From: Nicolin Chen <nicolinc@nvidia.com>
To: <jgg@nvidia.com>, <kevin.tian@intel.com>, <corbet@lwn.net>,
<will@kernel.org>
Cc: <bagasdotme@gmail.com>, <robin.murphy@arm.com>, <joro@8bytes.org>,
<thierry.reding@gmail.com>, <vdumpa@nvidia.com>,
<jonathanh@nvidia.com>, <shuah@kernel.org>, <jsnitsel@redhat.com>,
<nathan@kernel.org>, <peterz@infradead.org>, <yi.l.liu@intel.com>,
<mshavit@google.com>, <praan@google.com>,
<zhangzekun11@huawei.com>, <iommu@lists.linux.dev>,
<linux-doc@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<linux-arm-kernel@lists.infradead.org>,
<linux-tegra@vger.kernel.org>, <linux-kselftest@vger.kernel.org>,
<patches@lists.linux.dev>, <mochs@nvidia.com>,
<alok.a.tiwari@oracle.com>, <vasant.hegde@amd.com>
Subject: [PATCH v2 00/22] iommufd: Add vIOMMU infrastructure (Part-4 vCMDQ)
Date: Fri, 25 Apr 2025 22:57:55 -0700 [thread overview]
Message-ID: <cover.1745646960.git.nicolinc@nvidia.com> (raw)
The vIOMMU object is designed to represent a slice of an IOMMU HW for its
virtualization features shared with or passed to user space (a VM mostly)
in a way of HW acceleration. This extended the HWPT-based design for more
advanced virtualization feature.
A vCMDQ introduced by this series as a part of the vIOMMU infrastructure
represents a HW supported queue/buffer for VM to use exclusively, e.g.
- NVIDIA's virtual command queue
- AMD vIOMMU's command buffer
either of which is an IOMMU HW feature to directly load and execute cache
invalidation commands issued by a guest kernel, to shoot down TLB entries
that HW cached for guest-owned stage-1 page table entries. This is a big
improvement since there is no VM Exit during an invalidation, compared to
the traditional invalidation pathway by trapping a guest-own invalidation
queue and forwarding those commands/requests to the host kernel that will
eventually fill a HW-owned queue to execute those commands.
Thus, a vCMDQ object, as an initial use case, is all about a guest-owned
HW command queue that VMM can allocate/configure depending on the request
from a guest kernel. Introduce a new IOMMUFD_OBJ_VCMDQ and its allocator
IOMMUFD_CMD_VCMDQ_ALLOC allowing VMM to forward the IOMMU-specific queue
info, such as queue base address, size, and etc.
Meanwhile, a guest-owned command queue needs the kernel (a command queue
driver) to control the queue by reading/writing its consumer and producer
indexes, which means the command queue HW allows the guest kernel to get
a direct R/W access to those registers. Introduce an mmap infrastructure
to the iommufd core so as to support pass through a piece of MMIO region
from the host physical address space to the guest physical address space.
The VMA info (vm_pgoff/size) used by an mmap must be pre-allocated during
the IOMMUFD_CMD_VCMDQ_ALLOC and given those info to the user space as an
output driver-data by the IOMMUFD_CMD_VCMDQ_ALLOC. So, this requires a
driver-specific user data support by a vIOMMU object.
As a real-world use case, this series implements a vCMDQ support to the
tegra241-cmdqv driver for the vCMDQ on NVIDIA Grace CPU. In another word,
this is also the Tegra CMDQV series Part-2 (user-space support), reworked
from Previous RFCv1:
https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/
This enables the HW accelerated feature for NVIDIA Grace CPU. Compared to
the standard SMMUv3 operating in the nested translation mode trapping CMDQ
for TLBI and ATC_INV commands, this gives a huge performance improvement:
70% to 90% reductions of invalidation time were measured by various DMA
unmap tests running in a guest OS.
This is on Github:
https://github.com/nicolinc/iommufd/commits/iommufd_vcmdq-v2
Paring QEMU branch for testing:
https://github.com/nicolinc/qemu/commits/wip/for_iommufd_vcmdq-v2
Changelog
v2
* Add Reviewed-by from Jason
* [smmu] Fix vsmmu initial value
* [smmu] Support impl for hw_info
* [tegra] Rename "slot" to "vsid"
* [tegra] Update kdocs and commit logs
* [tegra] Map/unmap LVCMDQ dynamically
* [tegra] Refcount the previous LVCMDQ
* [tegra] Return -EEXIST if LVCMDQ exists
* [tegra] Simplify VINTF cleanup routine
* [tegra] Use vmid and s2_domain in vsmmu
* [tegra] Rename "mmap_pgoff" to "immap_id"
* [tegra] Add more addr and length validation
* [iommufd] Add more narrative to mmap's kdoc
* [iommufd] Add iommufd_struct_depend/undepend()
* [iommufd] Rename vcmdq_free op to vcmdq_destroy
* [iommufd] Fix bug in iommu_copy_struct_to_user()
* [iommufd] Drop is_io from iommufd_ctx_alloc_mmap()
* [iommufd] Test the queue memory for its contiguity
* [iommufd] Return -ENXIO if address or length fails
* [iommufd] Do not change @min_last in mock_viommu_alloc()
* [iommufd] Generalize TEGRA241_VCMDQ data in core structure
* [iommufd] Add selftest coverage for IOMMUFD_CMD_VCMDQ_ALLOC
* [iommufd] Add iopt_pin_pages() to prevent queue memory from unmapping
v1
https://lore.kernel.org/all/cover.1744353300.git.nicolinc@nvidia.com/
Thanks
Nicolin
Nicolin Chen (22):
iommufd/viommu: Add driver-allocated vDEVICE support
iommu: Pass in a driver-level user data structure to viommu_alloc op
iommufd/viommu: Allow driver-specific user data for a vIOMMU object
iommu: Add iommu_copy_struct_to_user helper
iommufd: Add iommufd_struct_destroy to revert iommufd_viommu_alloc
iommufd/selftest: Support user_data in mock_viommu_alloc
iommufd/selftest: Add covearge for viommu data
iommufd: Abstract iopt_pin_pages and iopt_unpin_pages helpers
iommufd/viommu: Introduce IOMMUFD_OBJ_VCMDQ and its related struct
iommufd/viommmu: Add IOMMUFD_CMD_VCMDQ_ALLOC ioctl
iommufd: Add for-driver helpers iommufd_vcmdq_depend/undepend()
iommufd/selftest: Add coverage for IOMMUFD_CMD_VCMDQ_ALLOC
iommufd: Add mmap interface
iommufd/selftest: Add coverage for the new mmap interface
Documentation: userspace-api: iommufd: Update vCMDQ
iommu/arm-smmu-v3-iommufd: Add vsmmu_alloc impl op
iommu/arm-smmu-v3-iommufd: Support implementation-defined hw_info
iommu/tegra241-cmdqv: Use request_threaded_irq
iommu/tegra241-cmdqv: Simplify deinit flow in
tegra241_cmdqv_remove_vintf()
iommu/tegra241-cmdqv: Do not statically map LVCMDQs
iommu/tegra241-cmdqv: Add user-space use support
iommu/tegra241-cmdqv: Add IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV support
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 25 +-
drivers/iommu/iommufd/io_pagetable.h | 8 +
drivers/iommu/iommufd/iommufd_private.h | 25 +-
drivers/iommu/iommufd/iommufd_test.h | 20 +
include/linux/iommu.h | 43 +-
include/linux/iommufd.h | 146 ++++++
include/uapi/linux/iommufd.h | 113 ++++-
tools/testing/selftests/iommu/iommufd_utils.h | 51 +-
.../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 42 +-
.../iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 451 +++++++++++++++++-
drivers/iommu/iommufd/device.c | 117 +----
drivers/iommu/iommufd/driver.c | 81 ++++
drivers/iommu/iommufd/io_pagetable.c | 95 ++++
drivers/iommu/iommufd/main.c | 58 ++-
drivers/iommu/iommufd/selftest.c | 123 ++++-
drivers/iommu/iommufd/viommu.c | 111 ++++-
tools/testing/selftests/iommu/iommufd.c | 93 +++-
.../selftests/iommu/iommufd_fail_nth.c | 11 +-
Documentation/userspace-api/iommufd.rst | 14 +
19 files changed, 1436 insertions(+), 191 deletions(-)
--
2.43.0
next reply other threads:[~2025-04-26 6:02 UTC|newest]
Thread overview: 146+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-26 5:57 Nicolin Chen [this message]
2025-04-26 5:57 ` [PATCH v2 01/22] iommufd/viommu: Add driver-allocated vDEVICE support Nicolin Chen
2025-04-27 6:23 ` Baolu Lu
2025-04-28 0:41 ` Tian, Kevin
2025-04-28 18:08 ` Nicolin Chen
2025-04-26 5:57 ` [PATCH v2 02/22] iommu: Pass in a driver-level user data structure to viommu_alloc op Nicolin Chen
2025-04-27 6:31 ` Baolu Lu
2025-04-28 17:19 ` Nicolin Chen
2025-04-28 17:28 ` Pranjal Shrivastava
2025-04-26 5:57 ` [PATCH v2 03/22] iommufd/viommu: Allow driver-specific user data for a vIOMMU object Nicolin Chen
2025-04-27 6:36 ` Baolu Lu
2025-04-28 17:52 ` Pranjal Shrivastava
2025-04-30 14:58 ` ALOK TIWARI
2025-04-26 5:57 ` [PATCH v2 04/22] iommu: Add iommu_copy_struct_to_user helper Nicolin Chen
2025-04-27 6:39 ` Baolu Lu
2025-04-28 17:50 ` Pranjal Shrivastava
2025-04-28 18:21 ` Nicolin Chen
2025-04-29 8:31 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 05/22] iommufd: Add iommufd_struct_destroy to revert iommufd_viommu_alloc Nicolin Chen
2025-04-27 6:55 ` Baolu Lu
2025-04-28 17:24 ` Nicolin Chen
2025-04-26 5:58 ` [PATCH v2 06/22] iommufd/selftest: Support user_data in mock_viommu_alloc Nicolin Chen
2025-04-28 18:56 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 07/22] iommufd/selftest: Add covearge for viommu data Nicolin Chen
2025-04-28 19:02 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 08/22] iommufd: Abstract iopt_pin_pages and iopt_unpin_pages helpers Nicolin Chen
2025-04-27 7:22 ` Baolu Lu
2025-04-28 17:41 ` Nicolin Chen
2025-05-05 15:01 ` Jason Gunthorpe
2025-05-05 15:44 ` Nicolin Chen
2025-05-05 15:55 ` Jason Gunthorpe
2025-05-05 16:03 ` Nicolin Chen
2025-05-05 16:05 ` Jason Gunthorpe
2025-05-05 16:19 ` Nicolin Chen
2025-05-05 16:56 ` Jason Gunthorpe
2025-04-28 20:14 ` Pranjal Shrivastava
2025-04-28 22:12 ` Nicolin Chen
2025-04-28 23:34 ` Nicolin Chen
2025-04-29 18:03 ` Pranjal Shrivastava
2025-05-06 9:36 ` Tian, Kevin
2025-05-06 19:17 ` Nicolin Chen
2025-05-07 7:22 ` Tian, Kevin
2025-05-07 7:36 ` Nicolin Chen
2025-05-07 7:51 ` Tian, Kevin
2025-04-26 5:58 ` [PATCH v2 09/22] iommufd/viommu: Introduce IOMMUFD_OBJ_VCMDQ and its related struct Nicolin Chen
2025-04-28 1:09 ` Baolu Lu
2025-04-28 18:10 ` Nicolin Chen
2025-05-05 15:02 ` Jason Gunthorpe
2025-05-05 15:45 ` Nicolin Chen
2025-04-28 21:01 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 10/22] iommufd/viommmu: Add IOMMUFD_CMD_VCMDQ_ALLOC ioctl Nicolin Chen
2025-04-28 1:32 ` Baolu Lu
2025-04-28 18:58 ` Nicolin Chen
2025-04-29 6:11 ` Baolu Lu
2025-04-28 12:12 ` Vasant Hegde
2025-04-28 20:02 ` Nicolin Chen
2025-04-29 5:34 ` Vasant Hegde
2025-04-29 6:45 ` Nicolin Chen
2025-04-29 10:22 ` Vasant Hegde
2025-04-29 17:14 ` Nicolin Chen
2025-04-30 4:22 ` Vasant Hegde
2025-04-30 8:01 ` Nicolin Chen
2025-04-30 10:21 ` Vasant Hegde
2025-05-06 9:25 ` Tian, Kevin
2025-05-06 20:12 ` Nicolin Chen
2025-05-07 7:25 ` Tian, Kevin
2025-05-07 7:37 ` Nicolin Chen
2025-05-07 12:33 ` Jason Gunthorpe
2025-05-07 20:51 ` Nicolin Chen
2025-04-28 21:34 ` Pranjal Shrivastava
2025-04-28 22:44 ` Nicolin Chen
2025-04-29 8:28 ` Pranjal Shrivastava
2025-04-29 18:10 ` Pranjal Shrivastava
2025-04-29 18:15 ` Nicolin Chen
2025-04-29 18:57 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 11/22] iommufd: Add for-driver helpers iommufd_vcmdq_depend/undepend() Nicolin Chen
2025-04-28 2:22 ` Baolu Lu
2025-04-28 18:17 ` Nicolin Chen
2025-04-29 12:40 ` Pranjal Shrivastava
2025-04-29 17:10 ` Nicolin Chen
2025-04-29 17:59 ` Pranjal Shrivastava
2025-04-29 18:07 ` Nicolin Chen
2025-04-29 18:44 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 12/22] iommufd/selftest: Add coverage for IOMMUFD_CMD_VCMDQ_ALLOC Nicolin Chen
2025-04-26 5:58 ` [PATCH v2 13/22] iommufd: Add mmap interface Nicolin Chen
2025-04-28 2:50 ` Baolu Lu
2025-04-28 18:54 ` Nicolin Chen
2025-05-05 16:50 ` Jason Gunthorpe
2025-05-05 17:21 ` Nicolin Chen
2025-05-05 17:28 ` Jason Gunthorpe
2025-05-05 20:07 ` Nicolin Chen
2025-05-06 9:22 ` Tian, Kevin
2025-05-06 12:55 ` Jason Gunthorpe
2025-05-06 12:54 ` Jason Gunthorpe
2025-05-06 20:54 ` Nicolin Chen
2025-05-07 12:36 ` Jason Gunthorpe
2025-05-07 20:49 ` Nicolin Chen
2025-04-29 20:24 ` Pranjal Shrivastava
2025-04-29 20:34 ` Pranjal Shrivastava
2025-04-29 20:39 ` Nicolin Chen
2025-04-29 20:55 ` Pranjal Shrivastava
2025-04-29 21:05 ` Nicolin Chen
2025-04-29 21:35 ` Pranjal Shrivastava
2025-04-29 21:46 ` Nicolin Chen
2025-04-29 21:57 ` Pranjal Shrivastava
2025-05-05 16:55 ` Jason Gunthorpe
2025-05-05 17:27 ` Nicolin Chen
2025-05-05 17:31 ` Jason Gunthorpe
2025-05-05 19:50 ` Nicolin Chen
2025-05-06 12:52 ` Jason Gunthorpe
2025-05-06 19:30 ` Nicolin Chen
2025-05-07 12:39 ` Jason Gunthorpe
2025-05-07 21:09 ` Nicolin Chen
2025-05-07 22:08 ` Jason Gunthorpe
2025-05-08 3:49 ` Nicolin Chen
2025-05-08 9:15 ` Tian, Kevin
2025-05-08 12:12 ` Jason Gunthorpe
2025-05-08 17:14 ` Nicolin Chen
2025-05-05 18:47 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 14/22] iommufd/selftest: Add coverage for the new " Nicolin Chen
2025-04-26 5:58 ` [PATCH v2 15/22] Documentation: userspace-api: iommufd: Update vCMDQ Nicolin Chen
2025-04-28 14:31 ` Bagas Sanjaya
2025-04-28 19:00 ` Nicolin Chen
2025-04-26 5:58 ` [PATCH v2 16/22] iommu/arm-smmu-v3-iommufd: Add vsmmu_alloc impl op Nicolin Chen
2025-04-29 21:36 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 17/22] iommu/arm-smmu-v3-iommufd: Support implementation-defined hw_info Nicolin Chen
2025-04-29 21:44 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 18/22] iommu/tegra241-cmdqv: Use request_threaded_irq Nicolin Chen
2025-04-29 21:47 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 19/22] iommu/tegra241-cmdqv: Simplify deinit flow in tegra241_cmdqv_remove_vintf() Nicolin Chen
2025-04-29 22:05 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 20/22] iommu/tegra241-cmdqv: Do not statically map LVCMDQs Nicolin Chen
2025-04-29 20:43 ` ALOK TIWARI
2025-04-29 22:32 ` Pranjal Shrivastava
2025-04-29 22:37 ` Nicolin Chen
2025-04-26 5:58 ` [PATCH v2 21/22] iommu/tegra241-cmdqv: Add user-space use support Nicolin Chen
2025-04-29 19:47 ` ALOK TIWARI
2025-04-29 21:12 ` Nicolin Chen
2025-04-30 21:59 ` Pranjal Shrivastava
2025-04-30 22:39 ` Nicolin Chen
2025-05-01 0:54 ` Nicolin Chen
2025-05-01 21:46 ` Pranjal Shrivastava
2025-05-01 21:45 ` Pranjal Shrivastava
2025-04-26 5:58 ` [PATCH v2 22/22] iommu/tegra241-cmdqv: Add IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV support Nicolin Chen
2025-04-30 15:07 ` ALOK TIWARI
2025-04-30 22:03 ` Pranjal Shrivastava
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.1745646960.git.nicolinc@nvidia.com \
--to=nicolinc@nvidia.com \
--cc=alok.a.tiwari@oracle.com \
--cc=bagasdotme@gmail.com \
--cc=corbet@lwn.net \
--cc=iommu@lists.linux.dev \
--cc=jgg@nvidia.com \
--cc=jonathanh@nvidia.com \
--cc=joro@8bytes.org \
--cc=jsnitsel@redhat.com \
--cc=kevin.tian@intel.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-tegra@vger.kernel.org \
--cc=mochs@nvidia.com \
--cc=mshavit@google.com \
--cc=nathan@kernel.org \
--cc=patches@lists.linux.dev \
--cc=peterz@infradead.org \
--cc=praan@google.com \
--cc=robin.murphy@arm.com \
--cc=shuah@kernel.org \
--cc=thierry.reding@gmail.com \
--cc=vasant.hegde@amd.com \
--cc=vdumpa@nvidia.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;
as well as URLs for NNTP newsgroup(s).