From: Jason Gunthorpe <jgg@nvidia.com>
To: "Liam R. Howlett" <Liam.Howlett@oracle.com>,
ankita@nvidia.com, aniketa@nvidia.com, vsethi@nvidia.com,
mochs@nvidia.com, skolothumtho@nvidia.com, linmiaohe@huawei.com,
nao.horiguchi@gmail.com, akpm@linux-foundation.org,
david@redhat.com, lorenzo.stoakes@oracle.com, vbabka@suse.cz,
rppt@kernel.org, surenb@google.com, mhocko@suse.com,
tony.luck@intel.com, bp@alien8.de, rafael@kernel.org,
guohanjun@huawei.com, mchehab@kernel.org, lenb@kernel.org,
kevin.tian@intel.com, alex@shazbot.org, cjia@nvidia.com,
kwankhede@nvidia.com, targupta@nvidia.com, zhiw@nvidia.com,
dnigam@nvidia.com, kjaju@nvidia.com,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-edac@vger.kernel.org, Jonathan.Cameron@huawei.com,
ira.weiny@intel.com, Smita.KoralahalliChannabasappa@amd.com,
u.kleine-koenig@baylibre.com, peterz@infradead.org,
linux-acpi@vger.kernel.org, kvm@vger.kernel.org
Subject: Re: [PATCH v3 0/3] mm: Implement ECC handling for pfn with no struct page
Date: Tue, 21 Oct 2025 13:44:44 -0300 [thread overview]
Message-ID: <20251021164444.GB699957@nvidia.com> (raw)
In-Reply-To: <hbk4hqrdaz7qipkpb5g2znhva63sghwsiqwlyf6pb6xccjtp47@vci5e4vbkjqo>
On Tue, Oct 21, 2025 at 12:30:48PM -0400, Liam R. Howlett wrote:
> > enables VM_PFNMAP vmas to map at PMD level. Otherwise, a poison to a PFN
> > would need breaking the PMD mapping into PTEs to unmap only the poisoned
> > PFN. This can have a major performance impact.
>
> Is the performance impact really a concern in the event of failed
> memory?
Yes, something like the KVM S2 is very sensitive to page size for TLB
performace.
> Does this happen enough to warrant this special case?
If you have a 100k sized cluster it happens constantly :\
> Surely it's not failing hardware that may cause performance impacts, so
> is this triggered in some other way that I'm missing or a conversation
> pointer?
It is the splitting of a pgd/pmd level into PTEs that gets mirrored
into the S2 and then greatly increases the cost of table walks inside
a guest. The HW caches are sized for 1G S2 PTEs, not 4k.
Jason
next prev parent reply other threads:[~2025-10-21 16:44 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-21 10:23 ankita
2025-10-21 10:23 ` [PATCH v3 1/3] mm: handle poisoning of pfn without struct pages ankita
2025-10-21 17:05 ` Ira Weiny
2025-10-22 16:00 ` Jiaqi Yan
2025-10-24 6:34 ` Miaohe Lin
2025-10-24 9:45 ` Shuai Xue
2025-10-24 11:52 ` Jason Gunthorpe
2025-10-24 11:59 ` Ankit Agrawal
2025-10-21 10:23 ` [PATCH v3 2/3] mm: Change ghes code to allow poison of non-struct pfn ankita
2025-10-21 17:13 ` Ira Weiny
2025-10-21 17:19 ` Luck, Tony
2025-10-22 6:53 ` Shuai Xue
2025-10-22 15:03 ` Ira Weiny
2025-10-24 10:03 ` Shuai Xue
2025-10-24 11:26 ` Ankit Agrawal
2025-10-21 10:23 ` [PATCH v3 3/3] vfio/nvgrace-gpu: register device memory for poison handling ankita
2025-10-21 16:30 ` [PATCH v3 0/3] mm: Implement ECC handling for pfn with no struct page Liam R. Howlett
2025-10-21 16:44 ` Jason Gunthorpe [this message]
2025-10-21 18:54 ` Liam R. Howlett
2025-10-21 22:38 ` Jason Gunthorpe
2025-10-24 11:16 ` Ankit Agrawal
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251021164444.GB699957@nvidia.com \
--to=jgg@nvidia.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=Liam.Howlett@oracle.com \
--cc=Smita.KoralahalliChannabasappa@amd.com \
--cc=akpm@linux-foundation.org \
--cc=alex@shazbot.org \
--cc=aniketa@nvidia.com \
--cc=ankita@nvidia.com \
--cc=bp@alien8.de \
--cc=cjia@nvidia.com \
--cc=david@redhat.com \
--cc=dnigam@nvidia.com \
--cc=guohanjun@huawei.com \
--cc=ira.weiny@intel.com \
--cc=kevin.tian@intel.com \
--cc=kjaju@nvidia.com \
--cc=kvm@vger.kernel.org \
--cc=kwankhede@nvidia.com \
--cc=lenb@kernel.org \
--cc=linmiaohe@huawei.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-edac@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=mchehab@kernel.org \
--cc=mhocko@suse.com \
--cc=mochs@nvidia.com \
--cc=nao.horiguchi@gmail.com \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=rppt@kernel.org \
--cc=skolothumtho@nvidia.com \
--cc=surenb@google.com \
--cc=targupta@nvidia.com \
--cc=tony.luck@intel.com \
--cc=u.kleine-koenig@baylibre.com \
--cc=vbabka@suse.cz \
--cc=vsethi@nvidia.com \
--cc=zhiw@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox