Skip to main content

Suche

Beiträge die mit STIBP getaggt sind


 
Linus complained about naming in one of the patches from the recent #Linux #kernel spectre v2 mitigation rework (): '[…] The above is not STIBP. It's just "disable IB". There's nothing "ST" about it.[…]' Here is Intels explanation: lore.kernel.org/lkml/84a1bd5c-…





 

 
For those that missed it over the weekend: The performance problem in the #Linux mainline #Kernel that happened due to improved #Spectre v2 protection was fixed over the weekend. A lot more details about this can be found in below thread from my Alter Ego @kernellogger

 
Das durch verbesserte #Spectre-v2 Gegenmaßnahmen entstandene Performance-Problem im #Linux mainline #Kernel sollte im Entwicklerzweig bzw. mit dem heute erwarteten 4.20-rc5 aus der Welt sein. Details dazu finden sich in folgendem Thread meines Alter Ego @kernellogger

 
The (in)famous #kernel performance regression in #Linux mainline/4.20-rc got fixed, as Linus merged the patch series that reworks the #STIBP stuff that helps mitigating #spectre v2. It's CCed stable and thus will show up in stable & longterm kernels, too. git.kernel.org/torvalds/c/4b7…


 
Eine Schutzfunktion sollte vor der Hardware-Lücke Spectre-V2 schützen, hat wohl aber mitunter starken Einfluss auf die Rechengeschwindigkeit. #Linux #LinuxundOpenSource #Linux-Kernel #OpenSource #STIBP #Spectre

 
#Linux #Kernel 4.19.4 is under review now (till at least Friday) and will revert the #spectre v2 #STIBP mitigation patches which are responsible for the big #performance impact a lot news websites wrote about in the past few days. lore.kernel.org/lkml/201811211…


#Linux

 
Linus on #STIBP and its performance impact on #Linux: lore.kernel.org/lkml/CAHk-=wg-… "[…] I don't think the code needs to be reverted, but the *behavior* of just unconditionally enabling STIBP needs to be reverted. Because it was clearly way more expensive than people were told. […]"