#define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */
#define PNV_IODA1_DMA32_SEGSIZE 0x10000000
-static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
- "NPU_OCAPI" };
+static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_OCAPI" };
static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
static void pnv_pci_configure_bus(struct pci_bus *bus);
unsigned int pe_num = pe->pe_number;
WARN_ON(pe->pdev);
- WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */
- kfree(pe->npucomp);
memset(pe, 0, sizeof(struct pnv_ioda_pe));
mutex_lock(&phb->ioda.pe_alloc_mutex);
* Release from all parents PELT-V. NPUs don't have a PELTV
* table
*/
- if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+ if (phb->type != PNV_PHB_NPU_OCAPI)
pnv_ioda_unset_peltv(phb, pe, parent);
rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
* Configure PELTV. NPUs don't have a PELTV table so skip
* configuration on them.
*/
- if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+ if (phb->type != PNV_PHB_NPU_OCAPI)
pnv_ioda_set_peltv(phb, pe, true);
/* Setup reverse map */
/* NOTE: We don't get a reference for the pointer in the PE
* data structure, both the device and PE structures should be
- * destroyed at the same time. However, removing nvlink
- * devices will need some work.
+ * destroyed at the same time.
*
* At some point we want to remove the PDN completely anyways
*/
return pe;
}
-static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
-{
- int pe_num, found_pe = false, rc;
- long rid;
- struct pnv_ioda_pe *pe;
- struct pci_dev *gpu_pdev;
- struct pci_dn *npu_pdn;
- struct pnv_phb *phb = pci_bus_to_pnvhb(npu_pdev->bus);
-
- /*
- * Intentionally leak a reference on the npu device (for
- * nvlink only; this is not an opencapi path) to make sure it
- * never goes away, as it's been the case all along and some
- * work is needed otherwise.
- */
- pci_dev_get(npu_pdev);
-
- /*
- * Due to a hardware errata PE#0 on the NPU is reserved for
- * error handling. This means we only have three PEs remaining
- * which need to be assigned to four links, implying some
- * links must share PEs.
- *
- * To achieve this we assign PEs such that NPUs linking the
- * same GPU get assigned the same PE.
- */
- gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev);
- for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
- pe = &phb->ioda.pe_array[pe_num];
- if (!pe->pdev)
- continue;
-
- if (pnv_pci_get_gpu_dev(pe->pdev) == gpu_pdev) {
- /*
- * This device has the same peer GPU so should
- * be assigned the same PE as the existing
- * peer NPU.
- */
- dev_info(&npu_pdev->dev,
- "Associating to existing PE %x\n", pe_num);
- npu_pdn = pci_get_pdn(npu_pdev);
- rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
- npu_pdn->pe_number = pe_num;
- phb->ioda.pe_rmap[rid] = pe->pe_number;
- pe->device_count++;
-
- /* Map the PE to this link */
- rc = opal_pci_set_pe(phb->opal_id, pe_num, rid,
- OpalPciBusAll,
- OPAL_COMPARE_RID_DEVICE_NUMBER,
- OPAL_COMPARE_RID_FUNCTION_NUMBER,
- OPAL_MAP_PE);
- WARN_ON(rc != OPAL_SUCCESS);
- found_pe = true;
- break;
- }
- }
-
- if (!found_pe)
- /*
- * Could not find an existing PE so allocate a new
- * one.
- */
- return pnv_ioda_setup_dev_PE(npu_pdev);
- else
- return pe;
-}
-
-static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
-{
- struct pci_dev *pdev;
-
- list_for_each_entry(pdev, &bus->devices, bus_list)
- pnv_ioda_setup_npu_PE(pdev);
-}
-
-static void pnv_pci_ioda_setup_nvlink(void)
-{
- struct pci_controller *hose;
- struct pnv_phb *phb;
- struct pnv_ioda_pe *pe;
-
- list_for_each_entry(hose, &hose_list, list_node) {
- phb = hose->private_data;
- if (phb->type == PNV_PHB_NPU_NVLINK) {
- /* PE#0 is needed for error reporting */
- pnv_ioda_reserve_pe(phb, 0);
- pnv_ioda_setup_npu_PEs(hose->bus);
- if (phb->model == PNV_PHB_MODEL_NPU2)
- WARN_ON_ONCE(pnv_npu2_init(hose));
- }
- }
- list_for_each_entry(hose, &hose_list, list_node) {
- phb = hose->private_data;
- if (phb->type != PNV_PHB_IODA2)
- continue;
-
- list_for_each_entry(pe, &phb->ioda.pe_list, list)
- pnv_npu2_map_lpar(pe, MSR_DR | MSR_PR | MSR_HV);
- }
-
-#ifdef CONFIG_IOMMU_API
- /* setup iommu groups so we can do nvlink pass-thru */
- pnv_pci_npu_setup_iommu_groups();
-#endif
-}
-
static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
struct pnv_ioda_pe *pe);
#define PHB3_TCE_KILL_INVAL_PE PPC_BIT(1)
#define PHB3_TCE_KILL_INVAL_ONE PPC_BIT(2)
-static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
- const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
-
- mb(); /* Ensure previous TCE table stores are visible */
- if (rm)
- __raw_rm_writeq_be(val, invalidate);
- else
- __raw_writeq_be(val, invalidate);
-}
-
static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)
{
/* 01xb - invalidate TCEs that match the specified PE# */
struct pnv_phb *phb = pe->phb;
unsigned int shift = tbl->it_page_shift;
- /*
- * NVLink1 can use the TCE kill register directly as
- * it's the same as PHB3. NVLink2 is different and
- * should go via the OPAL call.
- */
- if (phb->model == PNV_PHB_MODEL_NPU) {
- /*
- * The NVLink hardware does not support TCE kill
- * per TCE entry so we have to invalidate
- * the entire cache for it.
- */
- pnv_pci_phb3_tce_invalidate_entire(phb, rm);
- continue;
- }
if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
pnv_pci_phb3_tce_invalidate(pe, rm, shift,
index, npages);
}
}
-void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
- if (phb->model == PNV_PHB_MODEL_NPU || phb->model == PNV_PHB_MODEL_PHB3)
- pnv_pci_phb3_tce_invalidate_entire(phb, rm);
- else
- opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL, 0, 0, 0, 0);
-}
-
static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
long npages, unsigned long uaddr,
enum dma_data_direction direction,
static void pnv_pci_ioda_fixup(void)
{
- pnv_pci_ioda_setup_nvlink();
pnv_pci_ioda_create_dbgfs();
pnv_pci_enable_bridges();
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;
.shutdown = pnv_pci_ioda_shutdown,
};
-static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
- .setup_msi_irqs = pnv_setup_msi_irqs,
- .teardown_msi_irqs = pnv_teardown_msi_irqs,
- .enable_device_hook = pnv_pci_enable_device_hook,
- .window_alignment = pnv_pci_window_alignment,
- .reset_secondary_bus = pnv_pci_reset_secondary_bus,
- .shutdown = pnv_pci_ioda_shutdown,
- .disable_device = pnv_npu_disable_device,
-};
-
static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
.enable_device_hook = pnv_ocapi_enable_device_hook,
.release_device = pnv_pci_release_device,
phb->model = PNV_PHB_MODEL_P7IOC;
else if (of_device_is_compatible(np, "ibm,power8-pciex"))
phb->model = PNV_PHB_MODEL_PHB3;
- else if (of_device_is_compatible(np, "ibm,power8-npu-pciex"))
- phb->model = PNV_PHB_MODEL_NPU;
- else if (of_device_is_compatible(np, "ibm,power9-npu-pciex"))
- phb->model = PNV_PHB_MODEL_NPU2;
else
phb->model = PNV_PHB_MODEL_UNKNOWN;
ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
switch (phb->type) {
- case PNV_PHB_NPU_NVLINK:
- hose->controller_ops = pnv_npu_ioda_controller_ops;
- break;
case PNV_PHB_NPU_OCAPI:
hose->controller_ops = pnv_npu_ocapi_ioda_controller_ops;
break;
pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
}
-void __init pnv_pci_init_npu_phb(struct device_node *np)
-{
- pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_NVLINK);
-}
-
void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np)
{
pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_OCAPI);