Hi Volodymyr/Maulik, On Fri, Mar 29, 2024 at 10:22:47AM +0530, Maulik Shah (mkshah) wrote: > > > On 3/29/2024 3:49 AM, Volodymyr Babchuk wrote: > > > > Hi Maulik > > > > "Maulik Shah (mkshah)" <quic_mkshah@xxxxxxxxxxx> writes: > > > > > On 3/28/2024 1:39 AM, Volodymyr Babchuk wrote: > > > > It appears that hardware does not like cacheable accesses to this > > > > region. Trying to access this shared memory region as Normal Memory > > > > leads to secure interrupt which causes an endless loop somewhere in > > > > Trust Zone. > > > > > > Linux does not write into cmd-db region. This region is write > > > protected by XPU. Making this region uncached magically solves the XPU > > > write fault > > > issue. > > > > > > Can you please include above details? > > > > Sure, I'll add this to the next version. > > > > Thanks. > > > > > > > In downstream, we have below which resolved similar issue on qcm6490. > > > > > > cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WC); > > > > > > Downstream SA8155P also have MEMREMAP_WC. Can you please give it a try > > > on your device? > > > > Yes, MEMREMAP_WC works as well. This opens the question: which type is > > more correct? I have no deep understanding in QCOM internals so it is > > hard to me to answer this question. > > > > XPU may have falsely detected clean cache eviction as "write" into the write > protected region so using uncached flag MEMREMAP_WC may be helping here and > is more correct in my understanding. > I have got the very same explanation from my other colleagues at Qualcomm. I could reproduce the problem 100% of the time on QCS6490 RB3 board with Linux booting in EL2. The problem goes away with non-cached mapping (MEMREMAP_WC/MEMREMAP_WB). Do you guys plan to send V2? Please CC me on the V2. Thanks, Pavan
