[PATCH] lib: sbi: Flush cache entries after writing PMP CSRs

[cp0613 at linux.alibaba.com]

On 2025-10-30 10:36 AM, Samuel Holland wrote:

> > If hardware is filling TLB entries for M-mode then it must tag these TLB
> > entries with privilege level so that they don't match for S-mode otherwise
> > a simple M-mode to S-mode switch at boot-time will allow bootloaders
> > to access M-mode memory with M-mode permissions.

> Yes, agreed, the TLB entries must be tagged with the privilege mode, but that's
> not the problem here. The problem has nothing at all to do with privilege mode
> transitions, and nothing to do with executing code in S-mode, either. The bug
> can be observed purely within the scope of the function calling
> sbi_hart_map_saddr().

> sbi_hart_map_saddr() rewrites a PMP range to allow M-mode access to some address
> range that it previously did not have permission to access. The problem is that
> this PMP change may not be observed until software executes a sfence.vma
> covering at least this address range. So without this patch, it is
> architecturally valid to receive an access fault when M-mode attempts to access
> this address range (i.e. on the very next line of code after calling
> sbi_hart_map_saddr()).

Hi Samuel,

Thank you so much for participating in the discussion.
You pointed out the key points, this is indeed a case.

Thanks,
Pei

> > Regards,
> > Samuel

> >>> Further, flushing TLB entries in sbi_hart_map/unmap_saddr() also
> >>> slows-down many SBI calls which use shared memory.