From: Jason Gunthorpe jgg@nvidia.com
Call vfio_pci_core_fill_phys_vec() with the proper physical ranges for the synthetic BAR 2 and BAR 4 regions. Otherwise use the normal flow based on the PCI bar.
This demonstrates a DMABUF that follows the region info report to only allow mapping parts of the region that are mmapable. Since the BAR is power of two sized and the "CXL" region is just page aligned the there can be a padding region at the end that is not mmaped or passed into the DMABUF.
The "CXL" ranges that are remapped into BAR 2 and BAR 4 areas are not PCI MMIO, they actually run over the CXL-like coherent interconnect and for the purposes of DMA behave identically to DRAM. We don't try to model this distinction between true PCI BAR memory that takes a real PCI path and the "CXL" memory that takes a different path in the p2p framework for now.
Signed-off-by: Jason Gunthorpe jgg@nvidia.com Tested-by: Alex Mastro amastro@fb.com Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Leon Romanovsky leonro@nvidia.com --- drivers/vfio/pci/nvgrace-gpu/main.c | 56 +++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+)
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index e346392b72f6..1a15c928f067 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -7,6 +7,7 @@ #include <linux/vfio_pci_core.h> #include <linux/delay.h> #include <linux/jiffies.h> +#include <linux/pci-p2pdma.h>
/* * The device memory usable to the workloads running in the VM is cached @@ -683,6 +684,54 @@ nvgrace_gpu_write(struct vfio_device *core_vdev, return vfio_pci_core_write(core_vdev, buf, count, ppos); }
+static int nvgrace_get_dmabuf_phys(struct vfio_pci_core_device *core_vdev, + struct p2pdma_provider **provider, + unsigned int region_index, + struct dma_buf_phys_vec *phys_vec, + struct vfio_region_dma_range *dma_ranges, + size_t nr_ranges) +{ + struct nvgrace_gpu_pci_core_device *nvdev = container_of( + core_vdev, struct nvgrace_gpu_pci_core_device, core_device); + struct pci_dev *pdev = core_vdev->pdev; + struct mem_region *mem_region = NULL; + + if (nvdev->resmem.memlength && region_index == RESMEM_REGION_INDEX) { + /* + * The P2P properties of the non-BAR memory is the same as the + * BAR memory, so just use the provider for index 0. Someday + * when CXL gets P2P support we could create CXLish providers + * for the non-BAR memory. + */ + mem_region = &nvdev->resmem; + } else if (region_index == USEMEM_REGION_INDEX) { + /* + * This is actually cachable memory and isn't treated as P2P in + * the chip. For now we have no way to push cachable memory + * through everything and the Grace HW doesn't care what caching + * attribute is programmed into the SMMU. So use BAR 0. + */ + mem_region = &nvdev->usemem; + } + + if (mem_region) { + *provider = pcim_p2pdma_provider(pdev, 0); + if (!*provider) + return -EINVAL; + return vfio_pci_core_fill_phys_vec(phys_vec, dma_ranges, + nr_ranges, + mem_region->memphys, + mem_region->memlength); + } + + return vfio_pci_core_get_dmabuf_phys(core_vdev, provider, region_index, + phys_vec, dma_ranges, nr_ranges); +} + +static const struct vfio_pci_device_ops nvgrace_gpu_pci_dev_ops = { + .get_dmabuf_phys = nvgrace_get_dmabuf_phys, +}; + static const struct vfio_device_ops nvgrace_gpu_pci_ops = { .name = "nvgrace-gpu-vfio-pci", .init = vfio_pci_core_init_dev, @@ -703,6 +752,10 @@ static const struct vfio_device_ops nvgrace_gpu_pci_ops = { .detach_ioas = vfio_iommufd_physical_detach_ioas, };
+static const struct vfio_pci_device_ops nvgrace_gpu_pci_dev_core_ops = { + .get_dmabuf_phys = vfio_pci_core_get_dmabuf_phys, +}; + static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = { .name = "nvgrace-gpu-vfio-pci-core", .init = vfio_pci_core_init_dev, @@ -965,6 +1018,9 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, memphys, memlength); if (ret) goto out_put_vdev; + nvdev->core_device.pci_ops = &nvgrace_gpu_pci_dev_ops; + } else { + nvdev->core_device.pci_ops = &nvgrace_gpu_pci_dev_core_ops; }
ret = vfio_pci_core_register_device(&nvdev->core_device);