Re: [PATCH -fixes] mm: Add a call to flush_cache_vmap() in vmap_pfn()

[Palmer Dabbelt <palmer@dabbelt.com>]

On Thu, 10 Aug 2023 08:13:56 PDT (-0700), Palmer Dabbelt wrote:
> On Wed, 09 Aug 2023 15:25:19 PDT (-0700), Christoph Hellwig wrote:
>> On Wed, Aug 09, 2023 at 06:46:33PM +0200, Alexandre Ghiti wrote:
>>> flush_cache_vmap() must be called after new vmalloc mappings are
>>> installed in the page table in order to allow architectures to make sure
>>> the new mapping is visible.
>>
>> Looks good.  I somehow vaguely remember seing a patch like this floating
>> around before as part of a series, but if that didn't make it it
>> certainly should now.
>>
>> Reviewed-by: Christoph Hellwig <hch@lst.de>
>
> I think we're likely to end up with performance problems around here,
> but at least it's correct.  If someone has performance
>
> Dylan: this fixes your breakage as well, right?
>
> I've queued it up for testing, but I doubt QEMU would find any issues
> here.  My build box has been slow lately, but it should end up in fixes
> later today.

Sorry about that, I'm in the wrong thread -- I meant to be over here 
<https://lore.kernel.org/all/20230725132246.817726-1-alexghiti@rivosinc.com/>.

Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>

but I'm not taking this via the RISC-V tree unless someone asks.