On 04.01.2023 21:04, Andrew Cooper wrote:
> On 21/12/2022 7:40 am, Jan Beulich wrote:
>> On 20.12.2022 21:56, Andrew Cooper wrote:
>>> On 20/12/2022 1:51 pm, Jan Beulich wrote:
On 16.12.2022 21:17, Andrew Cooper wrote:
> +"mov%[cr4], %%cr4\n\t" /* CR4.PGE = 1 */
> +
On 21/12/2022 7:40 am, Jan Beulich wrote:
> On 20.12.2022 21:56, Andrew Cooper wrote:
>> On 20/12/2022 1:51 pm, Jan Beulich wrote:
>>> On 16.12.2022 21:17, Andrew Cooper wrote:
+"mov%[cr4], %%cr4\n\t" /* CR4.PGE = 1 */
+: [cr4] "=&a" (tmp) /* Could be "r", but "a"
On 20.12.2022 21:56, Andrew Cooper wrote:
> On 20/12/2022 1:51 pm, Jan Beulich wrote:
>> On 16.12.2022 21:17, Andrew Cooper wrote:
>>> +"mov%[cr4], %%cr4\n\t" /* CR4.PGE = 1 */
>>> +: [cr4] "=&a" (tmp) /* Could be "r", but "a" makes better asm */
>>> +: [cr3] "r" (__
On 20/12/2022 1:51 pm, Jan Beulich wrote:
> On 16.12.2022 21:17, Andrew Cooper wrote:
>> Partly for clarity because there is a lot of subtle magic at work here.
>> Expand the commentary of what's going on.
>>
>> Also, because there is no need to double copy the stack (32kB) to retrieve
>> local val
On 16.12.2022 21:17, Andrew Cooper wrote:
> Partly for clarity because there is a lot of subtle magic at work here.
> Expand the commentary of what's going on.
>
> Also, because there is no need to double copy the stack (32kB) to retrieve
> local values spilled to the stack under the old alias, wh
Partly for clarity because there is a lot of subtle magic at work here.
Expand the commentary of what's going on.
Also, because there is no need to double copy the stack (32kB) to retrieve
local values spilled to the stack under the old alias, when all of the
aforementioned local variables are goi
