On 01/06/2014 12:58 AM, joeyli wrote:
> 於 二，2013-12-31 於 16:42 -0800，H. Peter Anvin 提到：
>> On 12/19/2013 09:41 PM, joeyli wrote:
>>>>
>>>> What platform do you have that has TAD support? I am wondering how this
>>>> was tested.
>>>>
>>>
>>> It's a testing platform that's only support get/set time functions of
>>> ACPI TAD.
>>>
>>
>> It would be really, really good to get this into Qemu (either SeaBIOS or
>> OVMF, or ideally both) so we can have anyone test.
>>
>> -hpa
>
> I will try to add to OVMF first.
>
For the record, I posted a patch to Qemu about a year ago to store the
timezone in the CMOS, which might be useful for this implementation. It
was rejected because of no firmware support, so if you implement it for
OVMF we can (update and) push this patch again.
-hpa
--- Begin Message ---
From: "H. Peter Anvin" <hpa@xxxxxxxxx>
There is no standard method for storing timezone information
associated with the classic PC/AT RTC, however, there are standard
methods in ACPI (Time and Alarm Device) and EFI (GetTime/SetTime) for
getting this information.
Since these are abstract methods, it is qreally firmware-specific how
it is stored, however, since Qemu initializes the RTC in the virtual
environment that information needs to come from Qemu in the first
place.
Non-PC platforms that use the MC146181 RTC may have their own
firmware-specific methods as well.
The most logical place to stash this information is in the RTC CMOS;
not only is it logically co-located with the relevant information, but
it is also very easy to access from ACPI bytecode. Thus, save the
timezone information in two bytes in CMOS that have no known standard
definition, but are yet within the 64 bytes that even the most basic
RTC CMOS implementations including the original MC146181 support.
Note: all timezones currently in use in the world are on 15-minutes
boundaries, which would allow this information to be stored in a
single signed byte. However, both EFI and ACPI use a minute-granular
interface (specified as -1440 to +1440 with 2047 used to mean
"unknown", this requires a minimum of 12 bits to represent); this
follows that model.
Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: "Kevin O'Connor" <kevin@xxxxxxxxxxxx>
Cc: David Woodhouse <dwmw2@xxxxxxxxxxxxx>
---
hw/mc146818rtc.c | 6 ++++++
hw/mc146818rtc_regs.h | 2 ++
2 files changed, 8 insertions(+)
diff --git a/hw/mc146818rtc.c b/hw/mc146818rtc.c
index 2fb11f6..72541dd 100644
--- a/hw/mc146818rtc.c
+++ b/hw/mc146818rtc.c
@@ -681,6 +681,7 @@ static void rtc_set_date_from_host(ISADevice *dev)
{
RTCState *s = DO_UPCAST(RTCState, dev, dev);
struct tm tm;
+ int minuteseast;
qemu_get_timedate(&tm, 0);
@@ -690,6 +691,11 @@ static void rtc_set_date_from_host(ISADevice *dev)
/* set the CMOS date */
rtc_set_cmos(s, &tm);
+
+ /* Set the timezone information as a signed 16-bit number of minutes */
+ minuteseast = ((int64_t)s->base_rtc - (int64_t)mktime(&tm)) / 60;
+ s->cmos_data[RTC_TIMEZONE_L] = (uint8_t)(minuteseast);
+ s->cmos_data[RTC_TIMEZONE_H] = (uint8_t)(minuteseast >> 8);
}
static int rtc_post_load(void *opaque, int version_id)
diff --git a/hw/mc146818rtc_regs.h b/hw/mc146818rtc_regs.h
index ccdee42..7dd5e0d 100644
--- a/hw/mc146818rtc_regs.h
+++ b/hw/mc146818rtc_regs.h
@@ -47,6 +47,8 @@
/* PC cmos mappings */
#define RTC_CENTURY 0x32
#define RTC_IBM_PS2_CENTURY_BYTE 0x37
+#define RTC_TIMEZONE_L 0x3e
+#define RTC_TIMEZONE_H 0x3f
#define REG_A_UIP 0x80
--
1.7.11.7
--- End Message ---
