Re: Tracing NetBSD sun4v issues

[Sad Clouds <cryintothebluesky%gmail.com@localhost>]

On Wed, 14 Oct 2026 11:42:16 +0100
Sad Clouds <cryintothebluesky%gmail.com@localhost> wrote:

> I can only conclude that when executing "return %i7 + 8" instruction, it
> potentially results in a window fill trap (as this instruction has
> similar semantics to the "restore" instruction) and the trap handler
> corrupts program counter register or similar, which causes execution to
> jump to jemalloc function, instead of _compat_setpassent.

Another scenario is when executing the return instruction, some other
trap occurs, not related to window fill, and the kernel has to save
user space program registers in PCB or somewhere, to service the trap.
Now when returning to the user space program, the kernel reloads its
registers but something gets messed up. The next step is to try and
trace those code paths.