[v1,2/3] vfio/nvgrace-gpu: Expose the blackwell device PF BAR1 to the VM

Commit Message

Ankit Agrawal Oct. 6, 2024, 10:27 a.m. UTC

From: Ankit Agrawal <[e-mail]>

There is a HW defect on Grace Hopper (GH) to support the
Multi-Instance GPU (MIG) feature [1] that necessiated the presence
of a 1G region carved out from the device memory and mapped as
uncached. The 1G region is shown as a fake BAR (comprising region 2 and 3)
to workaround the issue.

The Grace Blackwell systems (GB) differ from GH systems in the following
aspects:
1. The aforementioned HW defect is fixed on GB systems.
2. There is a usable BAR1 (region 2 and 3) on GB systems for the
GPUdirect RDMA feature [2].

This patch accommodate those GB changes by showing the 64b physical
device BAR1 (region2 and 3) to the VM instead of the fake one. This
takes care of both the differences.

Moreover, the entire device memory is exposed on GB as cacheable to
the VM as there is no carveout required.

Link: https://www.nvidia.com/en-in/technologies/multi-instance-gpu/ [1]
Link: https://docs.nvidia.com/cuda/gpudirect-rdma/ [2]

Signed-off-by: Ankit Agrawal <[e-mail]>
---
 drivers/vfio/pci/nvgrace-gpu/main.c | 32 +++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

Patch

diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index c23db6eaf979..e3a7eceb6228 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -72,7 +72,7 @@  nvgrace_gpu_memregion(int index,
 	if (index == USEMEM_REGION_INDEX)
 		return &nvdev->usemem;
 
-	if (index == RESMEM_REGION_INDEX)
+	if (!nvdev->has_mig_hw_bug_fix && index == RESMEM_REGION_INDEX)
 		return &nvdev->resmem;
 
 	return NULL;
@@ -715,6 +715,16 @@  static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = {
 	.detach_ioas	= vfio_iommufd_physical_detach_ioas,
 };
 
+static void
+nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
+			      struct nvgrace_gpu_pci_core_device *nvdev,
+			      u64 memphys, u64 memlength)
+{
+	nvdev->usemem.memphys = memphys;
+	nvdev->usemem.memlength = memlength;
+	nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength);
+}
+
 static int
 nvgrace_gpu_fetch_memory_property(struct pci_dev *pdev,
 				  u64 *pmemphys, u64 *pmemlength)
@@ -752,9 +762,9 @@  nvgrace_gpu_fetch_memory_property(struct pci_dev *pdev,
 }
 
 static int
-nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
-			      struct nvgrace_gpu_pci_core_device *nvdev,
-			      u64 memphys, u64 memlength)
+nvgrace_gpu_nvdev_struct_workaround(struct pci_dev *pdev,
+				    struct nvgrace_gpu_pci_core_device *nvdev,
+				    u64 memphys, u64 memlength)
 {
 	int ret = 0;
 
@@ -864,10 +874,16 @@  static int nvgrace_gpu_probe(struct pci_dev *pdev,
 		 * Device memory properties are identified in the host ACPI
 		 * table. Set the nvgrace_gpu_pci_core_device structure.
 		 */
-		ret = nvgrace_gpu_init_nvdev_struct(pdev, nvdev,
-						    memphys, memlength);
-		if (ret)
-			goto out_put_vdev;
+		if (nvdev->has_mig_hw_bug_fix) {
+			nvgrace_gpu_init_nvdev_struct(pdev, nvdev,
+						      memphys, memlength);
+		} else {
+			ret = nvgrace_gpu_nvdev_struct_workaround(pdev, nvdev,
+								  memphys,
+								  memlength);
+			if (ret)
+				goto out_put_vdev;
+		}
 	}
 
 	ret = vfio_pci_core_register_device(&nvdev->core_device);