On 02/05/25 10:57, Dave Hansen wrote:
gah, the cc list here is rotund...
On 5/2/25 09:38, Valentin Schneider wrote: ...
All of the paths to enter the kernel from userspace have some SWITCH_TO_KERNEL_CR3 variant. If they didn't, the userspace that they entered from could have attacked the kernel with Meltdown.
I'm theorizing that if this is _just_ about avoiding TLB flush IPIs that you can get away with a single mechanism.
So right now there would indeed be the TLB flush IPIs, but also the text_poke() ones (sync_core() after patching text).
These are the two NOHZ-breaking IPIs that show up on my HP box, and that I also got reports for from folks using NOHZ_FULL + CPU isolation in production, mostly on SPR "edge enhanced" type of systems.
...
While I don't expect the list to grow much, it's unfortunately not just the TLB flush IPIs.
Isn't text patching way easier than TLB flushes? You just need *some* serialization. Heck, since TLB flushes are architecturally serializing, you could probably even reuse the exact same mechanism: implement deferred text patch serialization operations as a deferred TLB flush.
The hardest part is figuring out which CPUs are in the state where they can be deferred or not. But you have to solve that in any case, and you already have an algorithm to do it.
Alright, off to mess around SWITCH_TO_KERNEL_CR3 to see how shoving deferred operations there would look then.