On Wed, 14 Oct 2026, Sad Clouds wrote:
On Wed, 14 Oct 2026 11:42:16 +0100 Sad Clouds <cryintothebluesky%gmail.com@localhost> wrote: 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.
The issue I was tracking involved a FILL trap from TL=0 causing a MMU fault from TL=1.
The function in locore.s that is invoked is sun4v_tl1_ptbl_miss.pcbsplii_other and pcbspill_others still have some kind of issue that I have not been able to track down yet.