diff options
Diffstat (limited to 'drivers/vfio/pci/nvgrace-gpu/main.c')
| -rw-r--r-- | drivers/vfio/pci/nvgrace-gpu/main.c | 493 |
1 files changed, 396 insertions, 97 deletions
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index a7fd018aa548..84d142a47ec6 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -5,6 +5,10 @@ #include <linux/sizes.h> #include <linux/vfio_pci_core.h> +#include <linux/delay.h> +#include <linux/jiffies.h> +#include <linux/pci-p2pdma.h> +#include <linux/pm_runtime.h> /* * The device memory usable to the workloads running in the VM is cached @@ -17,12 +21,21 @@ #define RESMEM_REGION_INDEX VFIO_PCI_BAR2_REGION_INDEX #define USEMEM_REGION_INDEX VFIO_PCI_BAR4_REGION_INDEX -/* Memory size expected as non cached and reserved by the VM driver */ -#define RESMEM_SIZE SZ_1G - /* A hardwired and constant ABI value between the GPU FW and VFIO driver. */ #define MEMBLK_SIZE SZ_512M +#define DVSEC_BITMAP_OFFSET 0xA +#define MIG_SUPPORTED_WITH_CACHED_RESMEM BIT(0) + +#define GPU_CAP_DVSEC_REGISTER 3 + +#define C2C_LINK_BAR0_OFFSET 0x1498 +#define HBM_TRAINING_BAR0_OFFSET 0x200BC +#define STATUS_READY 0xFF + +#define POLL_QUANTUM_MS 1000 +#define POLL_TIMEOUT_MS (30 * 1000) + /* * The state of the two device memory region - resmem and usemem - is * saved as struct mem_region. @@ -46,6 +59,9 @@ struct nvgrace_gpu_pci_core_device { struct mem_region resmem; /* Lock to control device memory kernel mapping */ struct mutex remap_lock; + bool has_mig_hw_bug; + /* GPU has just been reset */ + bool reset_done; }; static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev) @@ -66,7 +82,7 @@ nvgrace_gpu_memregion(int index, if (index == USEMEM_REGION_INDEX) return &nvdev->usemem; - if (index == RESMEM_REGION_INDEX) + if (nvdev->resmem.memlength && index == RESMEM_REGION_INDEX) return &nvdev->resmem; return NULL; @@ -90,6 +106,19 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev) mutex_init(&nvdev->remap_lock); } + /* + * GPU readiness is checked by reading the BAR0 registers. + * + * ioremap BAR0 to ensure that the BAR0 mapping is present before + * register reads on first fault before establishing any GPU + * memory mapping. + */ + ret = vfio_pci_core_setup_barmap(vdev, 0); + if (ret) { + vfio_pci_core_disable(vdev); + return ret; + } + vfio_pci_core_finish_enable(vdev); return 0; @@ -118,6 +147,106 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev) vfio_pci_core_close_device(core_vdev); } +static int nvgrace_gpu_wait_device_ready(void __iomem *io) +{ + unsigned long timeout = jiffies + msecs_to_jiffies(POLL_TIMEOUT_MS); + + do { + if ((ioread32(io + C2C_LINK_BAR0_OFFSET) == STATUS_READY) && + (ioread32(io + HBM_TRAINING_BAR0_OFFSET) == STATUS_READY)) + return 0; + msleep(POLL_QUANTUM_MS); + } while (!time_after(jiffies, timeout)); + + return -ETIME; +} + +/* + * If the GPU memory is accessed by the CPU while the GPU is not ready + * after reset, it can cause harmless corrected RAS events to be logged. + * Make sure the GPU is ready before establishing the mappings. + */ +static int +nvgrace_gpu_check_device_ready(struct nvgrace_gpu_pci_core_device *nvdev) +{ + struct vfio_pci_core_device *vdev = &nvdev->core_device; + int ret; + + lockdep_assert_held_read(&vdev->memory_lock); + + if (!nvdev->reset_done) + return 0; + + if (!__vfio_pci_memory_enabled(vdev)) + return -EIO; + + ret = nvgrace_gpu_wait_device_ready(vdev->barmap[0]); + if (ret) + return ret; + + nvdev->reset_done = false; + + return 0; +} + +static unsigned long addr_to_pgoff(struct vm_area_struct *vma, + unsigned long addr) +{ + u64 pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + + return ((addr - vma->vm_start) >> PAGE_SHIFT) + pgoff; +} + +static vm_fault_t nvgrace_gpu_vfio_pci_huge_fault(struct vm_fault *vmf, + unsigned int order) +{ + struct vm_area_struct *vma = vmf->vma; + struct nvgrace_gpu_pci_core_device *nvdev = vma->vm_private_data; + struct vfio_pci_core_device *vdev = &nvdev->core_device; + unsigned int index = + vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); + vm_fault_t ret = VM_FAULT_FALLBACK; + struct mem_region *memregion; + unsigned long pfn, addr; + + memregion = nvgrace_gpu_memregion(index, nvdev); + if (!memregion) + return VM_FAULT_SIGBUS; + + addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); + pfn = PHYS_PFN(memregion->memphys) + addr_to_pgoff(vma, addr); + + if (is_aligned_for_order(vma, addr, pfn, order)) { + scoped_guard(rwsem_read, &vdev->memory_lock) { + if (vdev->pm_runtime_engaged || + nvgrace_gpu_check_device_ready(nvdev)) + return VM_FAULT_SIGBUS; + + ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); + } + } + + dev_dbg_ratelimited(&vdev->pdev->dev, + "%s order = %d pfn 0x%lx: 0x%x\n", + __func__, order, pfn, + (unsigned int)ret); + + return ret; +} + +static vm_fault_t nvgrace_gpu_vfio_pci_fault(struct vm_fault *vmf) +{ + return nvgrace_gpu_vfio_pci_huge_fault(vmf, 0); +} + +static const struct vm_operations_struct nvgrace_gpu_vfio_pci_mmap_ops = { + .fault = nvgrace_gpu_vfio_pci_fault, +#ifdef CONFIG_ARCH_SUPPORTS_HUGE_PFNMAP + .huge_fault = nvgrace_gpu_vfio_pci_huge_fault, +#endif +}; + static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma) { @@ -125,10 +254,8 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, container_of(core_vdev, struct nvgrace_gpu_pci_core_device, core_device.vdev); struct mem_region *memregion; - unsigned long start_pfn; u64 req_len, pgoff, end; unsigned int index; - int ret = 0; index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); @@ -145,17 +272,18 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); if (check_sub_overflow(vma->vm_end, vma->vm_start, &req_len) || - check_add_overflow(PHYS_PFN(memregion->memphys), pgoff, &start_pfn) || check_add_overflow(PFN_PHYS(pgoff), req_len, &end)) return -EOVERFLOW; /* - * Check that the mapping request does not go beyond available device - * memory size + * Check that the mapping request does not go beyond the exposed + * device memory size. */ if (end > memregion->memlength) return -EINVAL; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); + /* * The carved out region of the device memory needs the NORMAL_NC * property. Communicate as such to the hypervisor. @@ -172,56 +300,31 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); } - /* - * Perform a PFN map to the memory and back the device BAR by the - * GPU memory. - * - * The available GPU memory size may not be power-of-2 aligned. The - * remainder is only backed by vfio_device_ops read/write handlers. - * - * During device reset, the GPU is safely disconnected to the CPU - * and access to the BAR will be immediately returned preventing - * machine check. - */ - ret = remap_pfn_range(vma, vma->vm_start, start_pfn, - req_len, vma->vm_page_prot); - if (ret) - return ret; - - vma->vm_pgoff = start_pfn; + vma->vm_ops = &nvgrace_gpu_vfio_pci_mmap_ops; + vma->vm_private_data = nvdev; return 0; } -static long -nvgrace_gpu_ioctl_get_region_info(struct vfio_device *core_vdev, - unsigned long arg) +static int nvgrace_gpu_ioctl_get_region_info(struct vfio_device *core_vdev, + struct vfio_region_info *info, + struct vfio_info_cap *caps) { struct nvgrace_gpu_pci_core_device *nvdev = container_of(core_vdev, struct nvgrace_gpu_pci_core_device, core_device.vdev); - unsigned long minsz = offsetofend(struct vfio_region_info, offset); - struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; struct vfio_region_info_cap_sparse_mmap *sparse; - struct vfio_region_info info; struct mem_region *memregion; u32 size; int ret; - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; - - if (info.argsz < minsz) - return -EINVAL; - /* * Request to determine the BAR region information. Send the * GPU memory information. */ - memregion = nvgrace_gpu_memregion(info.index, nvdev); + memregion = nvgrace_gpu_memregion(info->index, nvdev); if (!memregion) - return vfio_pci_core_ioctl(core_vdev, - VFIO_DEVICE_GET_REGION_INFO, arg); + return vfio_pci_ioctl_get_region_info(core_vdev, info, caps); size = struct_size(sparse, areas, 1); @@ -240,49 +343,28 @@ nvgrace_gpu_ioctl_get_region_info(struct vfio_device *core_vdev, sparse->header.id = VFIO_REGION_INFO_CAP_SPARSE_MMAP; sparse->header.version = 1; - ret = vfio_info_add_capability(&caps, &sparse->header, size); + ret = vfio_info_add_capability(caps, &sparse->header, size); kfree(sparse); if (ret) return ret; - info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info->offset = VFIO_PCI_INDEX_TO_OFFSET(info->index); /* * The region memory size may not be power-of-2 aligned. - * Given that the memory as a BAR and may not be + * Given that the memory is a BAR and may not be * aligned, roundup to the next power-of-2. */ - info.size = memregion->bar_size; - info.flags = VFIO_REGION_INFO_FLAG_READ | + info->size = memregion->bar_size; + info->flags = VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE | VFIO_REGION_INFO_FLAG_MMAP; - - if (caps.size) { - info.flags |= VFIO_REGION_INFO_FLAG_CAPS; - if (info.argsz < sizeof(info) + caps.size) { - info.argsz = sizeof(info) + caps.size; - info.cap_offset = 0; - } else { - vfio_info_cap_shift(&caps, sizeof(info)); - if (copy_to_user((void __user *)arg + - sizeof(info), caps.buf, - caps.size)) { - kfree(caps.buf); - return -EFAULT; - } - info.cap_offset = sizeof(info); - } - kfree(caps.buf); - } - return copy_to_user((void __user *)arg, &info, minsz) ? - -EFAULT : 0; + return 0; } static long nvgrace_gpu_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg) { switch (cmd) { - case VFIO_DEVICE_GET_REGION_INFO: - return nvgrace_gpu_ioctl_get_region_info(core_vdev, arg); case VFIO_DEVICE_IOEVENTFD: return -ENOTTY; case VFIO_DEVICE_RESET: @@ -498,6 +580,7 @@ static ssize_t nvgrace_gpu_read_mem(struct nvgrace_gpu_pci_core_device *nvdev, char __user *buf, size_t count, loff_t *ppos) { + struct vfio_pci_core_device *vdev = &nvdev->core_device; u64 offset = *ppos & VFIO_PCI_OFFSET_MASK; unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); struct mem_region *memregion; @@ -524,9 +607,15 @@ nvgrace_gpu_read_mem(struct nvgrace_gpu_pci_core_device *nvdev, else mem_count = min(count, memregion->memlength - (size_t)offset); - ret = nvgrace_gpu_map_and_read(nvdev, buf, mem_count, ppos); - if (ret) - return ret; + scoped_guard(rwsem_read, &vdev->memory_lock) { + ret = nvgrace_gpu_check_device_ready(nvdev); + if (ret) + return ret; + + ret = nvgrace_gpu_map_and_read(nvdev, buf, mem_count, ppos); + if (ret) + return ret; + } /* * Only the device memory present on the hardware is mapped, which may @@ -551,9 +640,16 @@ nvgrace_gpu_read(struct vfio_device *core_vdev, struct nvgrace_gpu_pci_core_device *nvdev = container_of(core_vdev, struct nvgrace_gpu_pci_core_device, core_device.vdev); + struct vfio_pci_core_device *vdev = &nvdev->core_device; + int ret; - if (nvgrace_gpu_memregion(index, nvdev)) - return nvgrace_gpu_read_mem(nvdev, buf, count, ppos); + if (nvgrace_gpu_memregion(index, nvdev)) { + if (pm_runtime_resume_and_get(&vdev->pdev->dev)) + return -EIO; + ret = nvgrace_gpu_read_mem(nvdev, buf, count, ppos); + pm_runtime_put(&vdev->pdev->dev); + return ret; + } if (index == VFIO_PCI_CONFIG_REGION_INDEX) return nvgrace_gpu_read_config_emu(core_vdev, buf, count, ppos); @@ -615,6 +711,7 @@ static ssize_t nvgrace_gpu_write_mem(struct nvgrace_gpu_pci_core_device *nvdev, size_t count, loff_t *ppos, const char __user *buf) { + struct vfio_pci_core_device *vdev = &nvdev->core_device; unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); u64 offset = *ppos & VFIO_PCI_OFFSET_MASK; struct mem_region *memregion; @@ -644,9 +741,15 @@ nvgrace_gpu_write_mem(struct nvgrace_gpu_pci_core_device *nvdev, */ mem_count = min(count, memregion->memlength - (size_t)offset); - ret = nvgrace_gpu_map_and_write(nvdev, buf, mem_count, ppos); - if (ret) - return ret; + scoped_guard(rwsem_read, &vdev->memory_lock) { + ret = nvgrace_gpu_check_device_ready(nvdev); + if (ret) + return ret; + + ret = nvgrace_gpu_map_and_write(nvdev, buf, mem_count, ppos); + if (ret) + return ret; + } exitfn: *ppos += count; @@ -660,10 +763,17 @@ nvgrace_gpu_write(struct vfio_device *core_vdev, struct nvgrace_gpu_pci_core_device *nvdev = container_of(core_vdev, struct nvgrace_gpu_pci_core_device, core_device.vdev); + struct vfio_pci_core_device *vdev = &nvdev->core_device; unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + int ret; - if (nvgrace_gpu_memregion(index, nvdev)) - return nvgrace_gpu_write_mem(nvdev, count, ppos, buf); + if (nvgrace_gpu_memregion(index, nvdev)) { + if (pm_runtime_resume_and_get(&vdev->pdev->dev)) + return -EIO; + ret = nvgrace_gpu_write_mem(nvdev, count, ppos, buf); + pm_runtime_put(&vdev->pdev->dev); + return ret; + } if (index == VFIO_PCI_CONFIG_REGION_INDEX) return nvgrace_gpu_write_config_emu(core_vdev, buf, count, ppos); @@ -671,6 +781,50 @@ 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; + + /* + * 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. + * } 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 = nvgrace_gpu_memregion(region_index, nvdev); + 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, @@ -678,18 +832,24 @@ static const struct vfio_device_ops nvgrace_gpu_pci_ops = { .open_device = nvgrace_gpu_open_device, .close_device = nvgrace_gpu_close_device, .ioctl = nvgrace_gpu_ioctl, + .get_region_info_caps = nvgrace_gpu_ioctl_get_region_info, .device_feature = vfio_pci_core_ioctl_feature, .read = nvgrace_gpu_read, .write = nvgrace_gpu_write, .mmap = nvgrace_gpu_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, .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, @@ -697,12 +857,14 @@ static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = { .open_device = nvgrace_gpu_open_device, .close_device = vfio_pci_core_close_device, .ioctl = vfio_pci_core_ioctl, + .get_region_info_caps = vfio_pci_ioctl_get_region_info, .device_feature = vfio_pci_core_ioctl_feature, .read = vfio_pci_core_read, .write = vfio_pci_core_write, .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, @@ -751,40 +913,67 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev, u64 memphys, u64 memlength) { int ret = 0; + u64 resmem_size = 0; /* - * The VM GPU device driver needs a non-cacheable region to support - * the MIG feature. Since the device memory is mapped as NORMAL cached, - * carve out a region from the end with a different NORMAL_NC - * property (called as reserved memory and represented as resmem). This - * region then is exposed as a 64b BAR (region 2 and 3) to the VM, while - * exposing the rest (termed as usable memory and represented using usemem) - * as cacheable 64b BAR (region 4 and 5). + * On Grace Hopper systems, the VM GPU device driver needs a non-cacheable + * region to support the MIG feature owing to a hardware bug. Since the + * device memory is mapped as NORMAL cached, carve out a region from the end + * with a different NORMAL_NC property (called as reserved memory and + * represented as resmem). This region then is exposed as a 64b BAR + * (region 2 and 3) to the VM, while exposing the rest (termed as usable + * memory and represented using usemem) as cacheable 64b BAR (region 4 and 5). * * devmem (memlength) * |-------------------------------------------------| * | | * usemem.memphys resmem.memphys + * + * This hardware bug is fixed on the Grace Blackwell platforms and the + * presence of the bug can be determined through nvdev->has_mig_hw_bug. + * Thus on systems with the hardware fix, there is no need to partition + * the GPU device memory and the entire memory is usable and mapped as + * NORMAL cached (i.e. resmem size is 0). */ + if (nvdev->has_mig_hw_bug) + resmem_size = SZ_1G; + nvdev->usemem.memphys = memphys; /* * The device memory exposed to the VM is added to the kernel by the - * VM driver module in chunks of memory block size. Only the usable - * memory (usemem) is added to the kernel for usage by the VM - * workloads. Make the usable memory size memblock aligned. + * VM driver module in chunks of memory block size. Note that only the + * usable memory (usemem) is added to the kernel for usage by the VM + * workloads. */ - if (check_sub_overflow(memlength, RESMEM_SIZE, + if (check_sub_overflow(memlength, resmem_size, &nvdev->usemem.memlength)) { ret = -EOVERFLOW; goto done; } /* - * The USEMEM part of the device memory has to be MEMBLK_SIZE - * aligned. This is a hardwired ABI value between the GPU FW and - * VFIO driver. The VM device driver is also aware of it and make - * use of the value for its calculation to determine USEMEM size. + * The usemem region is exposed as a 64B Bar composed of region 4 and 5. + * Calculate and save the BAR size for the region. + */ + nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength); + + /* + * If the hardware has the fix for MIG, there is no requirement + * for splitting the device memory to create RESMEM. The entire + * device memory is usable and will be USEMEM. Return here for + * such case. + */ + if (!nvdev->has_mig_hw_bug) + goto done; + + /* + * When the device memory is split to workaround the MIG bug on + * Grace Hopper, the USEMEM part of the device memory has to be + * MEMBLK_SIZE aligned. This is a hardwired ABI value between the + * GPU FW and VFIO driver. The VM device driver is also aware of it + * and make use of the value for its calculation to determine USEMEM + * size. Note that the device memory may not be 512M aligned. */ nvdev->usemem.memlength = round_down(nvdev->usemem.memlength, MEMBLK_SIZE); @@ -803,15 +992,84 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev, } /* - * The memory regions are exposed as BARs. Calculate and save - * the BAR size for them. + * The resmem region is exposed as a 64b BAR composed of region 2 and 3 + * for Grace Hopper. Calculate and save the BAR size for the region. */ - nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength); nvdev->resmem.bar_size = roundup_pow_of_two(nvdev->resmem.memlength); done: return ret; } +static bool nvgrace_gpu_has_mig_hw_bug(struct pci_dev *pdev) +{ + int pcie_dvsec; + u16 dvsec_ctrl16; + + pcie_dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_NVIDIA, + GPU_CAP_DVSEC_REGISTER); + + if (pcie_dvsec) { + pci_read_config_word(pdev, + pcie_dvsec + DVSEC_BITMAP_OFFSET, + &dvsec_ctrl16); + + if (dvsec_ctrl16 & MIG_SUPPORTED_WITH_CACHED_RESMEM) + return false; + } + + return true; +} + +/* + * To reduce the system bootup time, the HBM training has + * been moved out of the UEFI on the Grace-Blackwell systems. + * + * The onus of checking whether the HBM training has completed + * thus falls on the module. The HBM training status can be + * determined from a BAR0 register. + * + * Similarly, another BAR0 register exposes the status of the + * CPU-GPU chip-to-chip (C2C) cache coherent interconnect. + * + * Poll these register and check for 30s. If the HBM training is + * not complete or if the C2C link is not ready, fail the probe. + * + * While the wait is not required on Grace Hopper systems, it + * is beneficial to make the check to ensure the device is in an + * expected state. + * + * Ensure that the BAR0 region is enabled before accessing the + * registers. + */ +static int nvgrace_gpu_probe_check_device_ready(struct pci_dev *pdev) +{ + void __iomem *io; + int ret; + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + ret = pci_request_selected_regions(pdev, 1 << 0, KBUILD_MODNAME); + if (ret) + goto request_region_exit; + + io = pci_iomap(pdev, 0, 0); + if (!io) { + ret = -ENOMEM; + goto iomap_exit; + } + + ret = nvgrace_gpu_wait_device_ready(io); + + pci_iounmap(pdev, io); +iomap_exit: + pci_release_selected_regions(pdev, 1 << 0); +request_region_exit: + pci_disable_device(pdev); + return ret; +} + static int nvgrace_gpu_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -820,6 +1078,10 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, u64 memphys, memlength; int ret; + ret = nvgrace_gpu_probe_check_device_ready(pdev); + if (ret) + return ret; + ret = nvgrace_gpu_fetch_memory_property(pdev, &memphys, &memlength); if (!ret) ops = &nvgrace_gpu_pci_ops; @@ -832,6 +1094,8 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, dev_set_drvdata(&pdev->dev, &nvdev->core_device); if (ops == &nvgrace_gpu_pci_ops) { + nvdev->has_mig_hw_bug = nvgrace_gpu_has_mig_hw_bug(pdev); + /* * Device memory properties are identified in the host ACPI * table. Set the nvgrace_gpu_pci_core_device structure. @@ -840,6 +1104,9 @@ 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); @@ -866,17 +1133,49 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = { { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2342) }, /* GH200 480GB */ { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2345) }, + /* GH200 SKU */ + { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2348) }, + /* GB200 SKU */ + { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2941) }, + /* GB300 SKU */ + { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x31C2) }, {} }; MODULE_DEVICE_TABLE(pci, nvgrace_gpu_vfio_pci_table); +/* + * The GPU reset is required to be serialized against the *first* mapping + * faults and read/writes accesses to prevent potential RAS events logging. + * + * First fault or access after a reset needs to poll device readiness, + * flag that a reset has occurred. The readiness test is done by holding + * the memory_lock read lock and we expect all vfio-pci initiated resets to + * hold the memory_lock write lock to avoid races. However, .reset_done + * extends beyond the scope of vfio-pci initiated resets therefore we + * cannot assert this behavior and use lockdep_assert_held_write. + */ +static void nvgrace_gpu_vfio_pci_reset_done(struct pci_dev *pdev) +{ + struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev); + struct nvgrace_gpu_pci_core_device *nvdev = + container_of(core_device, struct nvgrace_gpu_pci_core_device, + core_device); + + nvdev->reset_done = true; +} + +static const struct pci_error_handlers nvgrace_gpu_vfio_pci_err_handlers = { + .reset_done = nvgrace_gpu_vfio_pci_reset_done, + .error_detected = vfio_pci_core_aer_err_detected, +}; + static struct pci_driver nvgrace_gpu_vfio_pci_driver = { .name = KBUILD_MODNAME, .id_table = nvgrace_gpu_vfio_pci_table, .probe = nvgrace_gpu_probe, .remove = nvgrace_gpu_remove, - .err_handler = &vfio_pci_core_err_handlers, + .err_handler = &nvgrace_gpu_vfio_pci_err_handlers, .driver_managed_dma = true, }; |