mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: fuwenxin <fuwenxin@linux.alibaba.com>
To: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
	linux-iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
	joro@8bytes.org, jgg@nvidia.com
Cc: fuwenxin <fuwenxin@linux.alibaba.com>,
	vasant.hegde@amd.com, jon.grimm@amd.com, yi.l.liu@intel.com,
	kevin.tian@intel.com, nicolinc@nvidia.com, wnliu@google.com,
	Guanghui Feng <guanghuifeng@linux.alibaba.com>,
	Guixin Liu <kanie@linux.alibaba.com>
Subject: Re: [PATCH v5 19/24] iommu/amd: Add per-segment translate device ID pool
Date: Thu, 24 Sep 2026 20:44:01 +0800	[thread overview]
Message-ID: <20260924124403.3858095-1-fuwenxin@linux.alibaba.com> (raw)
In-Reply-To: <20260914184750.222939-20-suravee.suthikulpanit@amd.com>

Hi Suravee,

> A translate device ID (TransDevID) is a host device-table index used
> by hardware vIOMMU. VFCTRL guest-misc names the slot; that DTE holds
> the nest-parent v1 table for GPA->SPA walks of guest IOMMU traffic.

> Reserve PCI requestor IDs in a per-segment pool so they are not
> used as vIOMMU translation DTEs. The device table is per-segment,
> so the pool is too.
>
> Add trans_devid.c with pci_seg init/fini and
> amd_iommu_trans_devid_reserve() from probe_device(). Keep
> reservations for the pci_seg lifetime, including after
> amd_iommu_release_device().

Reservation only happens on the probe path, but some DTE-slot holders
never probe, so their devids stay unreserved while
trans_devid_find_free_locked() [patch 22] treats any xa_load()==NULL
slot as free.

One such holder is the IOMMU's own function: init.c deliberately does
rlookup_table[iommu->devid] = NULL , so it never reaches probe_device()
 -- yet patch 13 programs the self DTE at exactly iommu->devid. 

Thanks,
fuwenxin

  reply	other threads:[~2026-09-24 12:44 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-14 18:47 [PATCH v5 00/24] iommu/amd: Introduce AMD Hardware-accelerated Virtualized IOMMU (vIOMMU) Support Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 01/24] iommu/amd: Introduce vIOMMU-specific events and event Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 02/24] iommu/amd: Introduce EVENT_TYPE_GUEST_EVENT_FAULT Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 03/24] iommu/amd: Detect and initialize AMD vIOMMU feature Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 04/24] iommu/amd: Introduce IOMMUFD vIOMMU support for AMD Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 05/24] iommu/amd: Allocate Guest IDs for IOMMUFD vIOMMU instances Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 06/24] iommu/amd: Map vIOMMU VF and VF Control MMIO BARs Suravee Suthikulpanit
2026-09-22  6:43   ` Guixin Liu
2026-09-14 18:47 ` [PATCH v5 07/24] iommu/amd: Add support for AMD vIOMMU VF MMIO region Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 08/24] iommu/amd: Introduce Reset vMMIO Command Suravee Suthikulpanit
2026-09-19 15:11   ` guanghuifeng
2026-09-21  9:10     ` Suthikulpanit, Suravee
2026-09-14 18:47 ` [PATCH v5 09/24] iommu/amd: Introduce and map vIOMMU private IPA region Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 10/24] iommu/amd: Pass iommu to device_flush_dte() Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 11/24] iommu/amd: Pass iommu and devid to amd_iommu_make_clear_dte() Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 12/24] iommu/amd: Store per-segment iommu_dev_data in an xarray Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 13/24] iommu/amd: Program IOMMU DTE with the private IPA domain Suravee Suthikulpanit
2026-09-19 15:26   ` guanghuifeng
2026-09-22  6:57   ` Guixin Liu
2026-09-14 18:47 ` [PATCH v5 14/24] iommu/amd: Add per-VM private IPA alloc/map helpers Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 15/24] iommu/amd: Add helper functions to manage DevID / DomID mapping tables Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 16/24] iommu/amd: Add IOMMUFD vDevice and DevID mapping Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 17/24] iommu/amd: Program nested DTE and DomID map on attach Suravee Suthikulpanit
2026-09-22  7:11   ` Guixin Liu
2026-09-14 18:47 ` [PATCH v5 18/24] iommu/amd: Init and clear vIOMMU DevID and DomID maps Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 19/24] iommu/amd: Add per-segment translate device ID pool Suravee Suthikulpanit
2026-09-24 12:44   ` fuwenxin [this message]
2026-09-14 18:47 ` [PATCH v5 20/24] iommu/amd: Reserve translate-device-id for PCI requestor aliases Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 21/24] iommu/amd: Add translation DTE and VFctrl TransDevID helpers Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 22/24] iommu/amd: Add translate-device-id alloc/free with vIOMMU owner Suravee Suthikulpanit
2026-09-14 18:47 ` [PATCH v5 23/24] iommu/amd: Assign per-vIOMMU translate device ID Suravee Suthikulpanit
2026-09-22  7:09   ` Guixin Liu
2026-09-14 18:47 ` [PATCH v5 24/24] iommu/amd: Relocate vIOMMU translate-device-id on PCI reserve Suravee Suthikulpanit

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=20260924124403.3858095-1-fuwenxin@linux.alibaba.com \
    --to=fuwenxin@linux.alibaba.com \
    --cc=guanghuifeng@linux.alibaba.com \
    --cc=jgg@nvidia.com \
    --cc=jon.grimm@amd.com \
    --cc=joro@8bytes.org \
    --cc=kanie@linux.alibaba.com \
    --cc=kevin.tian@intel.com \
    --cc=linux-iommu@lists.linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nicolinc@nvidia.com \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=vasant.hegde@amd.com \
    --cc=wnliu@google.com \
    --cc=yi.l.liu@intel.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®