powerpc/powernv/npu: Simplify DMA setup
NPU devices are emulated in firmware and mainly used for NPU NVLink
training; one NPU device is per a hardware link. Their DMA/TCE setup
must match the GPU which is connected via PCIe and NVLink so any changes
to the DMA/TCE setup on the GPU PCIe device need to be propagated to
the NVLink device as this is what device drivers expect and it doesn't
make much sense to do anything else.
This makes NPU DMA setup explicit.
pnv_npu_ioda_controller_ops::pnv_npu_dma_set_mask is moved to pci-ioda,
made static and prints warning as dma_set_mask() should never be called
on this function as in any case it will not configure GPU; so we make
this explicit.
Instead of using PNV_IODA_PE_PEER and peers[] (which the next patch will
remove), we test every PCI device if there are corresponding NVLink
devices. If there are any, we propagate bypass mode to just found NPU
devices by calling the setup helper directly (which takes @bypass) and
avoid guessing (i.e. calculating from DMA mask) whether we need bypass
or not on NPU devices. Since DMA setup happens in very rare occasion,
this will not slow down booting or VFIO start/stop much.
This renames pnv_npu_disable_bypass to pnv_npu_dma_set_32 to make it
more clear what the function really does which is programming 32bit
table address to the TVT ("disabling bypass" means writing zeroes to
the TVT).
This removes pnv_npu_dma_set_bypass() from pnv_npu_ioda_fixup() as
the DMA configuration on NPU does not matter until dma_set_mask() is
called on GPU and that will do the NPU DMA configuration.
This removes phb->dma_dev_setup initialization for NPU as
pnv_pci_ioda_dma_dev_setup is no-op for it anyway.
This stops using npe->tce_bypass_base as it never changes and values
other than zero are not supported.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Alistair Popple <alistair@popple.id.au>
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 9b99aa1..c94ee1b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1669,8 +1669,6 @@
struct pnv_ioda_pe *pe;
uint64_t top;
bool bypass = false;
- struct pci_dev *linked_npu_dev;
- int i;
if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
return -ENODEV;;
@@ -1691,15 +1689,7 @@
*pdev->dev.dma_mask = dma_mask;
/* Update peer npu devices */
- if (pe->flags & PNV_IODA_PE_PEER)
- for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) {
- if (!pe->peers[i])
- continue;
-
- linked_npu_dev = pe->peers[i]->pdev;
- if (dma_get_mask(&linked_npu_dev->dev) != dma_mask)
- dma_set_mask(&linked_npu_dev->dev, dma_mask);
- }
+ pnv_npu_try_dma_set_bypass(pdev, bypass);
return 0;
}
@@ -3194,7 +3184,6 @@
enable_bypass = dma_get_mask(&pe->pdev->dev) ==
DMA_BIT_MASK(64);
pnv_npu_init_dma_pe(pe);
- pnv_npu_dma_set_bypass(pe, enable_bypass);
}
}
}
@@ -3340,6 +3329,14 @@
.shutdown = pnv_pci_ioda_shutdown,
};
+static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask)
+{
+ dev_err_once(&npdev->dev,
+ "%s operation unsupported for NVLink devices\n",
+ __func__);
+ return -EPERM;
+}
+
static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
.dma_dev_setup = pnv_pci_dma_dev_setup,
#ifdef CONFIG_PCI_MSI
@@ -3516,9 +3513,6 @@
phb->freeze_pe = pnv_ioda_freeze_pe;
phb->unfreeze_pe = pnv_ioda_unfreeze_pe;
- /* Setup TCEs */
- phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
-
/* Setup MSI support */
pnv_pci_init_ioda_msis(phb);
@@ -3531,10 +3525,12 @@
*/
ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
- if (phb->type == PNV_PHB_NPU)
+ if (phb->type == PNV_PHB_NPU) {
hose->controller_ops = pnv_npu_ioda_controller_ops;
- else
+ } else {
+ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
hose->controller_ops = pnv_pci_ioda_controller_ops;
+ }
#ifdef CONFIG_PCI_IOV
ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;