct page *page = ctx->cur_page;
-	struct iomap_page *iop = iomap_page_create(inode, page);
+	struct iomap_page *iop;
 	bool same_page = false, is_contig = false;
 	loff_t orig_pos = pos;
 	unsigned poff, plen;
@@ -252,6 +253,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	}
 
 	/* zero post-eof blocks as the page may be mapped */
+	iop = iomap_page_create(inode, page);
 	iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
 	if (plen == 0)
 		goto done;
@@ -967,7 +969,6 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 		block_commit_write(page, 0, length);
 	} else {
 		WARN_ON_ONCE(!PageUptodate(page));
-		iomap_page_create(inode, page);
 		set_page_dirty(page);
 	}
 
@@ -1304,14 +1305,13 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 		struct writeback_control *wbc, struct inode *inode,
 		struct page *page, u64 end_offset)
 {
-	struct iomap_page *iop = to_iomap_page(page);
+	struct iomap_page *iop = iomap_page_create(inode, page);
 	struct iomap_ioend *ioend, *next;
 	unsigned len = i_blocksize(inode);
 	u64 file_offset; /* file offset of page */
 	int error = 0, count = 0, i;
 	LIST_HEAD(submit_list);
 
-	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
 	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0);
 
 	/*
diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
index dab1b02eba5b..ce6fb810854f 100644
--- a/fs/iomap/seek.c
+++ b/fs/iomap/seek.c
@@ -35,23 +35,20 @@ loff_t
 iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
 {
 	loff_t size = i_size_read(inode);
-	loff_t length = size - offset;
 	loff_t ret;
 
 	/* Nothing to be found before or beyond the end of the file. */
 	if (offset < 0 || offset >= size)
 		return -ENXIO;
 
-	while (length > 0) {
-		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
-				  &offset, iomap_seek_hole_actor);
+	while (offset < size) {
+		ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT,
+				  ops, &offset, iomap_seek_hole_actor);
 		if (ret < 0)
 			return ret;
 		if (ret == 0)
 			break;
-
 		offset += ret;
-		length -= ret;
 	}
 
 	return offset;
@@ -83,27 +80,23 @@ loff_t
 iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
 {
 	loff_t size = i_size_read(inode);
-	loff_t length = size - offset;
 	loff_t ret;
 
 	/* Nothing to be found before or beyond the end of the file. */
 	if (offset < 0 || offset >= size)
 		return -ENXIO;
 
-	while (length > 0) {
-		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
-				  &offset, iomap_seek_data_actor);
+	while (offset < size) {
+		ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT,
+				  ops, &offset, iomap_seek_data_actor);
 		if (ret < 0)
 			return ret;
 		if (ret == 0)
-			break;
-
+			return offset;
 		offset += ret;
-		length -= ret;
 	}
 
-	if (length <= 0)
-		return -ENXIO;
-	return offset;
+	/* We've reached the end of the file without finding data */
+	return -ENXIO;
 }
 EXPORT_SYMBOL_GPL(iomap_seek_data);
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 778ec52cce70..ee9ec0c50bec 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -804,6 +804,14 @@ xfs_ag_shrink_space(
 	args.fsbno = XFS_AGB_TO_FSB(mp, agno, aglen - delta);
 
 	/*
+	 * Make sure that the last inode cluster cannot overlap with the new
+	 * end of the AG, even if it's sparse.
+	 */
+	error = xfs_ialloc_check_shrink(*tpp, agno, agibp, aglen - delta);
+	if (error)
+		return error;
+
+	/*
 	 * Disable perag reservations so it doesn't cause the allocation request
 	 * to fail. We'll reestablish reservation before we return.
 	 */
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index d9d7d5137b73..191d51725988 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -483,7 +483,7 @@ xfs_attr_set_iter(
 		if (error)
 			return error;
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_RM_LBLK:
 		/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
 		dac->dela_state = XFS_DAS_RM_LBLK;
@@ -496,7 +496,7 @@ xfs_attr_set_iter(
 			return -EAGAIN;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_RD_LEAF:
 		/*
 		 * This is the last step for leaf format. Read the block with
@@ -528,7 +528,7 @@ xfs_attr_set_iter(
 				return error;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_ALLOC_NODE:
 		/*
 		 * If there was an out-of-line value, allocate the blocks we
@@ -590,7 +590,7 @@ xfs_attr_set_iter(
 		if (error)
 			return error;
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_RM_NBLK:
 		/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
 		dac->dela_state = XFS_DAS_RM_NBLK;
@@ -603,7 +603,7 @@ xfs_attr_set_iter(
 			return -EAGAIN;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_CLR_FLAG:
 		/*
 		 * The last state for node format. Look up the old attr and
@@ -1406,7 +1406,7 @@ xfs_attr_remove_iter(
 			state = dac->da_state;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_RMTBLK:
 		dac->dela_state = XFS_DAS_RMTBLK;
 
@@ -1441,7 +1441,7 @@ xfs_attr_remove_iter(
 			return -EAGAIN;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_RM_NAME:
 		/*
 		 * If we came here fresh from a transaction roll, reattach all
@@ -1469,7 +1469,7 @@ xfs_attr_remove_iter(
 			return -EAGAIN;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case XFS_DAS_RM_SHRINK:
 		/*
 		 * If the result is small enough, push it all into the inode.
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 57d9cb632983..aaf8805a82df 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2928,3 +2928,58 @@ xfs_ialloc_calc_rootino(
 
 	return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno));
 }
+
+/*
+ * Ensure there are not sparse inode clusters that cross the new EOAG.
+ *
+ * This is a no-op for non-spinode filesystems since clusters are always fully
+ * allocated and checking the bnobt suffices.  However, a spinode filesystem
+ * could have a record where the upper inodes are free blocks.  If those blocks
+ * were removed from the filesystem, the inode record would extend beyond EOAG,
+ * which will be flagged as corruption.
+ */
+int
+xfs_ialloc_check_shrink(
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	struct xfs_buf		*agibp,
+	xfs_agblock_t		new_length)
+{
+	struct xfs_inobt_rec_incore rec;
+	struct xfs_btree_cur	*cur;
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_perag	*pag;
+	xfs_agino_t		agino = XFS_AGB_TO_AGINO(mp, new_length);
+	int			has;
+	int			error;
+
+	if (!xfs_sb_version_hassparseinodes(&mp->m_sb))
+		return 0;
+
+	pag = xfs_perag_get(mp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO);
+
+	/* Look up the inobt record that would correspond to the new EOFS. */
+	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has);
+	if (error || !has)
+		goto out;
+
+	error = xfs_inobt_get_rec(cur, &rec, &has);
+	if (error)
+		goto out;
+
+	if (!has) {
+		error = -EFSCORRUPTED;
+		goto out;
+	}
+
+	/* If the record covers inodes that would be beyond EOFS, bail out. */
+	if (rec.ir_startino + XFS_INODES_PER_CHUNK > agino) {
+		error = -ENOSPC;
+		goto out;
+	}
+out:
+	xfs_btree_del_cursor(cur, error);
+	xfs_perag_put(pag);
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 9df7c80408ff..9a2112b4ad5e 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -122,4 +122,7 @@ int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
 void xfs_ialloc_setup_geometry(struct xfs_mount *mp);
 xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit);
 
+int xfs_ialloc_check_shrink(struct xfs_trans *tp, xfs_agnumber_t agno,
+		struct xfs_buf *agibp, xfs_agblock_t new_length);
+
 #endif	/* __XFS_IALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 04ce361688f7..84ea2e0af9f0 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -592,23 +592,27 @@ xfs_inode_validate_extsize(
 	/*
 	 * This comment describes a historic gap in this verifier function.
 	 *
-	 * On older kernels, the extent size hint verifier doesn't check that
-	 * the extent size hint is an integer multiple of the realtime extent
-	 * size on a directory with both RTINHERIT and EXTSZINHERIT flags set.
-	 * The verifier has always enforced the alignment rule for regular
-	 * files with the REALTIME flag set.
+	 * For a directory with both RTINHERIT and EXTSZINHERIT flags set, this
+	 * function has never checked that the extent size hint is an integer
+	 * multiple of the realtime extent size.  Since we allow users to set
+	 * this combination  on non-rt filesystems /and/ to change the rt
+	 * extent size when adding a rt device to a filesystem, the net effect
+	 * is that users can configure a filesystem anticipating one rt
+	 * geometry and change their minds later.  Directories do not use the
+	 * extent size hint, so this is harmless for them.
 	 *
 	 * If a directory with a misaligned extent size hint is allowed to
 	 * propagate that hint into a new regular realtime file, the result
 	 * is that the inode cluster buffer verifier will trigger a corruption
-	 * shutdown the next time it is run.
+	 * shutdown the next time it is run, because the verifier has always
+	 * enforced the alignment rule for regular files.
 	 *
-	 * Unfortunately, there could be filesystems with these misconfigured
-	 * directories in the wild, so we cannot add a check to this verifier
-	 * at this time because that will result a new source of directory
-	 * corruption errors when reading an existing filesystem.  Instead, we
-	 * permit the misconfiguration to pass through the verifiers so that
-	 * callers of this function can correct and mitigate externally.
+	 * Because we allow administrators to set a new rt extent size when
+	 * adding a rt section, we cannot add a check to this verifier because
+	 * that will result a new source of directory corruption errors when
+	 * reading an existing filesystem.  Instead, we rely on callers to
+	 * decide when alignment checks are appropriate, and fix things up as
+	 * needed.
 	 */
 
 	if (rt_flag)
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 8d595a5c4abd..16f723ebe8dd 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -143,16 +143,14 @@ xfs_trans_log_inode(
 	}
 
 	/*
-	 * Inode verifiers on older kernels don't check that the extent size
-	 * hint is an integer multiple of the rt extent size on a directory
-	 * with both rtinherit and extszinherit flags set.  If we're logging a
-	 * directory that is misconfigured in this way, clear the hint.
+	 * Inode verifiers do not check that the extent size hint is an integer
+	 * multiple of the rt extent size on a directory with both rtinherit
+	 * and extszinherit flags set.  If we're logging a directory that is
+	 * misconfigured in this way, clear the hint.
 	 */
 	if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
 	    (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
 	    (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) {
-		xfs_info_once(ip->i_mount,
-	"Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino);
 		ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
 				   XFS_DIFLAG_EXTSZINHERIT);
 		ip->i_extsize = 0;
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 61f90b2c9430..76fbc7ca4cec 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -73,11 +73,25 @@ xchk_inode_extsize(
 	uint16_t		flags)
 {
 	xfs_failaddr_t		fa;
+	uint32_t		value = be32_to_cpu(dip->di_extsize);
 
-	fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize),
-			mode, flags);
+	fa = xfs_inode_validate_extsize(sc->mp, value, mode, flags);
 	if (fa)
 		xchk_ino_set_corrupt(sc, ino);
+
+	/*
+	 * XFS allows a sysadmin to change the rt extent size when adding a rt
+	 * section to a filesystem after formatting.  If there are any
+	 * directories with extszinherit and rtinherit set, the hint could
+	 * become misaligned with the new rextsize.  The verifier doesn't check
+	 * this, because we allow rtinherit directories even without an rt
+	 * device.  Flag this as an administrative warning since we will clean
+	 * this up eventually.
+	 */
+	if ((flags & XFS_DIFLAG_RTINHERIT) &&
+	    (flags & XFS_DIFLAG_EXTSZINHERIT) &&
+	    value % sc->mp->m_sb.sb_rextsize > 0)
+		xchk_ino_set_warning(sc, ino);
 }
 
 /*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a835ceb79ba5..990b72ae3635 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2763,6 +2763,19 @@ xfs_remove(
 		error = xfs_droplink(tp, ip);
 		if (error)
 			goto out_trans_cancel;
+
+		/*
+		 * Point the unlinked child directory's ".." entry to the root
+		 * directory to eliminate back-references to inodes that may
+		 * get freed before the child directory is closed.  If the fs
+		 * gets shrunk, this can lead to dirent inode validation errors.
+		 */
+		if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) {
+			error = xfs_dir_replace(tp, ip, &xfs_name_dotdot,
+					tp->t_mountp->m_sb.sb_rootino, 0);
+			if (error)
+				return error;
+		}
 	} else {
 		/*
 		 * When removing a non-directory we need to log the parent
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 65270e63c032..16039ea10ac9 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1065,7 +1065,24 @@ xfs_fill_fsxattr(
 
 	fileattr_fill_xflags(fa, xfs_ip2xflags(ip));
 
-	fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+	if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) {
+		fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+	} else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
+		/*
+		 * Don't let a misaligned extent size hint on a directory
+		 * escape to userspace if it won't pass the setattr checks
+		 * later.
+		 */
+		if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+		    ip->i_extsize % mp->m_sb.sb_rextsize > 0) {
+			fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE |
+					    FS_XFLAG_EXTSZINHERIT);
+			fa->fsx_extsize = 0;
+		} else {
+			fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+		}
+	}
+
 	if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
 		fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize);
 	fa->fsx_projid = ip->i_projid;
@@ -1292,10 +1309,10 @@ xfs_ioctl_setattr_check_extsize(
 	new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
 
 	/*
-	 * Inode verifiers on older kernels don't check that the extent size
-	 * hint is an integer multiple of the rt extent size on a directory
-	 * with both rtinherit and extszinherit flags set.  Don't let sysadmins
-	 * misconfigure directories.
+	 * Inode verifiers do not check that the extent size hint is an integer
+	 * multiple of the rt extent size on a directory with both rtinherit
+	 * and extszinherit flags set.  Don't let sysadmins misconfigure
+	 * directories.
 	 */
 	if ((new_diflags & XFS_DIFLAG_RTINHERIT) &&
 	    (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) {
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 4e7be6b4ca8e..699066fb9052 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -923,16 +923,41 @@ xfs_growfs_rt(
 	uint8_t		*rsum_cache;	/* old summary cache */
 
 	sbp = &mp->m_sb;
-	/*
-	 * Initial error checking.
-	 */
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (mp->m_rtdev_targp == NULL || mp->m_rbmip == NULL ||
-	    (nrblocks = in->newblocks) <= sbp->sb_rblocks ||
-	    (sbp->sb_rblocks && (in->extsize != sbp->sb_rextsize)))
+
+	/* Needs to have been mounted with an rt device. */
+	if (!XFS_IS_REALTIME_MOUNT(mp))
+		return -EINVAL;
+	/*
+	 * Mount should fail if the rt bitmap/summary files don't load, but
+	 * we'll check anyway.
+	 */
+	if (!mp->m_rbmip || !mp->m_rsumip)
+		return -EINVAL;
+
+	/* Shrink not supported. */
+	if (in->newblocks <= sbp->sb_rblocks)
+		return -EINVAL;
+
+	/* Can only change rt extent size when adding rt volume. */
+	if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize)
+		return -EINVAL;
+
+	/* Range check the extent size. */
+	if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE ||
+	    XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE)
 		return -EINVAL;
-	if ((error = xfs_sb_validate_fsb_count(sbp, nrblocks)))
+
+	/* Unsupported realtime features. */
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb) ||
+	    xfs_sb_version_hasreflink(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	nrblocks = in->newblocks;
+	error = xfs_sb_validate_fsb_count(sbp, nrblocks);
+	if (error)
 		return error;
 	/*
 	 * Read in the last block of the device, make sure it exists.
@@ -996,7 +1021,8 @@ xfs_growfs_rt(
 		     ((sbp->sb_rextents & ((1 << mp->m_blkbit_log) - 1)) != 0);
 	     bmbno < nrbmblocks;
 	     bmbno++) {
-		xfs_trans_t	*tp;
+		struct xfs_trans	*tp;
+		xfs_rfsblock_t		nrblocks_step;
 
 		*nmp = *mp;
 		nsbp = &nmp->m_sb;
@@ -1005,10 +1031,9 @@ xfs_growfs_rt(
 		 */
 		nsbp->sb_rextsize = in->extsize;
 		nsbp->sb_rbmblocks = bmbno + 1;
-		nsbp->sb_rblocks =
-			XFS_RTMIN(nrblocks,
-				  nsbp->sb_rbmblocks * NBBY *
-				  nsbp->sb_blocksize * nsbp->sb_rextsize);
+		nrblocks_step = (bmbno + 1) * NBBY * nsbp->sb_blocksize *
+				nsbp->sb_rextsize;
+		nsbp->sb_rblocks = min(nrblocks, nrblocks_step);
 		nsbp->sb_rextents = nsbp->sb_rblocks;
 		do_div(nsbp->sb_rextents, nsbp->sb_rextsize);
 		ASSERT(nsbp->sb_rextents != 0);
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index dbf03635869c..70055d486bf7 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -705,9 +705,6 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 		return 0;
 
 	bio = bio_alloc(GFP_NOFS, nr_pages);
-	if (!bio)
-		return -ENOMEM;
-
 	bio_set_dev(bio, bdev);
 	bio->bi_iter.bi_sector = zi->i_zsector;
 	bio->bi_write_hint = iocb->ki_hint;