commit
5b8b58063029f02da573120ef4dc9079822e3cda upstream.
According to the OPAL docs:
skiboot-5.2.5/doc/opal-api/opal-rtc-read-3.txt
skiboot-5.2.5/doc/opal-api/opal-rtc-write-4.txt
OPAL_HARDWARE may be returned from OPAL_RTC_READ or OPAL_RTC_WRITE and
this indicates either a transient or permanent error.
Prior to this patch, Linux was not dealing with OPAL_HARDWARE being a
permanent error particularly well, in that you could end up in a busy
loop.
This was not too hard to trigger on an AMI BMC based OpenPOWER machine
doing a continuous "ipmitool mc reset cold" to the BMC, the result of
that being that we'd get stuck in an infinite loop in
opal_get_rtc_time().
We now retry a few times before returning the error higher up the
stack.
Fixes:
16b1d26e77b1 ("rtc/tpo: Driver to support rtc and wakeup on PowerNV platform")
Cc: stable@vger.kernel.org # v3.19+
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
{
long rc = OPAL_BUSY;
+ int retries = 10;
u32 y_m_d;
u64 h_m_s_ms;
__be32 __y_m_d;
rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
if (rc == OPAL_BUSY_EVENT)
opal_poll_events(NULL);
- else
+ else if (retries-- && (rc == OPAL_HARDWARE
+ || rc == OPAL_INTERNAL_ERROR))
msleep(10);
+ else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
+ break;
}
if (rc != OPAL_SUCCESS)
static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
{
long rc = OPAL_BUSY;
+ int retries = 10;
u32 y_m_d = 0;
u64 h_m_s_ms = 0;
rc = opal_rtc_write(y_m_d, h_m_s_ms);
if (rc == OPAL_BUSY_EVENT)
opal_poll_events(NULL);
- else
+ else if (retries-- && (rc == OPAL_HARDWARE
+ || rc == OPAL_INTERNAL_ERROR))
msleep(10);
+ else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
+ break;
}
return rc == OPAL_SUCCESS ? 0 : -EIO;