tools/xenstore: Preserve bad client until they are destroyed

XenStored will kill any connection that it thinks has misbehaved,
this is currently happening in two places:
 * In `handle_input()` if the sanity check on the ring and the message
   fails.
 * In `handle_output()` when failing to write the response in the ring.

As the domain structure is a child of the connection, XenStored will
destroy its view of the domain when killing the connection. This will
result in sending @releaseDomain event to all the watchers.

As the watch event doesn't carry which domain has been released,
the watcher (such as XenStored) will generally go through the list of
domains registers and check if one of them is shutting down/dying.
In the case of a client misbehaving, the domain will likely to be
running, so no action will be performed.

When the domain is effectively destroyed, XenStored will not be aware of
the domain anymore. So the watch event is not going to be sent.
By consequence, the watchers of the event will not release mappings
they may have on the domain. This will result in a zombie domain.

In order to send @releaseDomain event at the correct time, we want
to keep the domain structure until the domain is effectively
shutting-down/dying.

We also want to keep the connection around so we could possibly revive
the connection in the future.

A new flag 'is_ignored' is added to mark whether a connection should be
ignored when checking if there are work to do. Additionally any
transactions, watches, buffers associated to the connection will be
freed as you can't do much with them (restarting the connection will
likely need a reset).

As a side note, when the device model were running in a stubdomain, a
guest would have been able to introduce a use-after-free because there
is two parents for a guest connection.

This is XSA-325.

Reported-by: Pawel Wieczorkiewicz <wipawel@amazon.de>
Signed-off-by: Harsha Shamsundara Havanur <havanur@amazon.com>
Signed-off-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>

diff --git a/tools/xenstore/xenstored_core.c b/tools/xenstore/xenstored_core.c
index 56b5e4578b1346e69ac066322ec6ce3993c8403b..1d05d25a48649687a234601230aa0aa2a365f629 100644 (file)
--- a/tools/xenstore/xenstored_core.c
+++ b/tools/xenstore/xenstored_core.c
@@ -1346,6 +1346,32 @@ static struct {
        [XS_DIRECTORY_PART]    = { "DIRECTORY_PART",    send_directory_part },
 };
 
+/*
+ * Keep the connection alive but stop processing any new request or sending
+ * reponse. This is to allow sending @releaseDomain watch event at the correct
+ * moment and/or to allow the connection to restart (not yet implemented).
+ *
+ * All watches, transactions, buffers will be freed.
+ */
+static void ignore_connection(struct connection *conn)
+{
+       struct buffered_data *out, *tmp;
+
+       trace("CONN %p ignored\n", conn);
+
+       conn->is_ignored = true;
+       conn_delete_all_watches(conn);
+       conn_delete_all_transactions(conn);
+
+       list_for_each_entry_safe(out, tmp, &conn->out_list, list) {
+               list_del(&out->list);
+               talloc_free(out);
+       }
+
+       talloc_free(conn->in);
+       conn->in = NULL;
+}
+
 static const char *sockmsg_string(enum xsd_sockmsg_type type)
 {
        if ((unsigned int)type < ARRAY_SIZE(wire_funcs) && wire_funcs[type].str)
@@ -1404,8 +1430,10 @@ static void consider_message(struct connection *conn)
        assert(conn->in == NULL);
 }
 
-/* Errors in reading or allocating here mean we get out of sync, so we
- * drop the whole client connection. */
+/*
+ * Errors in reading or allocating here means we get out of sync, so we mark
+ * the connection as ignored.
+ */
 static void handle_input(struct connection *conn)
 {
        int bytes;
@@ -1462,14 +1490,14 @@ static void handle_input(struct connection *conn)
        return;
 
 bad_client:
-       /* Kill it. */
-       talloc_free(conn);
+       ignore_connection(conn);
 }
 
 static void handle_output(struct connection *conn)
 {
+       /* Ignore the connection if an error occured */
        if (!write_messages(conn))
-               talloc_free(conn);
+               ignore_connection(conn);
 }
 
 struct connection *new_connection(connwritefn_t *write, connreadfn_t *read)
@@ -1485,6 +1513,7 @@ struct connection *new_connection(connwritefn_t *write, connreadfn_t *read)
        new->write = write;
        new->read = read;
        new->can_write = true;
+       new->is_ignored = false;
        new->transaction_started = 0;
        INIT_LIST_HEAD(&new->out_list);
        INIT_LIST_HEAD(&new->watches);
@@ -2171,8 +2200,9 @@ int main(int argc, char *argv[])
                                        if (fds[conn->pollfd_idx].revents
                                            & ~(POLLIN|POLLOUT))
                                                talloc_free(conn);
-                                       else if (fds[conn->pollfd_idx].revents
-                                                & POLLIN)
+                                       else if ((fds[conn->pollfd_idx].revents
+                                                 & POLLIN) &&
+                                                !conn->is_ignored)
                                                handle_input(conn);
                                }
                                if (talloc_free(conn) == 0)
@@ -2184,8 +2214,9 @@ int main(int argc, char *argv[])
                                        if (fds[conn->pollfd_idx].revents
                                            & ~(POLLIN|POLLOUT))
                                                talloc_free(conn);
-                                       else if (fds[conn->pollfd_idx].revents
-                                                & POLLOUT)
+                                       else if ((fds[conn->pollfd_idx].revents
+                                                 & POLLOUT) &&
+                                                !conn->is_ignored)
                                                handle_output(conn);
                                }
                                if (talloc_free(conn) == 0)

diff --git a/tools/xenstore/xenstored_core.h b/tools/xenstore/xenstored_core.h
index eb19b71f5f46ff281f9f24f1013cd80ee9bae8dd..196a6fd2b0bed378866283dd421098bd2fdc01cc 100644 (file)
--- a/tools/xenstore/xenstored_core.h
+++ b/tools/xenstore/xenstored_core.h
@@ -80,6 +80,9 @@ struct connection
        /* Is this a read-only connection? */
        bool can_write;
 
+       /* Is this connection ignored? */
+       bool is_ignored;
+
        /* Buffered incoming data. */
        struct buffered_data *in;
 

diff --git a/tools/xenstore/xenstored_domain.c b/tools/xenstore/xenstored_domain.c
index dc635e9be30cb9b4898d9b84c5e460f9eadabc6a..d5e1e3e9d42d64f9e52a7bdea5fbdc2a6e37f671 100644 (file)
--- a/tools/xenstore/xenstored_domain.c
+++ b/tools/xenstore/xenstored_domain.c
@@ -286,6 +286,10 @@ bool domain_can_read(struct connection *conn)
 
        if (domain_is_unprivileged(conn) && conn->domain->wrl_credit < 0)
                return false;
+
+       if (conn->is_ignored)
+               return false;
+
        return (intf->req_cons != intf->req_prod);
 }
 
@@ -303,6 +307,10 @@ bool domain_is_unprivileged(struct connection *conn)
 bool domain_can_write(struct connection *conn)
 {
        struct xenstore_domain_interface *intf = conn->domain->interface;
+
+       if (conn->is_ignored)
+               return false;
+
        return ((intf->rsp_prod - intf->rsp_cons) != XENSTORE_RING_SIZE);
 }