On 15/10/2018 14:11, Andrew Cooper wrote:
> On 15/10/18 12:44, Juergen Gross wrote:
>> On 15/10/2018 13:28, Roger Pau Monné wrote:
>>> On Mon, Oct 15, 2018 at 11:36:16AM +0100, Andrew Cooper wrote:
In particular, initialising %dr6 with the value 0 is buggy, because on
hardware supporting
On 15/10/18 12:44, Juergen Gross wrote:
> On 15/10/2018 13:28, Roger Pau Monné wrote:
>> On Mon, Oct 15, 2018 at 11:36:16AM +0100, Andrew Cooper wrote:
>>> In particular, initialising %dr6 with the value 0 is buggy, because on
>>> hardware supporting Transnational Memory, it will cause the sticky
On 15/10/2018 13:28, Roger Pau Monné wrote:
> On Mon, Oct 15, 2018 at 11:36:16AM +0100, Andrew Cooper wrote:
>> In particular, initialising %dr6 with the value 0 is buggy, because on
>> hardware supporting Transnational Memory, it will cause the sticky RTM bit to
>> be asserted, even though a
On Mon, Oct 15, 2018 at 11:36:16AM +0100, Andrew Cooper wrote:
> In particular, initialising %dr6 with the value 0 is buggy, because on
> hardware supporting Transnational Memory, it will cause the sticky RTM bit to
> be asserted, even though a debug exception from a transaction hasn't actually
>
In particular, initialising %dr6 with the value 0 is buggy, because on
hardware supporting Transnational Memory, it will cause the sticky RTM bit to
be asserted, even though a debug exception from a transaction hasn't actually
been observed.
Move X86_DR6_DEFAULT into x86-defns.h along with the