From 59334d821e8a981a2dbf921896ba052c615f0f30 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Sun, 22 Nov 2020 18:38:28 +1100 Subject: [PATCH] powerpc/powernv/npu: Do not attempt NPU2 setup on POWER8NVL NPU commit b1198a88230f2ce50c271e22b82a8b8610b2eea9 upstream. We execute certain NPU2 setup code (such as mapping an LPID to a device in NPU2) unconditionally if an Nvlink bridge is detected. However this cannot succeed on POWER8NVL machines and errors appear in dmesg. This is harmless as skiboot returns an error and the only place we check it is vfio-pci but that code does not get called on P8+ either. This adds a check if pnv_npu2_xxx helpers are called on a machine with NPU2 which initializes pnv_phb::npu in pnv_npu2_init(); pnv_phb::npu==NULL on POWER8/NVL (Naples). While at this, fix NULL derefencing in pnv_npu_peers_take_ownership/ pnv_npu_peers_release_ownership which occurs when GPUs on mentioned P8s cause EEH which happens if "vfio-pci" disables devices using the D3 power state; the vfio-pci's disable_idle_d3 module parameter controls this and must be set on Naples. The EEH handling clears the entire pnv_ioda_pe struct in pnv_ioda_free_pe() hence the NULL derefencing. We cannot recover from that but at least we stop crashing. Tested on - POWER9 pvr=004e1201, Ubuntu 19.04 host, Ubuntu 18.04 vm, NVIDIA GV100 10de:1db1 driver 418.39 - POWER8 pvr=004c0100, RHEL 7.6 host, Ubuntu 16.10 vm, NVIDIA P100 10de:15f9 driver 396.47 Fixes: 1b785611e119 ("powerpc/powernv/npu: Add release_ownership hook") Cc: stable@vger.kernel.org # 5.0 Signed-off-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201122073828.15446-1-aik@ozlabs.ru Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/powernv/npu-dma.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index b95b9e3c4c98..c640cb993209 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -384,7 +384,8 @@ static void pnv_npu_peers_take_ownership(struct iommu_table_group *table_group) for (i = 0; i < npucomp->pe_num; ++i) { struct pnv_ioda_pe *pe = npucomp->pe[i]; - if (!pe->table_group.ops->take_ownership) + if (!pe->table_group.ops || + !pe->table_group.ops->take_ownership) continue; pe->table_group.ops->take_ownership(&pe->table_group); } @@ -400,7 +401,8 @@ static void pnv_npu_peers_release_ownership( for (i = 0; i < npucomp->pe_num; ++i) { struct pnv_ioda_pe *pe = npucomp->pe[i]; - if (!pe->table_group.ops->release_ownership) + if (!pe->table_group.ops || + !pe->table_group.ops->release_ownership) continue; pe->table_group.ops->release_ownership(&pe->table_group); } @@ -560,6 +562,11 @@ int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid, return -ENODEV; hose = pci_bus_to_host(npdev->bus); + if (hose->npu == NULL) { + dev_info_once(&npdev->dev, "Nvlink1 does not support contexts"); + return 0; + } + nphb = hose->private_data; dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=%u\n", @@ -607,6 +614,11 @@ int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev) return -ENODEV; hose = pci_bus_to_host(npdev->bus); + if (hose->npu == NULL) { + dev_info_once(&npdev->dev, "Nvlink1 does not support contexts"); + return 0; + } + nphb = hose->private_data; dev_dbg(&gpdev->dev, "destroy context opalid=%llu\n",