From: Ankit Agrawal Refactor vfio_pci_mmap_huge_fault to take out the implementation to map the VMA to the PTE/PMD/PUD as a separate function. Export the new function to be used by nvgrace-gpu module. No functional change is intended. Cc: Shameer Kolothum Cc: Alex Williamson Cc: Jason Gunthorpe Reviewed-by: Shameer Kolothum Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/vfio_pci_core.c | 54 +++++++++++++++++--------------- include/linux/vfio_pci_core.h | 16 ++++++++++ 2 files changed, 45 insertions(+), 25 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 7dcf5439dedc..52e3a10d776b 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1640,48 +1640,52 @@ static unsigned long vma_to_pfn(struct vm_area_struct *vma) return (pci_resource_start(vdev->pdev, index) >> PAGE_SHIFT) + pgoff; } -static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, - unsigned int order) +vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev, + struct vm_fault *vmf, + unsigned long pfn, + unsigned int order) { - struct vm_area_struct *vma = vmf->vma; - struct vfio_pci_core_device *vdev = vma->vm_private_data; - unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1); - unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; - unsigned long pfn = vma_to_pfn(vma) + pgoff; - vm_fault_t ret = VM_FAULT_SIGBUS; - - if (order && (addr < vma->vm_start || - addr + (PAGE_SIZE << order) > vma->vm_end || - pfn & ((1 << order) - 1))) { - ret = VM_FAULT_FALLBACK; - goto out; - } - - down_read(&vdev->memory_lock); + lockdep_assert_held_read(&vdev->memory_lock); if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) - goto out_unlock; + return VM_FAULT_SIGBUS; switch (order) { case 0: - ret = vmf_insert_pfn(vma, vmf->address, pfn); - break; + return vmf_insert_pfn(vmf->vma, vmf->address, pfn); #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP case PMD_ORDER: - ret = vmf_insert_pfn_pmd(vmf, pfn, false); - break; + return vmf_insert_pfn_pmd(vmf, pfn, false); #endif #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP case PUD_ORDER: - ret = vmf_insert_pfn_pud(vmf, pfn, false); + return vmf_insert_pfn_pud(vmf, pfn, false); break; #endif default: + return VM_FAULT_FALLBACK; + } +} +EXPORT_SYMBOL_GPL(vfio_pci_vmf_insert_pfn); + +static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, + unsigned int order) +{ + struct vm_area_struct *vma = vmf->vma; + struct vfio_pci_core_device *vdev = vma->vm_private_data; + unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1); + unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; + unsigned long pfn = vma_to_pfn(vma) + pgoff; + vm_fault_t ret; + + if (unmappable_for_order(vma, addr, pfn, order)) { ret = VM_FAULT_FALLBACK; + goto out; } -out_unlock: - up_read(&vdev->memory_lock); + scoped_guard(rwsem_read, &vdev->memory_lock) + ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); + out: dev_dbg_ratelimited(&vdev->pdev->dev, "%s(,order = %d) BAR %ld page offset 0x%lx: 0x%x\n", diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index f541044e42a2..1d457216ce4d 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -119,6 +119,9 @@ ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, size_t count, loff_t *ppos); +vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev, + struct vm_fault *vmf, unsigned long pfn, + unsigned int order); int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma); void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count); int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); @@ -161,4 +164,17 @@ VFIO_IOREAD_DECLARATION(32) VFIO_IOREAD_DECLARATION(64) #endif +static inline bool unmappable_for_order(struct vm_area_struct *vma, + unsigned long addr, + unsigned long pfn, + unsigned int order) +{ + if (order && (addr < vma->vm_start || + addr + (PAGE_SIZE << order) > vma->vm_end || + !IS_ALIGNED(pfn, 1 << order))) + return true; + + return false; +} + #endif /* VFIO_PCI_CORE_H */ -- 2.34.1 From: Ankit Agrawal NVIDIA's Grace based systems have large device memory. The device memory is mapped as VM_PFNMAP in the VMM VMA. The nvgrace-gpu module could make use of the huge PFNMAP support added in mm [1]. To make use of the huge pfnmap support, fault/huge_fault ops based mapping mechanism needs to be implemented. Currently nvgrace-gpu module relies on remap_pfn_range to do the mapping during VM bootup. Replace it to instead rely on fault and use vfio_pci_vmf_insert_pfn to setup the mapping. Moreover to enable huge pfnmap, nvgrace-gpu module is updated by adding huge_fault ops implementation. The implementation establishes mapping according to the order request. Note that if the PFN or the VMA address is unaligned to the order, the mapping fallbacks to the PTE level. Link: https://lore.kernel.org/all/20240826204353.2228736-1-peterx@redhat.com/ [1] Cc: Shameer Kolothum Cc: Alex Williamson Cc: Jason Gunthorpe Cc: Vikram Sethi Reviewed-by: Zhi Wang Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/nvgrace-gpu/main.c | 85 +++++++++++++++++++++-------- 1 file changed, 63 insertions(+), 22 deletions(-) diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index e346392b72f6..ac9551b9e4b6 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -130,6 +130,63 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev) vfio_pci_core_close_device(core_vdev); } +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_SIGBUS; + struct mem_region *memregion; + unsigned long pfn, addr; + + memregion = nvgrace_gpu_memregion(index, nvdev); + if (!memregion) + return ret; + + addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); + pfn = PHYS_PFN(memregion->memphys) + addr_to_pgoff(vma, addr); + + if (unmappable_for_order(vma, addr, pfn, order)) { + ret = VM_FAULT_FALLBACK; + goto out; + } + + scoped_guard(rwsem_read, &vdev->memory_lock) + ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); + +out: + 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) { @@ -137,10 +194,8 @@ 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); @@ -157,17 +212,18 @@ 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. @@ -184,23 +240,8 @@ 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; } -- 2.34.1 From: Ankit Agrawal Remove code duplication in vfio_pci_core_mmap by calling vfio_pci_core_setup_barmap to perform the bar mapping. No functional change is intended. Cc: Donald Dutile Reviewed-by: Shameer Kolothum Reviewed-by: Zhi Wang Suggested-by: Alex Williamson Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/vfio_pci_core.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 52e3a10d776b..020bf3aa22e9 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1753,18 +1753,9 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma * Even though we don't make use of the barmap for the mmap, * we need to request the region and the barmap tracks that. */ - if (!vdev->barmap[index]) { - ret = pci_request_selected_regions(pdev, - 1 << index, "vfio-pci"); - if (ret) - return ret; - - vdev->barmap[index] = pci_iomap(pdev, index, 0); - if (!vdev->barmap[index]) { - pci_release_selected_regions(pdev, 1 << index); - return -ENOMEM; - } - } + ret = vfio_pci_core_setup_barmap(vdev, index); + if (ret) + return ret; vma->vm_private_data = vdev; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); -- 2.34.1 From: Ankit Agrawal Split the function that check for the GPU device being ready on the probe. Move the code to wait for the GPU to be ready through BAR0 register reads to a separate function. This would help reuse the code. This also fixes a bug where the return status in case of timeout gets overridden by return from pci_enable_device. With the fix, a timeout generate an error as initially intended. Fixes: d85f69d520e6 ("vfio/nvgrace-gpu: Check the HBM training and C2C link status") Reviewed-by: Zhi Wang Reviewed-by: Shameer Kolothum Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/nvgrace-gpu/main.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index ac9551b9e4b6..f691deb8e43c 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -130,6 +130,20 @@ 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; +} + static unsigned long addr_to_pgoff(struct vm_area_struct *vma, unsigned long addr) { @@ -934,9 +948,8 @@ static bool nvgrace_gpu_has_mig_hw_bug(struct pci_dev *pdev) * Ensure that the BAR0 region is enabled before accessing the * registers. */ -static int nvgrace_gpu_wait_device_ready(struct pci_dev *pdev) +static int nvgrace_gpu_probe_check_device_ready(struct pci_dev *pdev) { - unsigned long timeout = jiffies + msecs_to_jiffies(POLL_TIMEOUT_MS); void __iomem *io; int ret = -ETIME; @@ -954,16 +967,8 @@ static int nvgrace_gpu_wait_device_ready(struct pci_dev *pdev) goto iomap_exit; } - do { - if ((ioread32(io + C2C_LINK_BAR0_OFFSET) == STATUS_READY) && - (ioread32(io + HBM_TRAINING_BAR0_OFFSET) == STATUS_READY)) { - ret = 0; - goto reg_check_exit; - } - msleep(POLL_QUANTUM_MS); - } while (!time_after(jiffies, timeout)); + ret = nvgrace_gpu_wait_device_ready(io); -reg_check_exit: pci_iounmap(pdev, io); iomap_exit: pci_release_selected_regions(pdev, 1 << 0); @@ -980,7 +985,7 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, u64 memphys, memlength; int ret; - ret = nvgrace_gpu_wait_device_ready(pdev); + ret = nvgrace_gpu_probe_check_device_ready(pdev); if (ret) return ret; -- 2.34.1 From: Ankit Agrawal Introduce a new flag reset_done to notify that the GPU has just been reset and the mapping to the GPU memory is zapped. Implement the reset_done handler to set this new variable. It will be used later in the patches to wait for the GPU memory to be ready before doing any mapping or access. Cc: Jason Gunthorpe Suggested-by: Alex Williamson Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/nvgrace-gpu/main.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index f691deb8e43c..b46984e76be7 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -58,6 +58,8 @@ struct nvgrace_gpu_pci_core_device { /* 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) @@ -1048,12 +1050,34 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = { 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. + * + * The reset_done implementation is triggered on every reset and is used + * set the reset_done variable that assists in achieving the serialization. + */ +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, }; -- 2.34.1 From: Ankit Agrawal Speculative prefetches from CPU to GPU memory until the GPU is ready after reset can cause harmless corrected RAS events to be logged on Grace systems. It is thus preferred that the mapping not be re-established until the GPU is ready post reset. The GPU readiness can be checked through BAR0 registers similar to the checking at the time of device probe. It can take several seconds for the GPU to be ready. So it is desirable that the time overlaps as much of the VM startup as possible to reduce impact on the VM bootup time. The GPU readiness state is thus checked on the first fault/huge_fault request or read/write access which amortizes the GPU readiness time. The first fault and read/write checks the GPU state when the reset_done flag - which denotes whether the GPU has just been reset. The memory_lock is taken across map/access to avoid races with GPU reset. Cc: Shameer Kolothum Cc: Alex Williamson Cc: Jason Gunthorpe Cc: Vikram Sethi Suggested-by: Alex Williamson Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/nvgrace-gpu/main.c | 81 +++++++++++++++++++++++++---- 1 file changed, 72 insertions(+), 9 deletions(-) diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index b46984e76be7..3064f8aca858 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -104,6 +104,17 @@ 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) + return ret; + vfio_pci_core_finish_enable(vdev); return 0; @@ -146,6 +157,31 @@ static int nvgrace_gpu_wait_device_ready(void __iomem *io) 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; + + 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) { @@ -163,13 +199,13 @@ static vm_fault_t nvgrace_gpu_vfio_pci_huge_fault(struct vm_fault *vmf, 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_SIGBUS; + vm_fault_t ret; struct mem_region *memregion; unsigned long pfn, addr; memregion = nvgrace_gpu_memregion(index, nvdev); if (!memregion) - return ret; + return VM_FAULT_SIGBUS; addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); pfn = PHYS_PFN(memregion->memphys) + addr_to_pgoff(vma, addr); @@ -179,8 +215,14 @@ static vm_fault_t nvgrace_gpu_vfio_pci_huge_fault(struct vm_fault *vmf, goto out; } - scoped_guard(rwsem_read, &vdev->memory_lock) + scoped_guard(rwsem_read, &vdev->memory_lock) { + if (nvgrace_gpu_check_device_ready(nvdev)) { + ret = VM_FAULT_SIGBUS; + goto out; + } + ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); + } out: dev_dbg_ratelimited(&vdev->pdev->dev, @@ -593,9 +635,15 @@ 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, &nvdev->core_device.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 @@ -713,9 +761,15 @@ 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, &nvdev->core_device.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; @@ -1056,6 +1110,15 @@ MODULE_DEVICE_TABLE(pci, nvgrace_gpu_vfio_pci_table); * * The reset_done implementation is triggered on every reset and is used * set the reset_done variable that assists in achieving the serialization. + * + * The writer memory_lock is held during reset through ioctl and FLR, while + * the reader is held in the fault and access code. + * + * The lock is however not taken during reset called through + * vfio_pci_core_enable during open. Whilst a serialization is not + * required at that early stage, it still prevents from putting + * lockdep_assert_held_write in this function. + * */ static void nvgrace_gpu_vfio_pci_reset_done(struct pci_dev *pdev) { -- 2.34.1