On Mon, 23 Feb 2026 15:55:03 +0000
<ankita@nvidia.com> wrote:
> From: Ankit Agrawal <ankita@nvidia.com>
>
> The nvgrace-gpu module tracks the various EGM regions on the system.
> The EGM region information - Base SPA and size - are part of the ACPI
> tables. This can be fetched from the DSD table using the GPU handle.
>
> When the GPUs are bound to the nvgrace-gpu module, it fetches the EGM
> region information from the ACPI table using the GPU's pci_dev. The
> EGM regions are tracked in a list and the information per region is
> maintained in the nvgrace_egm_dev.
>
> Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
> ---
> drivers/vfio/pci/nvgrace-gpu/egm_dev.c | 24 +++++++++++++++++++++++-
> drivers/vfio/pci/nvgrace-gpu/egm_dev.h | 4 +++-
> drivers/vfio/pci/nvgrace-gpu/main.c | 8 ++++++--
> include/linux/nvgrace-egm.h | 2 ++
> 4 files changed, 34 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/vfio/pci/nvgrace-gpu/egm_dev.c b/drivers/vfio/pci/nvgrace-gpu/egm_dev.c
> index 0bf95688a486..20291504aca8 100644
> --- a/drivers/vfio/pci/nvgrace-gpu/egm_dev.c
> +++ b/drivers/vfio/pci/nvgrace-gpu/egm_dev.c
> @@ -17,6 +17,26 @@ int nvgrace_gpu_has_egm_property(struct pci_dev *pdev, u64 *pegmpxm)
> pegmpxm);
> }
>
> +int nvgrace_gpu_fetch_egm_property(struct pci_dev *pdev, u64 *pegmphys,
> + u64 *pegmlength)
> +{
> + int ret;
> +
> + /*
> + * The memory information is present in the system ACPI tables as DSD
> + * properties nvidia,egm-base-pa and nvidia,egm-size.
> + */
> + ret = device_property_read_u64(&pdev->dev, "nvidia,egm-size",
> + pegmlength);
> + if (ret)
> + return ret;
> +
> + ret = device_property_read_u64(&pdev->dev, "nvidia,egm-base-pa",
> + pegmphys);
> +
> + return ret;
> +}
What guarantees that all GPUs in the same PXM have the same properties?
AIUI we only consume the resulting properties for the first GPU
associated to the egm_dev. Why do we even bother to retrieve the
properties for subsequent GPUs?
Nit, it's a bit inconsistent to partially write caller data on error
versus read to local variables and set the caller data only on success.
Thanks,
Alex
> +
> int add_gpu(struct nvgrace_egm_dev *egm_dev, struct pci_dev *pdev)
> {
> struct gpu_node *node;
> @@ -54,7 +74,7 @@ static void nvgrace_gpu_release_aux_device(struct device *device)
>
> struct nvgrace_egm_dev *
> nvgrace_gpu_create_aux_device(struct pci_dev *pdev, const char *name,
> - u64 egmpxm)
> + u64 egmphys, u64 egmlength, u64 egmpxm)
> {
> struct nvgrace_egm_dev *egm_dev;
> int ret;
> @@ -64,6 +84,8 @@ nvgrace_gpu_create_aux_device(struct pci_dev *pdev, const char *name,
> goto create_err;
>
> egm_dev->egmpxm = egmpxm;
> + egm_dev->egmphys = egmphys;
> + egm_dev->egmlength = egmlength;
> INIT_LIST_HEAD(&egm_dev->gpus);
>
> egm_dev->aux_dev.id = egmpxm;
> diff --git a/drivers/vfio/pci/nvgrace-gpu/egm_dev.h b/drivers/vfio/pci/nvgrace-gpu/egm_dev.h
> index 1635753c9e50..2e1612445898 100644
> --- a/drivers/vfio/pci/nvgrace-gpu/egm_dev.h
> +++ b/drivers/vfio/pci/nvgrace-gpu/egm_dev.h
> @@ -16,6 +16,8 @@ void remove_gpu(struct nvgrace_egm_dev *egm_dev, struct pci_dev *pdev);
>
> struct nvgrace_egm_dev *
> nvgrace_gpu_create_aux_device(struct pci_dev *pdev, const char *name,
> - u64 egmphys);
> + u64 egmphys, u64 egmlength, u64 egmpxm);
>
> +int nvgrace_gpu_fetch_egm_property(struct pci_dev *pdev, u64 *pegmphys,
> + u64 *pegmlength);
> #endif /* EGM_DEV_H */
> diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
> index 3dd0c57e5789..b356e941340a 100644
> --- a/drivers/vfio/pci/nvgrace-gpu/main.c
> +++ b/drivers/vfio/pci/nvgrace-gpu/main.c
> @@ -78,7 +78,7 @@ static struct list_head egm_dev_list;
> static int nvgrace_gpu_create_egm_aux_device(struct pci_dev *pdev)
> {
> struct nvgrace_egm_dev_entry *egm_entry = NULL;
> - u64 egmpxm;
> + u64 egmphys, egmlength, egmpxm;
> int ret = 0;
> bool is_new_region = false;
>
> @@ -91,6 +91,10 @@ static int nvgrace_gpu_create_egm_aux_device(struct pci_dev *pdev)
> if (nvgrace_gpu_has_egm_property(pdev, &egmpxm))
> goto exit;
>
> + ret = nvgrace_gpu_fetch_egm_property(pdev, &egmphys, &egmlength);
> + if (ret)
> + goto exit;
> +
> list_for_each_entry(egm_entry, &egm_dev_list, list) {
> /*
> * A system could have multiple GPUs associated with an
> @@ -110,7 +114,7 @@ static int nvgrace_gpu_create_egm_aux_device(struct pci_dev *pdev)
>
> egm_entry->egm_dev =
> nvgrace_gpu_create_aux_device(pdev, NVGRACE_EGM_DEV_NAME,
> - egmpxm);
> + egmphys, egmlength, egmpxm);
> if (!egm_entry->egm_dev) {
> ret = -EINVAL;
> goto free_egm_entry;
> diff --git a/include/linux/nvgrace-egm.h b/include/linux/nvgrace-egm.h
> index e42494a2b1a6..a66906753267 100644
> --- a/include/linux/nvgrace-egm.h
> +++ b/include/linux/nvgrace-egm.h
> @@ -17,6 +17,8 @@ struct gpu_node {
>
> struct nvgrace_egm_dev {
> struct auxiliary_device aux_dev;
> + phys_addr_t egmphys;
> + size_t egmlength;
> u64 egmpxm;
> struct list_head gpus;
> };