Linux IOMMU Development
 help / color / mirror / Atom feed
From: Nicolin Chen <nicolinc@nvidia.com>
To: <will@kernel.org>, <robin.murphy@arm.com>, <jgg@nvidia.com>
Cc: <joro@8bytes.org>, <kevin.tian@intel.com>, <praan@google.com>,
	<nathan@kernel.org>, <yi.l.liu@intel.com>, <peterz@infradead.org>,
	<mshavit@google.com>, <jsnitsel@redhat.com>,
	<smostafa@google.com>, <jeff.johnson@oss.qualcomm.com>,
	<zhangzekun11@huawei.com>, <linux-arm-kernel@lists.infradead.org>,
	<iommu@lists.linux.dev>, <linux-kernel@vger.kernel.org>,
	<shameerali.kolothum.thodi@huawei.com>
Subject: [PATCH v2 00/11] iommu/arm-smmu-v3: Allocate vmid per vsmmu instead of s2_parent
Date: Mon, 14 Apr 2025 21:57:35 -0700	[thread overview]
Message-ID: <cover.1744692494.git.nicolinc@nvidia.com> (raw)

With a system having multiple SMMU physical instances, multiple vSMMUs can
be allocated for a VM that deivces behind different SMMUs are assigned to.
In such a use case, the IPA->PA mappings (i.e. the stage-2 I/O page table)
can be shared across the vSMMU instances.

With a shareable S2 parent domain, it is more natural to store a vmid per
vSMMU instance v.s. a shared S2 domain, since each physical SMMU instance
maintains its own vmid bitmap.

Have a few patches to get the functions ready for the vmid migration. And
decouple the vmid from S2 parent domains and move its allocation to vSMMU
instances. Note that a regular S2 domain (!nest_parent) has to retain the
s2_cfg and vmid for non-nesting use cases, if the SMMU HW doesn't support
stage 1. Maintain a per-S2-domain vsmmus list and a per-vSMMU ats_devices
list to iterate for S2 cache invalidation cmds and ATC invalidation cmds.

This is on Github:
https://github.com/nicolinc/iommufd/commits/smmuv3_vmid-v2

Changelog
v2
 * Add Reviewed-by from Jason and Pranjal
 * Add WARN_ON_ONCE(!vmid) in arm_smmu_make_s2_domain_ste()
 * Add arm_smmu_s2_parent_can_share() for a compatibility check
 * Introduce arm_smmu_s2_parent_tlb_inv_* helpers replacing the non-nesting
   routines
 * Introduce arm_vsmmu_atc_inv_domain() using a per-vSMMU ats_devices list,
   replacing the nested_ats_flush in struct arm_smmu_master_domain
v1
 https://lore.kernel.org/all/cover.1741150594.git.nicolinc@nvidia.com/

Thanks
Nicolin

Nicolin Chen (11):
  iommu/arm-smmu-v3: Pass in vmid to arm_smmu_make_s2_domain_ste()
  iommu/arm-smmu-v3: Pass in smmu/iommu_domain to
    __arm_smmu_tlb_inv_range()
  iommu/arm-smmu-v3: Share cmdq/cmd helpers with arm-smmu-v3-iommufd
  iommu/arm-smmu-v3: Add an inline arm_smmu_tlb_inv_vmid helper
  iommu/arm-smmu-v3: Rename arm_smmu_attach_prepare_vmaster
  iommu/arm-smmu-v3: Introduce arm_smmu_s2_parent_tlb_ invalidation
    helpers
  iommu/arm-smmu-v3: Introduce arm_vsmmu_atc_inv_domain()
  iommu/arm-smmu-v3: Use vSMMU helpers for S2 and ATC invalidations
  iommu/arm-smmu-v3: Clean up nested_ats_flush from master_domain
  iommu/arm-smmu-v3: Decouple vmid from S2 nest_parent domain
  iommu/arm-smmu-v3: Allow to share S2 nest_parent domain across vSMMUs

 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  77 +++++++-
 .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c     | 175 ++++++++++++++++--
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c  |   3 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 139 +++++++-------
 4 files changed, 297 insertions(+), 97 deletions(-)

-- 
2.43.0


             reply	other threads:[~2025-04-15  4:58 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-15  4:57 Nicolin Chen [this message]
2025-04-15  4:57 ` [PATCH v2 01/11] iommu/arm-smmu-v3: Pass in vmid to arm_smmu_make_s2_domain_ste() Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 02/11] iommu/arm-smmu-v3: Pass in smmu/iommu_domain to __arm_smmu_tlb_inv_range() Nicolin Chen
2025-05-15 15:06   ` Will Deacon
2025-04-15  4:57 ` [PATCH v2 03/11] iommu/arm-smmu-v3: Share cmdq/cmd helpers with arm-smmu-v3-iommufd Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 04/11] iommu/arm-smmu-v3: Add an inline arm_smmu_tlb_inv_vmid helper Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 05/11] iommu/arm-smmu-v3: Rename arm_smmu_attach_prepare_vmaster Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 06/11] iommu/arm-smmu-v3: Introduce arm_smmu_s2_parent_tlb_ invalidation helpers Nicolin Chen
2025-04-15 12:50   ` Jason Gunthorpe
2025-04-15 20:10     ` Nicolin Chen
2025-04-15 23:46       ` Jason Gunthorpe
2025-04-15  4:57 ` [PATCH v2 07/11] iommu/arm-smmu-v3: Introduce arm_vsmmu_atc_inv_domain() Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 08/11] iommu/arm-smmu-v3: Use vSMMU helpers for S2 and ATC invalidations Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 09/11] iommu/arm-smmu-v3: Clean up nested_ats_flush from master_domain Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 10/11] iommu/arm-smmu-v3: Decouple vmid from S2 nest_parent domain Nicolin Chen
2025-04-15  4:57 ` [PATCH v2 11/11] iommu/arm-smmu-v3: Allow to share S2 nest_parent domain across vSMMUs Nicolin Chen

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=cover.1744692494.git.nicolinc@nvidia.com \
    --to=nicolinc@nvidia.com \
    --cc=iommu@lists.linux.dev \
    --cc=jeff.johnson@oss.qualcomm.com \
    --cc=jgg@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=jsnitsel@redhat.com \
    --cc=kevin.tian@intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mshavit@google.com \
    --cc=nathan@kernel.org \
    --cc=peterz@infradead.org \
    --cc=praan@google.com \
    --cc=robin.murphy@arm.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=smostafa@google.com \
    --cc=will@kernel.org \
    --cc=yi.l.liu@intel.com \
    --cc=zhangzekun11@huawei.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