Skip to content

[linux-nvidia-6.18-next] Backport: Add Extended GPU Memory (EGM) virtualization support - #559

Open
kelsey-steele wants to merge 19 commits into
NVIDIA:linux-nvidia-6.18-nextfrom
kelsey-steele:kelseys/backport-egm-6.18
Open

[linux-nvidia-6.18-next] Backport: Add Extended GPU Memory (EGM) virtualization support#559
kelsey-steele wants to merge 19 commits into
NVIDIA:linux-nvidia-6.18-nextfrom
kelsey-steele:kelseys/backport-egm-6.18

Conversation

@kelsey-steele

@kelsey-steele kelsey-steele commented Sep 2, 2026 •
edited
Loading

Copy link
Copy Markdown
Collaborator

Summary

Backports the EGM (Extended GPU Memory) driver support for Grace GPU passthrough.

18 of the 19 patches are clean cherry-picks from 26.04_linux-nvidia.

The one backport "arm64: configs: Build CONFIG_NVGRACE_EGM as LKM", is only such due to context changes around the code. The patch itself is the same.

Testing

  • Builds cleanly and boots (Grace/GH200).
  • nvgrace_egm loads and correctly attaches as an auxiliary device of nvgrace_gpu_vfio_pci (lsmod shows nvgrace_egm ... 1 nvgrace_gpu_vfio_pci).
  • I am blocked on testing full functional verification (/dev/egm* device creation, EGM-backed VM boot) as I seem to be restricted on enabling EGM through the bios on my reserved machine. I put out a request to enable this and waiting to hear back. Though since this was all a clean backport from 26.04 and lived in our 6.17 kernel also, I'm setting up the PR.

ankita-nv and others added 19 commits September 1, 2026 18:09
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Introduce module to manage EGM
c1ca7d6 
BugLink: https://bugs.launchpad.net/bugs/2119656

The Extended GPU Memory (EGM) feature enables the GPU access to
the system memory across sockets and nodes. In this mode, the
physical memory can be allocated for GPU usage from anywhere
in a multi-node system. The feature is being extended to
virtualization.

EGM when enabled in the virtualization stack, the host memory
is partitioned into 2: One partition for the Host OS usage, and
a second EGM region. The EGM region essentially becomes the
system memory of the VM. The following figure shows the memory map
in the virtualization environment.

|---- Sysmem ----|                  |--- GPU mem ---|  VM Memory Map
|                |                  |               |
|                |                  |               |
|------ EGM -----|--Host Mem----|   |--- GPU mem ---|  Host Memory Map

The EGM region is not available to the host memory for its usage as it
is not added to the kernel. Its base HPA and the length is communicated
through the DSDT entries. A linear mapping between the VM IPA and system
HPA is a requirement for EGM support. The EGM region is thus assigned to
a VM by mapping the QEMU VMA to a linearly increasing HPA of the EGM
region using remap_pfn_range().

Introduce a new nvgrace-egm helper module to nvgrace-gpu to manage the
EGM/VM region for the VM.

nvgrace-egm module handles the following:
1. Fetch the EGM memory properties (base HPA, length, proximity domain).
2. Create a char device that can be used as memory-backend-file by Qemu
for the VM and implement file operations. The char device is /dev/egmX,
where X is the PXM node ID of the EGM being mapped fetched in 1.
3. Zero the EGM memory on first device open().
4. Map the QEMU VMA to the EGM region using remap_pfn_range.
5. Cleaning up state and destroying the chardev on device unbind.

Signed-off-by: Ankit Agrawal <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 892ac24 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 3a1b819 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off-by: Brad Figg <[email protected]>

(cherry picked from commit 8807f4b noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>
(backported from commit fa30498 noble:linux-nvidia-6.17)
[jacobmartin: adjust patch context to align with upstream commit
e5f19b6 ("vfio/nvgrace-gpu: register device memory for poison
handling"), as opposed to the original SAUCE version of the
same patch.]
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 5a1e11b https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Handle pages with ECC errors on the EGM
d769dad 
BugLink: https://bugs.launchpad.net/bugs/2119656

It is possible for some system memory pages on the EGM to
have uncorrectable ECC errors. A list of pages known with such
errors (referred as retired pages) are maintained by the Host
UEFI. The Host UEFI populates such list in a reserved region.
It communicates the SPA of this region through a ACPI DSDT property.

nvgrace-egm module is responsible to store the list of retired page
offsets to be made available for usermode processes. The module:
1. Get the reserved memory region SPA and maps to it to fetch
the list of bad pages.
2. Calculate the retired page offsets in the EGM and stores it.
3. Expose an ioctl to allow querying of the offsets.

The ioctl is called by usermode apps such as QEMU to get the
retired page offsets. The usermode apps are expected to take
appropriate action to communicate the list to the VM.

Signed-off-by: Ankit Agrawal <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit be54641 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit c4cb193 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 6b0a6d6 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 6494245 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 4d66732 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: arm64: configs: Build CONFIG_NVGRACE_EGM as LKM
8f4d914 
BugLink: https://bugs.launchpad.net/bugs/2119656

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 5bb23c1 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 7d2ea55 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 077c834 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit f5a03d0 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(backported from commit 48a4124 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
[kelseys: no changes to patch, resolved context conflict]
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Move the egm header file to include
d744ddc 
BugLink: https://bugs.launchpad.net/bugs/2119656

nvgrace-egm exposes the API register_egm_node & unregister_egm_node
to manage EGM (Extended GPU Memory) present on the system.

To allow out-of-tree driver such as nvidia-vgpu-vfio make use of them,
move the declaration to a new nvgrace-egm.h in include.

Signed-off-by: Ankit Agrawal <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit bed340f https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit a961663 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 020c46c noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>
(cherry picked from commit 739457a noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 627a278 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Free region memory during unregistra…
d0e68bb 
…tion

BugLink: https://bugs.launchpad.net/bugs/2119656

Free the kmalloc'd region when the EGM is unregistered.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit fc592b9 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit f24760c https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 374b166 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 8f781d0 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit de1f033 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Move region hash initialization
fb1ea76 
BugLink: https://bugs.launchpad.net/bugs/2119656

Move region hash initiaization alongside the other region initialization
statements to avoid situations where the hash table was not properly
initialized.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 8021c1d https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit e1264a6 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 0f8a098 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 22f790a noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit b0afaa8 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Handle and convey EGM registration e…
f8d9d14 
…rrors

BugLink: https://bugs.launchpad.net/bugs/2119656

Update error handling within EGM regiration routine to catch and
return errors to the caller.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit a57210c https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit a706ff8 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit edc0ac0 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit e7a177e noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit b8d20f6 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-gpu: Handle EGM registration failure
6a5d4d3 
BugLink: https://bugs.launchpad.net/bugs/2119656

Detect and handle a failure from the EGM registration service.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit f18eee3 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 8371b68 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit be5ae8f noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 2dd5903 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit d841a67 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Address sparse errors
a879646 
BugLink: https://bugs.launchpad.net/bugs/2119656

Fix minor syntax errors from sparse.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit bbb64e6 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit fe78194 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit b192960 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit c1d3f21 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 9145d3c https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Ensure ACPI value reads are successful
23ccee9 
BugLink: https://bugs.launchpad.net/bugs/2119656

Ensure ACPI table reads are successful prior to using the value.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit b2947b0 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 9258355 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 2c5b472 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 3f72f24 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 63ccf20 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Avoid invalid retired pages base
064a975 
BugLink: https://bugs.launchpad.net/bugs/2119656

Some environments may provide a "nvidia,egm-retired-pages-data-base” but
fail to populate it with a base address, leaving it NULL. Mapping this
invalid value results in a synchronous exception when the region is first
touched. Detect a NULL value, generate a warning to draw attention to the
firmware bug, and return without mapping.

INFO:    th500_ras_intr_handler: External Abort reason=1 syndrome=0x92000410 flags=0x1
[   82.104493] Internal error: synchronous external abort: 0000000096000410 [NVIDIA#1] SMP
[   82.114898] Modules linked in: nvgrace_gpu_vfio_pci(E) nvgrace_egm(E)
[   82.257218] CPU: 0 PID: 10 Comm: kworker/0:1 Tainted: G           OE      6.8.12+ NVIDIA#5
[   82.265135] Hardware name: NVIDIA GH200 P5042, BIOS 24103110 20241031
[   82.271720] Workqueue: events work_for_cpu_fn
[   82.276180] pstate: 03400009 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
[   82.283298] pc : register_egm_node+0x2cc/0x440 [nvgrace_egm]
[   82.289087] lr : register_egm_node+0x2c4/0x440 [nvgrace_egm]
[   82.294872] sp : ffff8000802ebc30
[   82.298254] x29: ffff8000802ebc60 x28: 00000000000000ff x27: 0000000000000000
[   82.305550] x26: ffff000087a320c8 x25: ffff0000a5700000 x24: ffff000087a32000
[   82.312846] x23: ffffa77cd758e368 x22: 0000000000000000 x21: ffffa77cd758c640
[   82.320141] x20: ffffa77cd758e170 x19: ffff800081e7d000 x18: ffff800080293038
[   82.327437] x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
[   82.334732] x14: 0000000000000000 x13: 65203a65646f6e5f x12: 0000000000000000
[   82.342027] x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000
[   82.349322] x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000
[   82.356618] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000
[   82.363913] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff800081e7d000
[   82.371210] Call trace:
[   82.373705]  register_egm_node+0x2cc/0x440 [nvgrace_egm]
[   82.379135]  nvgrace_gpu_probe+0x2ac/0x528 [nvgrace_gpu_vfio_pci]
[   82.385366]  local_pci_probe+0x4c/0xe0
[   82.389198]  work_for_cpu_fn+0x28/0x58
[   82.393026]  process_one_work+0x168/0x3f0
[   82.397123]  worker_thread+0x360/0x480
[   82.400952]  kthread+0x11c/0x128
[   82.404248]  ret_from_fork+0x10/0x20
[   82.407906] Code: d2820001 940002b3 aa0003f3 b4fffac0 (f9400017)
[   82.414134] ---[ end trace 0000000000000000 ]---

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 7ba2930 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 349fb1c https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 6e9c94a noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit c5992d5 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit aff377b https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Update EGM unregistration API
9b0b922 
BugLink: https://bugs.launchpad.net/bugs/2119656

In an effort to simplify the programming model, use a symmetrical model
for the the EGM regsiration APIs. This avoids the caller needing to keep
a cookie or even have knowlege of if EGM is supported. Update the EGM
unregisration API to use the PCI device as its parameter.

Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit d8903ec https://github.com/nvmochs/NV-Kernels/tree/vegm_01232025)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 5839fc5 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit f6fb40e noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 0e607bc noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit c89cfea https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: track GPUs associated with the EGM r…
2ec85b3 
…egions

BugLink: https://bugs.launchpad.net/bugs/2119656

GB200 systems could have multiple GPUs associated with
an EGM region. For proper EGM functionality the host
topology in terms of GPU affinity has to be replicated
in the VM. Hence the EGM region structure must track the
GPU devices belonging to the same socket.

On the device probe, the device pci_dev struct is added to a
linked list of the appropriate EGM region.

Similarly on device remove, the pci_dev struct for the GPU
is removed from the EGM region.

Signed-off-by: Ankit Agrawal <[email protected]>
Ref: sj24: /home/nvidia/ankita/kernel_patches/0001_vfio_nvgrace-egm_track_GPUs_associated_with_the_EGM_regions.patch
(koba: Enhance error handling, Remove egm_node from unregister_egm_node
and move destroy_egm_chardev a little forward)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 0222c35 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 5ba1a1f noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit c167095 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 1f08cff https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: list gpus through sysfs
34a44e5 
BugLink: https://bugs.launchpad.net/bugs/2119656

To replicate the host EGM topology in the VM in terms of
the GPU affinity, the userspace need to be aware of which
GPUs belong to the same socket as the EGM region.

Expose the list of GPUs associated with an EGM region
through sysfs. The list can be queried from the location
/sys/devices/virtual/egm/egmX/gpu_devices.

Signed-off-by: Ankit Agrawal <[email protected]>
Ref: sj24: /home/nvidia/ankita/kernel_patches/0002_vfio_nvgrace-egm_list_gpus_through_sysfs.patch
(koba: Enchance error handling for sysfs_create_group)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit fec2356 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 5dde2f0 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit a5284ca noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit cc460ff https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: expose the egm size through sysfs
3555f60 
BugLink: https://bugs.launchpad.net/bugs/2119656

To allocate the EGM, the userspace need to know it's size. Currently,
there is no easy way for the userspace to determine that.

Make nvgrace-egm expose the size through sysfs that can be queried
by the userspace from /sys/devices/virtual/egm/egmX/egm_size.

Signed-off-by: Ankit Agrawal <[email protected]>
Ref: sj24: /home/nvidia/ankita/kernel_patches/0003_vfio_nvgrace-egm_expose_the_egm_size_through_sysfs.patch
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit dcdcef2 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 9940157 noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit e025c29 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit 4bf52ef https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: register EGM PFNMAP range with memor…
4d1cbca 
…y_failure

BugLink: https://bugs.launchpad.net/bugs/2138892

EGM carveout memory is mapped directly into userspace (QEMU) and is not
added to the kernel. It is not managed by the kernel page allocator and
has no struct pages. The module can thus utilize the Linux memory manager's
memory_failure mechanism for regions with no struct pages. The Linux MM
code exposes register/unregister APIs allowing modules to register such
memory regions for memory_failure handling.

Register the EGM PFN range with the MM memory_failure infrastructure on
open, and unregister it on the last close. Provide a PFN-to-VMA offset
callback that validates the PFN is within the EGM region and the VMA,
then converts it to a file offset and records the poisoned offset in the
existing hashtable for reporting to userspace.

Signed-off-by: Ankit Agrawal <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Acked-by: Noah Wager <[email protected]>
Signed-off-by: Brad Figg <[email protected]>

(cherry picked from commit 3fde504 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit de5a032 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nvmochs @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Address smatch errors
7f8c1e0 
BugLink: https://bugs.launchpad.net/bugs/2119656

Return the intended errno upon a copyout fault, remove unnecessary
checks following container_of pointer derivation, and use the correct
macro and types for overflow checking.

Signed-off-by: Matthew R. Ochs <[email protected]>
Acked-by: Kai-Heng Feng <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Acked-by: Koba Ko <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 429910b https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.8-next)
Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit bda63f3 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit 942bf3b noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(cherry picked from commit 63dd059 noble:linux-nvidia-6.17)
Signed-off-by: Matthew R. Ochs <[email protected]>

(cherry picked from commit f8c59b7 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@kobak2026 @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: Add null pointer checks after memory…
65b2930 
… allocations

BugLink: https://bugs.launchpad.net/bugs/2119656

Add missing null pointer checks after vzalloc() calls in the NVIDIA
Grace GPU driver's EGM (External GPU Memory) handling code. This
prevents potential null pointer dereferences in the memory failure
handling and bad page fetching functions, providing proper error
handling for allocation failures.

Signed-off-by: Koba Ko <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Carol L. Soto <[email protected]>
Signed-off-by: Matthew R. Ochs <[email protected]>
(cherry picked from commit 63127e2 https://github.com/NVIDIA/NV-Kernels/tree/24.04_linux-nvidia-adv-6.11-next)
Signed-off-by: Nirmoy Das <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matt Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off--by: Brad Figg <[email protected]>

(cherry picked from commit e5f0c8d noble:linux-nvidia-6.14)
Signed-off-by: Abdur Rahman <[email protected]>

(backported from commit 862ed5a noble:linux-nvidia-6.17)
[mochs: Addressed collission for a null pointer check that is no longer needed]
Signed-off-by: Matthew R. Ochs <[email protected]>

(cherry picked from commit 8e8763e https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@ankita-nv @kelsey-steele
NVIDIA: SAUCE: vfio/nvgrace-egm: split zapping EGM into 1GB chunks
c5b8b94 
BugLink: https://bugs.launchpad.net/bugs/2142160

When initializing EGM (Extended GPU Memory) regions, the current
implementation performs a single memset operation over the entire
memory region. For very large regions, this can result in long-running
uninterruptible operations that may cause system responsiveness issues
or trigger watchdog timeouts.

Split the memset operation into 1GB chunks.

Signed-off-by: Ankit Agrawal <[email protected]>
Acked-by: Carol L Soto <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Acked-by: Noah Wager <[email protected]>
Acked-by: Jacob Martin <[email protected]>
Signed-off-by: Brad Figg <[email protected]>

(cherry picked from commit 3554744 noble:linux-nvidia-6.17)
Signed-off-by: Jacob Martin <[email protected]>

(cherry picked from commit a577394 https://github.com/NVIDIA/NV-Kernels/tree/26.04_linux-nvidia)
Signed-off-by: Kelsey Steele <[email protected]>
@nirmoy nirmoy added the help wanted Extra attention is needed label Sep 2, 2026
@nirmoy

nirmoy commented Sep 2, 2026 •
edited
Loading

Copy link
Copy Markdown
Collaborator

BaseOS Kernel Review

Warning

⚠️ Review needs attention

EGM teardown can leave a freed PFN interval node reachable by memory_failure, while unsynchronized shared lists permit UAF/list corruption. mmap also exposes physical pages beyond the firmware-defined EGM region.

Findings: Critical 3 · High 16 · Medium 16 · Low 26

🔍 Review artifacts

📦 Kernel deb builds — 🟢 2/2 passed

Note

Build reports and debs are retained for 10 days after the PR closes.

Review metadata
  • Reviewed head: c5b8b947ec0e
  • Overall status: attention needed
  • Architectures: 2/2 successful

This comment is maintained by BaseOS Reviewer and updated when the GitHub watcher publishes a newer review.

@clsotog

clsotog commented Sep 2, 2026

Copy link
Copy Markdown
Collaborator

Acked-by: Carol L Soto <[email protected]>

@nirmoy

nirmoy commented Sep 2, 2026

Copy link
Copy Markdown
Collaborator

18 of the 19 patches are clean cherry-picks from 26.04_linux-nvidia.
Nice.

Acked-by: Nirmoy Das <[email protected]> with full e2e testing.

@nirmoy nirmoy added has_2_acks and removed help wanted Extra attention is needed has_1_ack labels Sep 2, 2026
@nvmochs

nvmochs commented Sep 2, 2026

Copy link
Copy Markdown
Collaborator

I confirmed all the patches have the correct provenance. I also confirmed that CONFIG_NVGRACE_EGM is already present in the full*.config files which we typically use to construct a kconfig for this kernel.

Reviewing with codex yielded some existing corner case issues, but I don't think it is worth fixing those as this series will eventually be replaced with a different implementation that is being pursued by Ankit upstream.

I am providing my ack for the series based on review, but would like for Kelsey to complete testing on GH / GB before it is merged.
Acked-by: Matthew R. Ochs <[email protected]>

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

has_2_acks

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@kelsey-steele @nirmoy @clsotog @nvmochs @ankita-nv @kobak2026