Xen devel - Mar 2007 - [Patch] Fix a decode bug in x86_emulate()

When decoding some instructions, such as “ff f3 (push %ebx)”, x86_emulate()
doesn’t check the type of operand. The attached patch fixes the issue.

Signed-off-by: Dexuan Cui <dexuan.cui@intel.com>
>-----Original Message-----
>From: Cui, Dexuan
>Sent: 2007年3月19日 18:57
>To: ''
>Cc: ''Keir Fraser''
>Subject: [Patch] lower the frequency of HPET device model to 1/32 of
TSC''s
>
>The frequency of HPET device model is defined to be the same as
TSC''s, but unluckily this
>doesn''t work well with calibrate_tsc_hpet() in Linux kernel
2.6.16-33, causing some IA32
>Linux HVM guests can''t boot sometimes.
>
>Calibrate_tsc_hpet() tries figuring out how many HPET ticks a TSC cycle
equals; it
>magnifies the result by scale of 2^32, trying to get a more accurate result
since it
>assumes the frequency of HPET in real world is usually less than 1/100 of
TSC, so the
>result of "(2^32 * hpet_freq) / tsc_freq" may exceed 32bits, then
a "divide error
>(overflow)" would occur!
>
>The result doesn''t overflow every time because hpet_freq/tsc_freq
may less than 1.0 due
>to the little inaccuracy in the implementation of HVM timer virtualization.
>
>The patch lowers the frequency of HPET device mode to 1/32 of TSC''s
to fix the issue.
>
> -- Dexuan
>
>


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel

Btw, there are lots of deadly checks such as "BUG()" in vmx.c. Can we
change them -- only crash the current guest domain? I think this may be better.

 -- Dexuan
>-----Original Message-----
>From: xen-devel-bounces@lists.xensource.com
>[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Cui, Dexuan
>Sent: 2007年3月27日 17:46
>To: xen-devel@lists.xensource.com
>Subject: [Xen-devel] [Patch] Fix a decode bug in x86_emulate()
>
>When decoding some instructions, such as “ff f3 (push %ebx)”, x86_emulate()
doesn’t
>check the type of operand. The attached patch fixes the issue.
>
>Signed-off-by: Dexuan Cui <dexuan.cui@intel.com>
>
>>-----Original Message-----
>>From: Cui, Dexuan
>>Sent: 2007年3月19日 18:57
>>To: ''
>>Cc: ''Keir Fraser''
>>Subject: [Patch] lower the frequency of HPET device model to 1/32 of
TSC''s
>>
>>The frequency of HPET device model is defined to be the same as
TSC''s, but unluckily
>this
>>doesn''t work well with calibrate_tsc_hpet() in Linux kernel
2.6.16-33, causing some
>IA32
>>Linux HVM guests can''t boot sometimes.
>>
>>Calibrate_tsc_hpet() tries figuring out how many HPET ticks a TSC cycle
equals; it
>>magnifies the result by scale of 2^32, trying to get a more accurate
result since it
>>assumes the frequency of HPET in real world is usually less than 1/100
of TSC, so the
>>result of "(2^32 * hpet_freq) / tsc_freq" may exceed 32bits,
then a "divide error
>>(overflow)" would occur!
>>
>>The result doesn''t overflow every time because
hpet_freq/tsc_freq may less than 1.0
>due
>>to the little inaccuracy in the implementation of HVM timer
virtualization.
>>
>>The patch lowers the frequency of HPET device mode to 1/32 of
TSC''s to fix the issue.
>>
>> -- Dexuan
>>
>>
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel

On 27/3/07 10:51, "Cui, Dexuan" <dexuan.cui@intel.com> wrote:
> Btw, there are lots of deadly checks such as "BUG()" in vmx.c.
Can we change
> them -- only crash the current guest domain? I think this may be better.
It depends on what the BUG check is. There are plenty of ''is the
hardware
doing something that is (from my point of view) insane?'' and I think it
is
correct to BUG in such cases. Many would indicate a hypervisor problem or
limitation rather than a guest problem.

 -- Keir



_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel