From: Andi Kleen <[email protected]>
The AMD K6 errata check relies on timing a indirect call.
But the way it was written it could be optimized to a direct call.
Force gcc to actually do a indirect call and not just
constant resolve the target address.
Signed-off-by: Andi Kleen <[email protected]>
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4a549db..11ea6f6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -115,7 +115,7 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
*/
n = K6_BUG_LOOP;
- f_vide = vide;
+ asm("" : "=g" (f_vide) : "0" (vide));
rdtscl(d);
while (n--)
f_vide();
* Andi Kleen <[email protected]> wrote:
> From: Andi Kleen <[email protected]>
>
> The AMD K6 errata check relies on timing a indirect call.
> But the way it was written it could be optimized to a direct call.
> Force gcc to actually do a indirect call and not just
> constant resolve the target address.
>
> Signed-off-by: Andi Kleen <[email protected]>
>
> diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
> index 4a549db..11ea6f6 100644
> --- a/arch/x86/kernel/cpu/amd.c
> +++ b/arch/x86/kernel/cpu/amd.c
> @@ -115,7 +115,7 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
> */
>
> n = K6_BUG_LOOP;
> - f_vide = vide;
> + asm("" : "=g" (f_vide) : "0" (vide));
> rdtscl(d);
> while (n--)
> f_vide();
Would be useful to read in the changelog about how you found the bug:
- saw miscalculated values and figured out the reason
- saw a new warning in GCC
- saw it during review
?
Ingo
> Would be useful to read in the changelog about how you found the bug:
>
> - saw miscalculated values and figured out the reason
> - saw a new warning in GCC
> - saw it during review
>
> ?
Saw it during code review when I was fixing the code for LTO.
I don't have a K6 anymore, but I still have fond memories of my K6
system.
-Andi