Intel: ADSP: move HPSRAM mask into assembly

[lyakh]

Assembly in power_down() in power_down.S already defines data and code to be locked in cache when powering down SRAM. Instead of adding another such location in power.c, move the hpsram_mask[] array into power_down.S. This fixes hard to debug failures when shutting down the ADSP.

Yes, thesofproject/sof#9268 raises its ugly head again: https://sof-ci.01.org/sofpr/PR9430/build7664/devicetest/index.html We are no wiser about real reasons, but this is yet another attempt at a more robust fix

[andyross]

FWIW: I still bet that if you whiteboxed a rig to enumerate all the dcache indexes and check how many of them can be pinned, we'd discover that something in the boot ROM or elsewhere has left a line pinned accidentally, preventing more pinning at that index, and we're just hitting that by bad luck in the linker.

Would be non-trivial assembly to write, and tedious to debug as the only feedback is a panic, but not "hard" hopefully.

[lyakh]

FWIW: I still bet that if you whiteboxed a rig to enumerate all the dcache indexes and check how many of them can be pinned, we'd discover that something in the boot ROM or elsewhere has left a line pinned accidentally, preventing more pinning at that index, and we're just hitting that by bad luck in the linker.

Would be non-trivial assembly to write, and tedious to debug as the only feedback is a panic, but not "hard" hopefully.

@andyross I tried some version of that and didn't identify any addresses where locking cache lines would fail. Maybe my attempt wasn't correct, but at least I did try.