xen/xenbus: Avoid synchronous wait on XenBus stalling shutdown/restart.

The 'read_reply' works with 'process_msg' to read of a reply in XenBus.
'process_msg' is running from within the 'xenbus' thread. Whenever
a message shows up in XenBus it is put on a xs_state.reply_list list
and 'read_reply' picks it up.

The problem is if the backend domain or the xenstored process is killed.
In which case 'xenbus' is still awaiting - and 'read_reply' if called -
stuck forever waiting for the reply_list to have some contents.

This is normally not a problem - as the backend domain can come back
or the xenstored process can be restarted. However if the domain
is in process of being powered off/restarted/halted - there is no
point of waiting on it coming back - as we are effectively being
terminated and should not impede the progress.

This patch solves this problem by checking whether the guest is the
right domain. If it is an initial domain and hurtling towards death -
there is no point of continuing the wait. All other type of guests
continue with their behavior (as Xenstore is expected to still be
running in another domain).

Fixes-Bug: http://bugs.xenproject.org/xen/bug/8
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

1 files changed, 41 insertions, 3 deletions

diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index b6d5fff43d16..ba804f3d8278 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -50,6 +50,7 @@
 #include <xen/xenbus.h>
 #include <xen/xen.h>
 #include "xenbus_comms.h"
+#include "xenbus_probe.h"
 
 struct xs_stored_msg {
 	struct list_head list;
@@ -139,6 +140,29 @@ static int get_error(const char *errorstring)
 	return xsd_errors[i].errnum;
 }
 
+static bool xenbus_ok(void)
+{
+	switch (xen_store_domain_type) {
+	case XS_LOCAL:
+		switch (system_state) {
+		case SYSTEM_POWER_OFF:
+		case SYSTEM_RESTART:
+		case SYSTEM_HALT:
+			return false;
+		default:
+			break;
+		}
+		return true;
+	case XS_PV:
+	case XS_HVM:
+		/* FIXME: Could check that the remote domain is alive,
+		 * but it is normally initial domain. */
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
 static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
 {
 	struct xs_stored_msg *msg;
@@ -148,9 +172,20 @@ static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
 
 	while (list_empty(&xs_state.reply_list)) {
 		spin_unlock(&xs_state.reply_lock);
-		/* XXX FIXME: Avoid synchronous wait for response here. */
-		wait_event(xs_state.reply_waitq,
-			   !list_empty(&xs_state.reply_list));
+		if (xenbus_ok())
+			/* XXX FIXME: Avoid synchronous wait for response here. */
+			wait_event_timeout(xs_state.reply_waitq,
+					   !list_empty(&xs_state.reply_list),
+					   msecs_to_jiffies(500));
+		else {
+			/*
+			 * If we are in the process of being shut-down there is
+			 * no point of trying to contact XenBus - it is either
+			 * killed (xenstored application) or the other domain
+			 * has been killed or is unreachable.
+			 */
+			return ERR_PTR(-EIO);
+		}
 		spin_lock(&xs_state.reply_lock);
 	}
 
@@ -215,6 +250,9 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 
 	mutex_unlock(&xs_state.request_mutex);
 
+	if (IS_ERR(ret))
+		return ret;
+
 	if ((msg->type == XS_TRANSACTION_END) ||
 	    ((req_msg.type == XS_TRANSACTION_START) &&
 	     (msg->type == XS_ERROR)))