Other Developers on Core 2 Bugs
My previous entry about Theo de Raadt’s comments on the level of severity of bugs in Intel’s Core 2 processors needs a little update. Linus Torvalds brushes off the alarm and says it’s nothing new. Matt Dillon of Dragonfly BSD isn’t as nonplussed as Torvalds by the errata disclosure in his quick run through of the list.
Notably, he says, “AE3 scares the hell out of me, and for the others AE5, AE8, AE21, and AE30 look serious.” He wrote in his bug-by-bug list:
AE3 - POPF/POPFD that sets the trap flag (aka when single-stepping a program) may cause unpredictable behavior. Holy shit. This one is serious.
He was a little less concerned about the other four, noting in the case of AE5 (memory aliasing with inconsistent dirty and access bits may cause a processor deadlock) how DragonflyBSD and FreeBSD (safely) handle access bits.
