From: Olaf Hering <olaf@aepfle.de>
To: xen-devel@lists.xensource.com
Subject: [PATCH] reset PV devices in crash kernel
Date: Fri, 4 Feb 2011 16:30:12 +0100 [thread overview]
Message-ID: <20110204153012.GA9258@aepfle.de> (raw)
In-Reply-To: <20110204152850.GA8726@aepfle.de>
After triggering a crash dump in a HVM guest, the PV backend drivers
will remain in connected state. When the kdump kernel starts the PV
drivers will skip such devices. As a result, no root device is found
and the vmcore cant be saved.
With this change all frontend devices with state XenbusStateConnected
will be reset by changing the state file to Closing/Closed/Initializing.
This will trigger a disconnect in the backend drivers. Now the frontend
drivers will find the backend drivers in state Initwait and can connect.
Signed-off-by: Olaf Hering <olaf@aepfle.de>
---
drivers/xen/xenbus/xenbus_comms.c | 4 +
drivers/xen/xenbus/xenbus_probe.c | 96 ++++++++++++++++++++++++++++++++++++++
2 files changed, 99 insertions(+), 1 deletion(-)
--- linux-2.6.18-xen.hg.orig/drivers/xen/xenbus/xenbus_comms.c
+++ linux-2.6.18-xen.hg/drivers/xen/xenbus/xenbus_comms.c
@@ -234,7 +234,9 @@ int xb_init_comms(void)
printk(KERN_WARNING "XENBUS response ring is not quiescent "
"(%08x:%08x): fixing up\n",
intf->rsp_cons, intf->rsp_prod);
- intf->rsp_cons = intf->rsp_prod;
+ /* breaks kdump */
+ if (!reset_devices)
+ intf->rsp_cons = intf->rsp_prod;
}
if (xenbus_irq)
--- linux-2.6.18-xen.hg.orig/drivers/xen/xenbus/xenbus_probe.c
+++ linux-2.6.18-xen.hg/drivers/xen/xenbus/xenbus_probe.c
@@ -854,11 +854,107 @@ void unregister_xenstore_notifier(struct
}
EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
+#ifdef CONFIG_CRASH_DUMP
+static DECLARE_WAIT_QUEUE_HEAD(be_state_wq);
+static int be_state;
+
+static void xenbus_reset_state_changed(struct xenbus_watch *w, const char **v, unsigned int l)
+{
+ xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &be_state);
+ printk(KERN_INFO "XENBUS: %s %s", v[XS_WATCH_PATH], xenbus_strstate(be_state));
+ wake_up(&be_state_wq);
+}
+
+static int xenbus_reset_check_final(int *st)
+{
+ return *st == XenbusStateInitialising || *st == XenbusStateInitWait;
+}
+
+static void xenbus_reset_frontend_state(char *backend, char *frontend)
+{
+ struct xenbus_watch watch;
+
+ memset(&watch, 0, sizeof(watch));
+ watch.node = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/state", backend);
+ if (!watch.node)
+ return;
+
+ watch.callback = xenbus_reset_state_changed;
+ be_state = XenbusStateUnknown;
+
+ printk(KERN_INFO "triggering reconnect on %s", backend);
+ register_xenbus_watch(&watch);
+
+ xenbus_printf(XBT_NIL, frontend, "state", "%d", XenbusStateClosing);
+ wait_event_interruptible(be_state_wq, be_state == XenbusStateClosing);
+
+ xenbus_printf(XBT_NIL, frontend, "state", "%d", XenbusStateClosed);
+ wait_event_interruptible(be_state_wq, be_state == XenbusStateClosed);
+
+ xenbus_printf(XBT_NIL, frontend, "state", "%d", XenbusStateInitialising);
+ wait_event_interruptible(be_state_wq, xenbus_reset_check_final(&be_state));
+
+ unregister_xenbus_watch(&watch);
+ printk(KERN_INFO "reconnect done on %s", backend);
+ kfree(watch.node);
+}
+
+static void xenbus_reset_check_state(char *frontend)
+{
+ int state, err;
+ char *backend;
+
+ err = xenbus_scanf(XBT_NIL, frontend, "state", "%i", &state);
+ /* frontend connected? */
+ if (err == 1 && state == XenbusStateConnected) {
+ backend = xenbus_read(XBT_NIL, frontend, "backend", NULL);
+ if (!backend || IS_ERR(backend))
+ return;
+ err = xenbus_scanf(XBT_NIL, backend, "state", "%i", &state);
+ /* backend connected? */
+ if (err == 1 && state == XenbusStateConnected)
+ xenbus_reset_frontend_state(backend, frontend);
+ kfree(backend);
+ }
+}
+
+static void xenbus_reset_state(void)
+{
+ char *frontend;
+ char **devclass, **dev;
+ int devclass_n, dev_n;
+ int i, j;
+
+ devclass = xenbus_directory(XBT_NIL, "device", "", &devclass_n);
+ if (IS_ERR(devclass))
+ return;
+
+ for (i = 0; i < devclass_n; i++) {
+ dev = xenbus_directory(XBT_NIL, "device", devclass[i], &dev_n);
+ if (IS_ERR(dev))
+ continue;
+ for (j = 0; j < dev_n; j++) {
+ frontend = kasprintf(GFP_NOIO|__GFP_HIGH, "device/%s/%s", devclass[i], dev[j]);
+ if (!frontend)
+ continue;
+ xenbus_reset_check_state(frontend);
+ kfree(frontend);
+ }
+ kfree(dev);
+ }
+ kfree(devclass);
+}
+#endif
void xenbus_probe(void *unused)
{
BUG_ON(!is_xenstored_ready());
+#ifdef CONFIG_CRASH_DUMP
+ /* reset devices in XenbusStateConnected state */
+ if (!is_initial_xendomain() && reset_devices)
+ xenbus_reset_state();
+#endif
/* Enumerate devices in xenstore and watch for changes. */
xenbus_probe_devices(&xenbus_frontend);
register_xenbus_watch(&fe_watch);
next prev parent reply other threads:[~2011-02-04 15:30 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-04 15:28 [PATCH] kdump: introduce "reset_devices" command line option Olaf Hering
2011-02-04 15:30 ` Olaf Hering [this message]
2011-02-07 16:28 ` [PATCH] reset PV devices in crash kernel Olaf Hering
2011-02-07 17:16 ` Konrad Rzeszutek Wilk
2011-02-07 17:42 ` Olaf Hering
2011-04-01 10:16 ` Olaf Hering
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20110204153012.GA9258@aepfle.de \
--to=olaf@aepfle.de \
--cc=xen-devel@lists.xensource.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).