Commit ab7032e7 authored by Alexey Kardashevskiy's avatar Alexey Kardashevskiy Committed by Michael Ellerman

powerpc/ioda/npu: Call skiboot's hot reset hook when disabling NPU2

The skiboot firmware has a hot reset handler which fences the NVIDIA V100
GPU RAM on Witherspoons and makes accesses no-op instead of throwing HMIs:
https://github.com/open-power/skiboot/commit/fca2b2b839a67

Now we are going to pass V100 via VFIO which most certainly involves
KVM guests which are often terminated without getting a chance to offline
GPU RAM so we end up with a running machine with misconfigured memory.
Accessing this memory produces hardware management interrupts (HMI)
which bring the host down.

To suppress HMIs, this wires up this hot reset hook to vfio_pci_disable()
via pci_disable_device() which switches NPU2 to a safe mode and prevents
HMIs.
Signed-off-by: default avatarAlexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: default avatarAlistair Popple <alistair@popple.id.au>
Reviewed-by: default avatarDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent ffca395b
...@@ -3667,6 +3667,15 @@ static void pnv_pci_release_device(struct pci_dev *pdev) ...@@ -3667,6 +3667,15 @@ static void pnv_pci_release_device(struct pci_dev *pdev)
pnv_ioda_release_pe(pe); pnv_ioda_release_pe(pe);
} }
static void pnv_npu_disable_device(struct pci_dev *pdev)
{
struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
struct eeh_pe *eehpe = edev ? edev->pe : NULL;
if (eehpe && eeh_ops && eeh_ops->reset)
eeh_ops->reset(eehpe, EEH_RESET_HOT);
}
static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
{ {
struct pnv_phb *phb = hose->private_data; struct pnv_phb *phb = hose->private_data;
...@@ -3707,6 +3716,7 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = { ...@@ -3707,6 +3716,7 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
.reset_secondary_bus = pnv_pci_reset_secondary_bus, .reset_secondary_bus = pnv_pci_reset_secondary_bus,
.dma_set_mask = pnv_npu_dma_set_mask, .dma_set_mask = pnv_npu_dma_set_mask,
.shutdown = pnv_pci_ioda_shutdown, .shutdown = pnv_pci_ioda_shutdown,
.disable_device = pnv_npu_disable_device,
}; };
static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = { static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment