powerpc/powernv/npu: Enable NVLink pass through
IBM POWER8 NVlink systems come with Tesla K40-ish GPUs each of which
also has a couple of fast speed links (NVLink). The interface to links
is exposed as an emulated PCI bridge which is included into the same
IOMMU group as the corresponding GPU.
In the kernel, NPUs get a separate PHB of the PNV_PHB_NPU type and a PE
which behave pretty much as the standard IODA2 PHB except NPU PHB has
just a single TVE in the hardware which means it can have either
32bit window or 64bit window or DMA bypass but never two of these.
In order to make these links work when GPU is passed to the guest,
these bridges need to be passed as well; otherwise performance will
degrade.
This implements and exports API to manage NPU state in regard to VFIO;
it replicates iommu_table_group_ops.
This defines a new pnv_pci_ioda2_npu_ops which is assigned to
the IODA2 bridge if there are NPUs for a GPU on the bridge.
The new callbacks call the default IODA2 callbacks plus new NPU API.
This adds a gpe_table_group_to_npe() helper to find NPU PE for the IODA2
table_group, it is not expected to fail as the helper is only called
from the pnv_pci_ioda2_npu_ops.
This does not define NPU-specific .release_ownership() so after
VFIO is finished, DMA on NPU is disabled which is ok as the nvidia
driver sets DMA mask when probing which enable 32 or 64bit DMA on NPU.
This adds a pnv_pci_npu_setup_iommu() helper which adds NPUs to
the GPU group if any found. The helper uses helpers to look for
the "ibm,gpu" property in the device tree which is a phandle of
the corresponding GPU.
This adds an additional loop over PEs in pnv_ioda_setup_dma() as the main
loop skips NPU PEs as they do not have 32bit DMA segments.
As pnv_npu_set_window() and pnv_npu_unset_window() are started being used
by the new IODA2-NPU IOMMU group, this makes the helpers public and
adds the DMA window number parameter.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-By: Alistair Popple <alistair@popple.id.au>
[mpe: Add pnv_pci_ioda_setup_iommu_api() to fix build with IOMMU_API=n]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index ef31218..4cfe704 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2389,6 +2389,116 @@
.take_ownership = pnv_ioda2_take_ownership,
.release_ownership = pnv_ioda2_release_ownership,
};
+
+static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque)
+{
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pnv_ioda_pe **ptmppe = opaque;
+ struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+
+ if (!pdn || pdn->pe_number == IODA_INVALID_PE)
+ return 0;
+
+ hose = pci_bus_to_host(pdev->bus);
+ phb = hose->private_data;
+ if (phb->type != PNV_PHB_NPU)
+ return 0;
+
+ *ptmppe = &phb->ioda.pe_array[pdn->pe_number];
+
+ return 1;
+}
+
+/*
+ * This returns PE of associated NPU.
+ * This assumes that NPU is in the same IOMMU group with GPU and there is
+ * no other PEs.
+ */
+static struct pnv_ioda_pe *gpe_table_group_to_npe(
+ struct iommu_table_group *table_group)
+{
+ struct pnv_ioda_pe *npe = NULL;
+ int ret = iommu_group_for_each_dev(table_group->group, &npe,
+ gpe_table_group_to_npe_cb);
+
+ BUG_ON(!ret || !npe);
+
+ return npe;
+}
+
+static long pnv_pci_ioda2_npu_set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ long ret = pnv_pci_ioda2_set_window(table_group, num, tbl);
+
+ if (ret)
+ return ret;
+
+ ret = pnv_npu_set_window(gpe_table_group_to_npe(table_group), num, tbl);
+ if (ret)
+ pnv_pci_ioda2_unset_window(table_group, num);
+
+ return ret;
+}
+
+static long pnv_pci_ioda2_npu_unset_window(
+ struct iommu_table_group *table_group,
+ int num)
+{
+ long ret = pnv_pci_ioda2_unset_window(table_group, num);
+
+ if (ret)
+ return ret;
+
+ return pnv_npu_unset_window(gpe_table_group_to_npe(table_group), num);
+}
+
+static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group)
+{
+ /*
+ * Detach NPU first as pnv_ioda2_take_ownership() will destroy
+ * the iommu_table if 32bit DMA is enabled.
+ */
+ pnv_npu_take_ownership(gpe_table_group_to_npe(table_group));
+ pnv_ioda2_take_ownership(table_group);
+}
+
+static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = {
+ .get_table_size = pnv_pci_ioda2_get_table_size,
+ .create_table = pnv_pci_ioda2_create_table,
+ .set_window = pnv_pci_ioda2_npu_set_window,
+ .unset_window = pnv_pci_ioda2_npu_unset_window,
+ .take_ownership = pnv_ioda2_npu_take_ownership,
+ .release_ownership = pnv_ioda2_release_ownership,
+};
+
+static void pnv_pci_ioda_setup_iommu_api(void)
+{
+ struct pci_controller *hose, *tmp;
+ struct pnv_phb *phb;
+ struct pnv_ioda_pe *pe, *gpe;
+
+ /*
+ * Now we have all PHBs discovered, time to add NPU devices to
+ * the corresponding IOMMU groups.
+ */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+ phb = hose->private_data;
+
+ if (phb->type != PNV_PHB_NPU)
+ continue;
+
+ list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+ gpe = pnv_pci_npu_setup_iommu(pe);
+ if (gpe)
+ gpe->table_group.ops = &pnv_pci_ioda2_npu_ops;
+ }
+ }
+}
+#else /* !CONFIG_IOMMU_API */
+static void pnv_pci_ioda_setup_iommu_api(void) { };
#endif
static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
@@ -3115,6 +3225,8 @@
phb = hose->private_data;
phb->initialized = 1;
}
+
+ pnv_pci_ioda_setup_iommu_api();
}
static void pnv_pci_ioda_create_dbgfs(void)