mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: John Garry <john.garry@arm.com>
To: Nicolin Chen <nicolinc@nvidia.com>, will@kernel.org, jgg@nvidia.com
Cc: robin.murphy@arm.com, joro@8bytes.org, praan@google.com,
	kevin.tian@intel.com, smostafa@google.com,
	linux-arm-kernel@lists.infradead.org, iommu@lists.linux.dev,
	linux-kernel@vger.kernel.org, jamien@nvidia.com, kas@kernel.org,
	Cristian Prundeanu <cpru@amazon.com>,
	Breno Leitao <leitao@kernel.org>,
	xueshuai@linux.alibaba.com
Subject: Re: [PATCH v12 11/12] iommu/arm-smmu-v3: Skip RMR bypass for kdump adoption
Date: Mon, 16 Nov 2026 12:26:20 +0000	[thread overview]
Message-ID: <4cf391ff-804a-46a1-8d3e-d0ff8442841f@arm.com> (raw)
In-Reply-To: <22a06965287dd478ee92f8028ae8ac27e054555d.1793593923.git.nicolinc@nvidia.com>

On 11/2/26 05:19, Nicolin Chen wrote:
> RMR bypass STEs are installed during SMMUv3 probe for StreamIDs listed by
> IORT RMR nodes. A normal boot switches the driver to a fresh stream table
> whose initial STEs abort, so those RMR SIDs need bypass entries before it
> becomes live. This preserves firmware/guest-owned traffic, including vSMMU
> guest MSI cases built around RMR-described SIDs.
> 
> ARM_SMMU_OPT_KDUMP_ADOPT is the opposite case: the driver keeps SMMUEN set
> and adopts the crashed kernel's stream table, so RMR SIDs already have the
> only translation state known to be safe for active in-flight DMA. Replacing
> an adopted STE with bypass can turn translated DMA into physical DMA, then
> point it at the wrong memory.
> 
> arm_smmu_make_bypass_ste() also rewrites the STE in place after clearing it
> first. While the table is live, a concurrent hardware STE fetch can observe
> V=0 or mixed old/new state.
> 
> Leaving the adopted STE unmodified keeps the kdump kernel using the crashed
> kernel's translation. That gives the endpoint driver a chance to probe and
> quiesce the device.
> 
> If the old STE was already abort or invalid, installing bypass would create
> new DMA permission; leaving it alone is a safer failure mode. Later domain
> setup still gets the RMR direct mappings through the reserved-region path.
> 
> Reviewed-by: Pranjal Shrivastava <praan@google.com>
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
> Tested-by: Breno Leitao <leitao@kernel.org>
> Tested-by: Cristian Prundeanu <cpru@amazon.com>
> Tested-by: Shuai Xue <xueshuai@linux.alibaba.com>
> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>

FWIW, regardless of comments below:

Reviewed-by: John Garry <john.garry@arm.com>

> ---
>   drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 13 +++++++++----
>   1 file changed, 9 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> index 1c53c690a2b02..3696d11c852a8 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -5810,6 +5810,14 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
>   	struct list_head rmr_list;
>   	struct iommu_resv_region *e;
>   
> +	/*
> +	 * Kdump

mega nit: "kdump" could better better, as it is a keyword

> adoption keeps the crashed kernel's table live. Rewriting the
> +	 * adopted STE here could expose an in-flight fetch to a transient V=0
> +	 * entry, or change Cfg=translate to Cfg=bypass. Must skip here.
> +	 */
> +	if (smmu->options & ARM_SMMU_OPT_KDUMP_ADOPT)
> +		return;
> +
>   	INIT_LIST_HEAD(&rmr_list);
>   	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);

Did you consider if we should sanitise the adopted ste against what 
iort_get_rmr_sids() returns? I suppose that would add even more complexity.

>   
> @@ -5826,10 +5834,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
>   				continue;
>   			}
>   
> -			/*
> -			 * STE table is not programmed to HW, see
> -			 * arm_smmu_initial_bypass_stes()
> -			 */
> +			/* The fresh stream table is not yet live. */
>   			arm_smmu_make_bypass_ste(smmu,
>   				arm_smmu_get_step_for_sid(smmu, rmr->sids[i]));
>   		}


  reply	other threads:[~2026-11-16 12:27 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-02  5:19 [PATCH v12 00/12] iommu/arm-smmu-v3: Adopt the crashed kernel's stream table for kdump Nicolin Chen
2026-11-02  5:19 ` [PATCH v12 01/12] iommu: Pass in NULL old_domain when attaching a deferred device Nicolin Chen
2026-11-02  5:19 ` [PATCH v12 02/12] iommu/arm-smmu-v3: Init the vmid_map ida before the stream table setup Nicolin Chen
2026-11-16  9:30   ` John Garry
2026-11-02  5:19 ` [PATCH v12 03/12] iommu/arm-smmu-v3: Make the ASID space per SMMU instance Nicolin Chen
2026-11-16  9:46   ` John Garry
2026-11-02  5:19 ` [PATCH v12 04/12] iommu/arm-smmu-v3: Pack the MSI vectors of the used sources Nicolin Chen
2026-11-16 10:29   ` John Garry
2026-11-02  5:19 ` [PATCH v12 05/12] iommu/arm-smmu-v3: Add ARM_SMMU_FEAT_EVTQ for the event queue Nicolin Chen
2026-11-16 10:59   ` John Garry
2026-11-02  5:19 ` [PATCH v12 06/12] iommu/arm-smmu-v3: Disable the EVTQ and the PRIQ in a kdump kernel Nicolin Chen
2026-11-16 11:08   ` John Garry
2026-11-02  5:19 ` [PATCH v12 07/12] iommu/arm-smmu-v3: Add ARM_SMMU_OPT_KDUMP_ADOPT for " Nicolin Chen
2026-11-02  5:19 ` [PATCH v12 08/12] iommu/arm-smmu-v3-kexec: Reserve crashed kernel's ASIDs and VMIDs Nicolin Chen
2026-11-02  5:19 ` [PATCH v12 09/12] iommu/arm-smmu-v3-kexec: Implement is_attach_deferred() Nicolin Chen
2026-11-16 12:03   ` John Garry
2026-11-02  5:19 ` [PATCH v12 10/12] iommu/arm-smmu-v3: Retain CR0_SMMUEN during kdump device reset Nicolin Chen
2026-11-16 12:19   ` John Garry
2026-11-02  5:19 ` [PATCH v12 11/12] iommu/arm-smmu-v3: Skip RMR bypass for kdump adoption Nicolin Chen
2026-11-16 12:26   ` John Garry [this message]
2026-11-02  5:19 ` [PATCH v12 12/12] iommu/arm-smmu-v3: Detect ARM_SMMU_OPT_KDUMP_ADOPT in probe() Nicolin Chen
2026-11-16 12:32   ` John Garry

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=4cf391ff-804a-46a1-8d3e-d0ff8442841f@arm.com \
    --to=john.garry@arm.com \
    --cc=cpru@amazon.com \
    --cc=iommu@lists.linux.dev \
    --cc=jamien@nvidia.com \
    --cc=jgg@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=kas@kernel.org \
    --cc=kevin.tian@intel.com \
    --cc=leitao@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nicolinc@nvidia.com \
    --cc=praan@google.com \
    --cc=robin.murphy@arm.com \
    --cc=smostafa@google.com \
    --cc=will@kernel.org \
    --cc=xueshuai@linux.alibaba.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

all inboxes | Powered by JetHome®