From: Jason Gunthorpe <jgg@nvidia.com>
To: Nicolin Chen <nicolinc@nvidia.com>
Cc: Pranjal Shrivastava <praan@google.com>,
Mostafa Saleh <smostafa@google.com>,
will@kernel.org, robin.murphy@arm.com, joro@8bytes.org,
kees@kernel.org, baolu.lu@linux.intel.com, kevin.tian@intel.com,
miko.lenczewski@arm.com, linux-arm-kernel@lists.infradead.org,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
stable@vger.kernel.org, jamien@nvidia.com
Subject: Re: [PATCH rc v7 0/7] iommu/arm-smmu-v3: Fix device crash on kdump kernel
Date: Fri, 3 Jul 2026 16:10:10 -0300 [thread overview]
Message-ID: <20260703191010.GQ7481@nvidia.com> (raw)
In-Reply-To: <akf9cjLaBLn82lKP@nvidia.com>
On Fri, Jul 03, 2026 at 11:20:34AM -0700, Nicolin Chen wrote:
> > So if you disable kdump when S2 is not supported it also disables it
> > when EL2 would be used, which effectively means it is not supported in
> > a VM.
>
> Hmm, they are actually not exclusive: e.g. Grace has both.
>
> EL2 is from FEAT_E2H, which is set when
> 1. IDR0.HYP=1
> 2. cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN)
>
> VMID is from FEAT_TRANS_S2, which is set When
> 1. IDR0_S2P=1
>
> So, host-level stage-1 TLBIs use EL2 commands (no VMID); guest-level
> TLBIs use NH_ commands (with VMID).
Oh... I see the half baked BTM stuff pushes STRW it into the NH mode
because the CPU runs in that mode so we loose the VMID :\
I guess VM support is important anyhow so you do have to scan the CD
tables and extract the ASIDs, carefully considering the STRW and VMID
of the STE :\
Jason
next prev parent reply other threads:[~2026-07-03 19:10 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-30 6:15 [PATCH rc v7 0/7] iommu/arm-smmu-v3: Fix device crash on kdump kernel Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 1/7] iommu/arm-smmu-v3: Add arm_smmu_kdump_adopt_strtab() for kdump Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 2/7] iommu/arm-smmu-v3: Implement is_attach_deferred() " Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 3/7] iommu/arm-smmu-v3: Do not enable EVTQ/PRIQ interrupts in kdump kernel Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 4/7] iommu/arm-smmu-v3: Skip EVTQ/PRIQ setup " Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 5/7] iommu/arm-smmu-v3: Retain CR0_SMMUEN during kdump device reset Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 6/7] iommu/arm-smmu-v3: Skip RMR bypass for kdump adoption Nicolin Chen
2026-06-30 6:15 ` [PATCH rc v7 7/7] iommu/arm-smmu-v3: Detect ARM_SMMU_OPT_KDUMP_ADOPT in probe() Nicolin Chen
2026-06-30 13:17 ` [PATCH rc v7 0/7] iommu/arm-smmu-v3: Fix device crash on kdump kernel Mostafa Saleh
2026-06-30 14:51 ` Pranjal Shrivastava
2026-06-30 15:33 ` Mostafa Saleh
2026-06-30 18:30 ` Pranjal Shrivastava
2026-06-30 19:08 ` Jason Gunthorpe
2026-06-30 19:24 ` Nicolin Chen
2026-07-01 0:25 ` Jason Gunthorpe
2026-06-30 18:59 ` Jason Gunthorpe
2026-07-01 13:05 ` Mostafa Saleh
2026-07-01 13:36 ` Pranjal Shrivastava
2026-07-02 14:41 ` Jason Gunthorpe
2026-07-02 19:25 ` Nicolin Chen
2026-07-02 23:50 ` Jason Gunthorpe
2026-07-03 3:32 ` Nicolin Chen
2026-07-03 11:57 ` Jason Gunthorpe
2026-07-03 18:20 ` Nicolin Chen
2026-07-03 19:10 ` Jason Gunthorpe [this message]
2026-06-30 18:56 ` Jason Gunthorpe
2026-06-30 19:27 ` Nicolin Chen
2026-07-01 9:58 ` Mostafa Saleh
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=20260703191010.GQ7481@nvidia.com \
--to=jgg@nvidia.com \
--cc=baolu.lu@linux.intel.com \
--cc=iommu@lists.linux.dev \
--cc=jamien@nvidia.com \
--cc=joro@8bytes.org \
--cc=kees@kernel.org \
--cc=kevin.tian@intel.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miko.lenczewski@arm.com \
--cc=nicolinc@nvidia.com \
--cc=praan@google.com \
--cc=robin.murphy@arm.com \
--cc=smostafa@google.com \
--cc=stable@vger.kernel.org \
--cc=will@kernel.org \
/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