We have observed hosts with misbehaving BMCs that receive a Get Device
GUID command but don't respond. This leads to an indefinite wait in the
ipmi_msghandler's __get_guid function, showing up as hung task messages
for modprobe.
According to IPMI 2.0 specification chapter 20, the implementation of
the Get Device GUID command is optional. Therefore, add a timeout to
waiting for its response and treat the lack of one the same as missing a
device GUID.
Signed-off-by: Stefan Nuernberger <s...@amazon.com>
Signed-off-by: Markus Boehme <mark...@amazon.com>
---
drivers/char/ipmi/ipmi_msghandler.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/drivers/char/ipmi/ipmi_msghandler.c
b/drivers/char/ipmi/ipmi_msghandler.c
index 2b213c9..2a2e8b2 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3184,18 +3184,26 @@ static void guid_handler(struct ipmi_smi *intf, struct
ipmi_recv_msg *msg)
static void __get_guid(struct ipmi_smi *intf)
{
- int rv;
+ long rv;
struct bmc_device *bmc = intf->bmc;
bmc->dyn_guid_set = 2;
intf->null_user_handler = guid_handler;
rv = send_guid_cmd(intf, 0);
- if (rv)
+ if (rv) {
/* Send failed, no GUID available. */
bmc->dyn_guid_set = 0;
- else
- wait_event(intf->waitq, bmc->dyn_guid_set != 2);
+ goto out;
+ }
+ rv = wait_event_timeout(intf->waitq, bmc->dyn_guid_set != 2, 5 * HZ);
+ if (rv == 0) {
+ dev_warn_once(intf->si_dev,
+ "Timed out waiting for GUID. Assuming GUID is not
available.\n");
+ bmc->dyn_guid_set = 0;
+ }
+
+out:
/* dyn_guid_set makes the guid data available. */
smp_rmb();
--
2.7.4
