powerpc/powernv/npu: Rework TCE Kill handling

The pnv_ioda_pe struct keeps an array of peers. At the moment it is only
used to link GPU and NPU for 2 purposes:

1. Access NPU quickly when configuring DMA for GPU - this was addressed
in the previos patch by removing use of it as DMA setup is not what
the kernel would constantly do.

2. Invalidate TCE cache for NPU when it is invalidated for GPU.
GPU and NPU are in different PE. There is already a mechanism to
attach multiple iommu_table_group to the same iommu_table (used for VFIO),
we can reuse it here so does this patch.

This gets rid of peers[] array and PNV_IODA_PE_PEER flag as they are
not needed anymore.

While we are here, add TCE cache invalidation after enabling bypass.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-By: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 800d70f..cb2d1da 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -136,22 +136,17 @@
 	struct pnv_ioda_pe *pe;
 	struct pci_dn *pdn;
 
-	if (npe->flags & PNV_IODA_PE_PEER) {
-		pe = npe->peers[0];
-		pdev = pe->pdev;
-	} else {
-		pdev = pnv_pci_get_gpu_dev(npe->pdev);
-		if (!pdev)
-			return NULL;
+	pdev = pnv_pci_get_gpu_dev(npe->pdev);
+	if (!pdev)
+		return NULL;
 
-		pdn = pci_get_pdn(pdev);
-		if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-			return NULL;
+	pdn = pci_get_pdn(pdev);
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return NULL;
 
-		hose = pci_bus_to_host(pdev->bus);
-		phb = hose->private_data;
-		pe = &phb->ioda.pe_array[pdn->pe_number];
-	}
+	hose = pci_bus_to_host(pdev->bus);
+	phb = hose->private_data;
+	pe = &phb->ioda.pe_array[pdn->pe_number];
 
 	if (gpdev)
 		*gpdev = pdev;
@@ -186,6 +181,10 @@
 	}
 	pnv_pci_ioda2_tce_invalidate_entire(phb, false);
 
+	/* Add the table to the list so its TCE cache will get invalidated */
+	pnv_pci_link_table_and_group(phb->hose->node, 0,
+			tbl, &npe->table_group);
+
 	return 0;
 }
 
@@ -206,45 +205,12 @@
 	}
 	pnv_pci_ioda2_tce_invalidate_entire(phb, false);
 
+	pnv_pci_unlink_table_and_group(npe->table_group.tables[0],
+			&npe->table_group);
+
 	return 0;
 }
 
-void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe)
-{
-	struct pnv_ioda_pe *gpe;
-	struct pci_dev *gpdev;
-	int i, avail = -1;
-
-	if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV))
-		return;
-
-	gpe = get_gpu_pci_dev_and_pe(npe, &gpdev);
-	if (!gpe)
-		return;
-
-	for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) {
-		/* Nothing to do if the PE is already connected. */
-		if (gpe->peers[i] == npe)
-			return;
-
-		if (!gpe->peers[i])
-			avail = i;
-	}
-
-	if (WARN_ON(avail < 0))
-		return;
-
-	gpe->peers[avail] = npe;
-	gpe->flags |= PNV_IODA_PE_PEER;
-
-	/*
-	 * We assume that the NPU devices only have a single peer PE
-	 * (the GPU PCIe device PE).
-	 */
-	npe->peers[0] = gpe;
-	npe->flags |= PNV_IODA_PE_PEER;
-}
-
 /*
  * Enables 32 bit DMA on NPU.
  */
@@ -302,6 +268,9 @@
 			npe->pe_number, npe->pe_number,
 			0 /* bypass base */, top);
 
+	if (rc == OPAL_SUCCESS)
+		pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+
 	return rc;
 }