Re: [PATCH v2 1/1] iommu/sva: Invalidate KVA range on kernel TLB flush

[Baolu Lu <baolu.lu@linux.intel.com>]

On 7/10/25 23:26, Dave Hansen wrote:
> On 7/10/25 06:22, Jason Gunthorpe wrote:
>>> Why does this matter? We flush the CPU TLB in a bunch of different ways,
>>> _especially_ when it's being done for kernel mappings. For example,
>>> __flush_tlb_all() is a non-ranged kernel flush which has a completely
>>> parallel implementation with flush_tlb_kernel_range(). Call sites that
>>> use _it_ are unaffected by the patch here.
>>>
>>> Basically, if we're only worried about vmalloc/vfree freeing page
>>> tables, then this patch is OK. If the problem is bigger than that, then
>>> we need a more comprehensive patch.
>> I think we are worried about any place that frees page tables.
> 
> The two places that come to mind are the remove_memory() code and
> __change_page_attr().
> 
> The remove_memory() gunk is in arch/x86/mm/init_64.c. It has a few sites
> that do flush_tlb_all(). Now that I'm looking at it, there look to be
> some races between freeing page tables pages and flushing the TLB. But,
> basically, if you stick to the sites in there that do flush_tlb_all()
> after free_pagetable(), you should be good.
> 
> As for the __change_page_attr() code, I think the only spot you need to
> hit is cpa_collapse_large_pages() and maybe the one in
> __split_large_page() as well.

Thank you for the guide. It appears that all paths mentioned above will
eventually call flush_tlb_all() after changing the page table. So, I can
simply put a call site in flush_tlb_all()? Something like this:

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a41499dfdc3f..3b85e7d3ba44 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1479,6 +1479,8 @@ void flush_tlb_all(void)
         else
                 /* Fall back to the IPI-based invalidation. */
                 on_each_cpu(do_flush_tlb_all, NULL, 1);
+
+       iommu_sva_invalidate_kva_range(0, TLB_FLUSH_ALL);
  }

> 
> This is all disturbingly ad-hoc, though. The remove_memory() code needs
> fixing and I'll probably go try to bring some order to the chaos in the
> process of fixing it up. But that's a separate problem than this IOMMU fun.

Yes. Please.

Thanks,
baolu