summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAlexey Kardashevskiy <aik@ozlabs.ru>2018-12-19 19:52:13 +1100
committerMichael Ellerman <mpe@ellerman.id.au>2018-12-21 16:20:46 +1100
commitab7032e793f9ad799ca2692046fba5baed6d2a86 (patch)
tree850c8d5693c8992edfb8595197afb76f320ea56e
parentffca395b11c4a5a6df6d6345f794b0e3d578e2d0 (diff)
downloadlinux-ab7032e793f9ad799ca2692046fba5baed6d2a86.tar.gz
linux-ab7032e793f9ad799ca2692046fba5baed6d2a86.tar.bz2
linux-ab7032e793f9ad799ca2692046fba5baed6d2a86.zip
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: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alistair Popple <alistair@popple.id.au> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 036a8b0a1ea4..c39def4e1a42 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3667,6 +3667,15 @@ static void pnv_pci_release_device(struct pci_dev *pdev)
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)
{
struct pnv_phb *phb = hose->private_data;
@@ -3707,6 +3716,7 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
.reset_secondary_bus = pnv_pci_reset_secondary_bus,
.dma_set_mask = pnv_npu_dma_set_mask,
.shutdown = pnv_pci_ioda_shutdown,
+ .disable_device = pnv_npu_disable_device,
};
static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {