Re: [PATCH 1/2] iommu/vt-d: Fix missing PASID in dev TLB flush with cache_tag_flush_all

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

On 7/12/25 12:09, Baolu Lu wrote:
> On 7/11/2025 4:21 PM, Ethan MILON wrote:
>> Hi Baolu,
>>
>> Thanks for the review.
>>
>> On 7/10/25 10:59, Baolu Lu wrote:
>>> Caution: External email. Do not open attachments or click links, 
>>> unless this email comes from a known sender and you know the content 
>>> is safe.
>>>
>>>
>>> On 7/9/2025 5:48 AM, Ethan MILON wrote:
>>>> The function cache_tag_flush_all() was originally implemented with
>>>> incorrect device TLB invalidation logic that does not handle PASID, in
>>>> commit c4d27ffaa8eb ("iommu/vt-d: Add cache tag invalidation helpers")
>>>>
>>>> This causes regressions where full address space TLB invalidations 
>>>> occur
>>>> with a PASID attached, such as during transparent hugepage unmapping in
>>>> SVA configurations or when calling iommu_flush_iotlb_all(). In these
>>>> cases, the device receives a TLB invalidation that lacks PASID.
>>>>
>>>> This incorrect logic was later extracted into
>>>> cache_tag_flush_devtlb_all(), in commit 3297d047cd7f ("iommu/vt-d:
>>>> Refactor IOTLB and Dev-IOTLB flush for batching")
>>>>
>>>> The fix replaces the call to cache_tag_flush_devtlb_all() with
>>>> cache_tag_flush_devtlb_psi(), which properly handles PASID.
>>>>
>>>> Fixes: 4f609dbff51b ("iommu/vt-d: Use cache helpers in 
>>>> arch_invalidate_secondary_tlbs")
>>>> Fixes: 4e589a53685c ("iommu/vt-d: Use cache_tag_flush_all() in 
>>>> flush_iotlb_all")
>>>>
>>> Remove above blank line.
>> Noted.
>>
>>>> Signed-off-by: Ethan Milon<ethan.milon@eviden.com>
>>> checkpatch.pl complains:
>>>
>>> WARNING: From:/Signed-off-by: email name mismatch: 'From: Ethan MILON
>>> <ethan.milon@eviden.com>' != 'Signed-off-by: Ethan Milon
>>> <ethan.milon@eviden.com>'
>> Understood. Our email server seems to overwrite our last names. I’ll
>> look into correcting that.
>>
>>>> ---
>>>>    drivers/iommu/intel/cache.c | 18 +-----------------
>>>>    1 file changed, 1 insertion(+), 17 deletions(-)
>>> Other looks good to me.
>> Should I send a v2 with the fixes?
> 
> No. I can change it manually if you have no objection.

Queued these two patches for linux-next with above nits addressed. Thank
you!

--
baolu