From 31594b263cc4fbe30ebbe412a4a788f726f03a02 Mon Sep 17 00:00:00 2001 From: Arthur Hanson Rasmusson Date: Sun, 4 Oct 2026 16:19:31 -0400 Subject: vgsp: end-to-end CUDA acceptance in the guest The no-claim emulation path now runs a stock CUDA program end to end: device properties, cudaMalloc, a GPU-authored string kernel read back byte-for-byte, two 4 MB host-to-device copies, a 1 M-element vectorAdd executed on the physical GPU through the host bridge, and the device-to-host copy-back verified element by element. Three consecutive supervised cycles report MAIL + VADD bad=0 checksum=392344090.500000 + STATUS OK with identical input/output hashes. Two data-path correctness fixes make the transfers sound: - Once-only op execution per GPFIFO entry. The pump replays recently consumed ring entries when translation batches are injected so missed releases can land; re-executing a CE copy is not idempotent because its source is a client staging buffer that may have been refilled. Slots now record their raw entry words and a replayed entry matching that identity suppresses operations while still processing releases. - Per-page translation of virtual operands. svc_copy resolved only the first page of a VA range and walked the PA linearly; client staging ranges are frequently split (observed 195 + 61 pages), so the tail of alternating chunks was read from unrelated memory. Multi-page copies now re-resolve each 4 KB page through the trusted resolver. Also carries the earlier uncommitted emulation fixes that got the client to the launch (QMD address-window gate, counter registration persistence, 512 MiB emulated FB, bridge slot hygiene) and bounded diagnostics (sema-bigop, sema-bigcopy, bridge-in/out hashes, daemon INCHECK/OUTCHECK/dumps). --- kernel/main.c | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) (limited to 'kernel/main.c') diff --git a/kernel/main.c b/kernel/main.c index 7001b3d..ca973b0 100644 --- a/kernel/main.c +++ b/kernel/main.c @@ -1285,15 +1285,34 @@ static int nv_vgpu_vfio_dev_mmap(struct vfio_device *vdev, struct vm_area_struct return 0; } - /* BAR2 region - ioremap'd host BAR; map backing physical address */ + /* BAR2 region - emulated shadow (emulation-only) or real BAR (claim) */ region_base = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR2_REGION_INDEX); region_size = vgpu->bars[2].size; if (offset >= region_base && offset < region_base + region_size) { + unsigned long bar2_off = offset - region_base; + unsigned long pos; + if (!vgpu->bars[2].vaddr || region_size == 0) return -ENODEV; if (offset + size > region_base + region_size) return -EINVAL; - pfn = (vgpu->bars[2].gpa + (offset - region_base)) >> PAGE_SHIFT; + if (vgpu->bars[2].emulated) { + /* Emulation-only: map the private shadow's own pages, + * never the physical GPU's BAR2 PFNs. */ + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); + vma->vm_page_prot = + pgprot_writecombine(vma->vm_page_prot); + for (pos = 0; pos < size; pos += PAGE_SIZE) { + pfn = vmalloc_to_pfn(vgpu->bars[2].vaddr + + bar2_off + pos); + if (remap_pfn_range(vma, vma->vm_start + pos, + pfn, PAGE_SIZE, + vma->vm_page_prot)) + return -EAGAIN; + } + return 0; + } + pfn = (vgpu->bars[2].gpa + bar2_off) >> PAGE_SHIFT; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); return remap_pfn_range(vma, vma->vm_start, pfn, size, vma->vm_page_prot); } @@ -2642,6 +2661,14 @@ MODULE_PARM_DESC(sema_copy_dst2, "Second destination window for sema_copy_dst (d module_param_named(sema_ce_grace_ms, gsp_sema_ce_grace_ms, uint, 0644); MODULE_PARM_DESC(sema_ce_grace_ms, "CE pending-entry grace window in ms (default 8000)"); +/* + * Bounded work-before-release hold (ms) for an unreadable CE entry; the + * deferred retry probe shows translations/pins land 0.5-2 s late. Absolute + * per-entry deadline, never reset; 0 disables. + */ +module_param_named(sema_push_hold_ms, gsp_sema_push_hold_ms, uint, 0644); +MODULE_PARM_DESC(sema_push_hold_ms, "CE unreadable-entry work-before-release hold in ms (default 2500, 0 disables)"); + /* * Grace window (ms) an untranslatable GR entry stays pending before the pump * consumes it as stale, so a late push-buffer pin can still make it readable. -- cgit v1.2.3