When running on an AMD vIOMMU, we observed multiple invalidations (of
decreasing power of 2 aligned sizes) when unmapping a single page.
Domain flush takes gather bounds (end-start) as size param. However,
gather->end is defined as the last inclusive address (start + size - 1).
This leads to an off by 1 error.
With this patch, verified that 1 invalidation occurs when unmapping a
single page.
Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
Signed-off-by: Jon Pan-Doh <[email protected]>
Tested-by: Sudheer Dantuluri <[email protected]>
Suggested-by: Gary Zibrat <[email protected]>
---
drivers/iommu/amd/iommu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 5a505ba5467e..da45b1ab042d 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2378,7 +2378,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
unsigned long flags;
spin_lock_irqsave(&dom->lock, flags);
- domain_flush_pages(dom, gather->start, gather->end - gather->start, 1);
+ domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
amd_iommu_domain_flush_complete(dom);
spin_unlock_irqrestore(&dom->lock, flags);
}
--
2.40.0.634.g4ca3ef3211-goog
> On Apr 26, 2023, at 1:32 PM, Jon Pan-Doh <[email protected]> wrote:
>
> When running on an AMD vIOMMU, we observed multiple invalidations (of
> decreasing power of 2 aligned sizes) when unmapping a single page.
>
> Domain flush takes gather bounds (end-start) as size param. However,
> gather->end is defined as the last inclusive address (start + size - 1).
> This leads to an off by 1 error.
>
> With this patch, verified that 1 invalidation occurs when unmapping a
> single page.
>
> Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
> Signed-off-by: Jon Pan-Doh <[email protected]>
> Tested-by: Sudheer Dantuluri <[email protected]>
> Suggested-by: Gary Zibrat <[email protected]>
>
Sorry for that.
Acked-by: Nadav Amit <[email protected]>
> On Apr 26, 2023, at 2:04 PM, Nadav Amit <[email protected]> wrote:
>
>
>
>> On Apr 26, 2023, at 1:32 PM, Jon Pan-Doh <[email protected]> wrote:
>>
>> When running on an AMD vIOMMU, we observed multiple invalidations (of
>> decreasing power of 2 aligned sizes) when unmapping a single page.
>>
>> Domain flush takes gather bounds (end-start) as size param. However,
>> gather->end is defined as the last inclusive address (start + size - 1).
>> This leads to an off by 1 error.
>>
>> With this patch, verified that 1 invalidation occurs when unmapping a
>> single page.
>>
>> Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
>> Signed-off-by: Jon Pan-Doh <[email protected]>
>> Tested-by: Sudheer Dantuluri <[email protected]>
>> Suggested-by: Gary Zibrat <[email protected]>
>>
>
> Sorry for that.
>
> Acked-by: Nadav Amit <[email protected]>
P.S. I think it is stable-worthy.
On 4/27/2023 2:02 AM, Jon Pan-Doh wrote:
> When running on an AMD vIOMMU, we observed multiple invalidations (of
> decreasing power of 2 aligned sizes) when unmapping a single page.
>
> Domain flush takes gather bounds (end-start) as size param. However,
> gather->end is defined as the last inclusive address (start + size - 1).
> This leads to an off by 1 error.
>
> With this patch, verified that 1 invalidation occurs when unmapping a
> single page.
>
> Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
> Signed-off-by: Jon Pan-Doh <[email protected]>
> Tested-by: Sudheer Dantuluri <[email protected]>
> Suggested-by: Gary Zibrat <[email protected]>
Thanks!
Reviewed-by: Vasant Hegde <[email protected]>
-Vasant
> ---
> drivers/iommu/amd/iommu.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
> index 5a505ba5467e..da45b1ab042d 100644
> --- a/drivers/iommu/amd/iommu.c
> +++ b/drivers/iommu/amd/iommu.c
> @@ -2378,7 +2378,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
> unsigned long flags;
>
> spin_lock_irqsave(&dom->lock, flags);
> - domain_flush_pages(dom, gather->start, gather->end - gather->start, 1);
> + domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
> amd_iommu_domain_flush_complete(dom);
> spin_unlock_irqrestore(&dom->lock, flags);
> }
Cc'ing [email protected] per Nadav's suggestion.
Hi Joerg,
[Cc'ing [email protected] per Nadav's suggestion]
This bug fix seems to have gotten the necessary reviews (AMD and
previous commit author). Is it eligible to be applied?
Thanks,
Jon
On Wed, Apr 26, 2023 at 1:32 PM Jon Pan-Doh <[email protected]> wrote:
>
> When running on an AMD vIOMMU, we observed multiple invalidations (of
> decreasing power of 2 aligned sizes) when unmapping a single page.
>
> Domain flush takes gather bounds (end-start) as size param. However,
> gather->end is defined as the last inclusive address (start + size - 1).
> This leads to an off by 1 error.
>
> With this patch, verified that 1 invalidation occurs when unmapping a
> single page.
>
> Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
> Signed-off-by: Jon Pan-Doh <[email protected]>
> Tested-by: Sudheer Dantuluri <[email protected]>
> Suggested-by: Gary Zibrat <[email protected]>
> ---
> drivers/iommu/amd/iommu.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
> index 5a505ba5467e..da45b1ab042d 100644
> --- a/drivers/iommu/amd/iommu.c
> +++ b/drivers/iommu/amd/iommu.c
> @@ -2378,7 +2378,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
> unsigned long flags;
>
> spin_lock_irqsave(&dom->lock, flags);
> - domain_flush_pages(dom, gather->start, gather->end - gather->start, 1);
> + domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
> amd_iommu_domain_flush_complete(dom);
> spin_unlock_irqrestore(&dom->lock, flags);
> }
> --
> 2.40.0.634.g4ca3ef3211-goog
>
On Tue, May 16, 2023 at 01:59:16PM -0700, Jon Pan-Doh wrote:
> Hi Joerg,
>
> [Cc'ing [email protected] per Nadav's suggestion]
<formletter>
This is not the correct way to submit patches for inclusion in the
stable kernel tree. Please read:
https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
for how to do this properly.
</formletter>
> On May 16, 2023, at 10:49 PM, Jon Pan-Doh <[email protected]> wrote:
>
> !! External Email
>
> On Wed, Apr 26, 2023 at 1:32 PM Jon Pan-Doh <[email protected]> wrote:
>>
>> When running on an AMD vIOMMU, we observed multiple invalidations (of
>> decreasing power of 2 aligned sizes) when unmapping a single page.
>>
>> Domain flush takes gather bounds (end-start) as size param. However,
>> gather->end is defined as the last inclusive address (start + size - 1).
>> This leads to an off by 1 error.
>>
>> With this patch, verified that 1 invalidation occurs when unmapping a
>> single page.
>>
>> Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
>> Signed-off-by: Jon Pan-Doh <[email protected]>
>> Tested-by: Sudheer Dantuluri <[email protected]>
>> Suggested-by: Gary Zibrat <[email protected]>
>
> Cc: [email protected]
Assuming the patch was still not applied, I think that Greg KH would
prefer that you send v2 that includes the “Cc: <[email protected]>”
(notice the “<“ and “>" signs) and ideally the version in which I added
the buggy code (sorry for that again) after a “#” sign.
I think it is version 5.15.
IOW: If the patch was still not applied by Joerg, please send v2 with:
Cc: <[email protected] <mailto:[email protected]>> # 5.15.x
In the commit log.
On Tue, May 16, 2023 at 9:38 PM Greg KH <[email protected]> wrote:
>
> On Tue, May 16, 2023 at 01:59:16PM -0700, Jon Pan-Doh wrote:
> > Hi Joerg,
> >
> > [Cc'ing [email protected] per Nadav's suggestion]
>
> <formletter>
>
> This is not the correct way to submit patches for inclusion in the
> stable kernel tree. Please read:
> https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
> for how to do this properly.
>
> </formletter>
Thanks for the link. Added the Cc tag as a reply to the patch.
Apologies for top-posting previously.
On Wed, Apr 26, 2023 at 1:32 PM Jon Pan-Doh <[email protected]> wrote:
>
> When running on an AMD vIOMMU, we observed multiple invalidations (of
> decreasing power of 2 aligned sizes) when unmapping a single page.
>
> Domain flush takes gather bounds (end-start) as size param. However,
> gather->end is defined as the last inclusive address (start + size - 1).
> This leads to an off by 1 error.
>
> With this patch, verified that 1 invalidation occurs when unmapping a
> single page.
>
> Fixes: a270be1b3fdf ("iommu/amd: Use only natural aligned flushes in a VM")
> Signed-off-by: Jon Pan-Doh <[email protected]>
> Tested-by: Sudheer Dantuluri <[email protected]>
> Suggested-by: Gary Zibrat <[email protected]>
Cc: [email protected]
On Tue, May 16, 2023 at 10:58 PM Nadav Amit <[email protected]> wrote:
> IOW: If the patch was still not applied by Joerg, please send v2 with:
>
> Cc: <[email protected] <mailto:[email protected]>> # 5.15.x
>
> In the commit log.
>
Thanks for the clarification/guidance. I've resent the patch for
review with added tags (Acked-by, Reviewed-by). Will re-read the patch
submission doc and try to avoid formatting issues in the future.
On Wed, Apr 26, 2023 at 01:32:56PM -0700, Jon Pan-Doh wrote:
> drivers/iommu/amd/iommu.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Applied for 6.4, thanks.