diff options
Diffstat (limited to 'arch/powerpc/platforms/powernv')
| -rw-r--r-- | arch/powerpc/platforms/powernv/Kconfig | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/eeh-powernv.c | 8 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/npu-dma.c | 564 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-power.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci-ioda-tce.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci-ioda.c | 265 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci.c | 49 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci.h | 36 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/vas-debug.c | 28 |
10 files changed, 641 insertions, 324 deletions
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 99083fe992d5..850eee860cf2 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -7,7 +7,7 @@ config PPC_POWERNV select PPC_ICP_NATIVE select PPC_XIVE_NATIVE select PPC_P7_NAP - select PCI + select FORCE_PCI select PCI_MSI select EPAPR_BOOT select PPC_INDIRECT_PIO diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index abc0be7507c8..f38078976c5d 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -564,8 +564,8 @@ static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) static int pnv_eeh_get_phb_state(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; s64 rc; int result = 0; @@ -603,8 +603,8 @@ static int pnv_eeh_get_phb_state(struct eeh_pe *pe) static int pnv_eeh_get_pe_state(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; s64 rc; int result; diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 75b935252981..d7f742ed48ba 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -9,32 +9,19 @@ * License as published by the Free Software Foundation. */ -#include <linux/slab.h> #include <linux/mmu_notifier.h> #include <linux/mmu_context.h> #include <linux/of.h> -#include <linux/export.h> #include <linux/pci.h> #include <linux/memblock.h> -#include <linux/iommu.h> #include <linux/sizes.h> #include <asm/debugfs.h> -#include <asm/tlb.h> #include <asm/powernv.h> -#include <asm/reg.h> -#include <asm/opal.h> -#include <asm/io.h> -#include <asm/iommu.h> -#include <asm/pnv-pci.h> -#include <asm/msi_bitmap.h> #include <asm/opal.h> -#include "powernv.h" #include "pci.h" -#define npu_to_phb(x) container_of(x, struct pnv_phb, npu) - /* * spinlock to protect initialisation of an npu_context for a particular * mm_struct. @@ -133,15 +120,25 @@ static struct pnv_ioda_pe *get_gpu_pci_dev_and_pe(struct pnv_ioda_pe *npe, return pe; } -long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num, +static long pnv_npu_unset_window(struct iommu_table_group *table_group, + int num); + +static long pnv_npu_set_window(struct iommu_table_group *table_group, int num, struct iommu_table *tbl) { + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); struct pnv_phb *phb = npe->phb; int64_t rc; const unsigned long size = tbl->it_indirect_levels ? tbl->it_level_size : tbl->it_size; const __u64 start_addr = tbl->it_offset << tbl->it_page_shift; const __u64 win_size = tbl->it_size << tbl->it_page_shift; + int num2 = (num == 0) ? 1 : 0; + + /* NPU has just one TVE so if there is another table, remove it first */ + if (npe->table_group.tables[num2]) + pnv_npu_unset_window(&npe->table_group, num2); pe_info(npe, "Setting up window %llx..%llx pg=%lx\n", start_addr, start_addr + win_size - 1, @@ -167,11 +164,16 @@ long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num, return 0; } -long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num) +static long pnv_npu_unset_window(struct iommu_table_group *table_group, int num) { + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); struct pnv_phb *phb = npe->phb; int64_t rc; + if (!npe->table_group.tables[num]) + return 0; + pe_info(npe, "Removing DMA window\n"); rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number, @@ -210,7 +212,8 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe) if (!gpe) return; - rc = pnv_npu_set_window(npe, 0, gpe->table_group.tables[0]); + rc = pnv_npu_set_window(&npe->table_group, 0, + gpe->table_group.tables[0]); /* * NVLink devices use the same TCE table configuration as @@ -235,7 +238,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe) if (phb->type != PNV_PHB_NPU_NVLINK || !npe->pdev) return -EINVAL; - rc = pnv_npu_unset_window(npe, 0); + rc = pnv_npu_unset_window(&npe->table_group, 0); if (rc != OPAL_SUCCESS) return rc; @@ -288,11 +291,15 @@ void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass) } } +#ifdef CONFIG_IOMMU_API /* Switch ownership from platform code to external user (e.g. VFIO) */ -void pnv_npu_take_ownership(struct pnv_ioda_pe *npe) +static void pnv_npu_take_ownership(struct iommu_table_group *table_group) { + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); struct pnv_phb *phb = npe->phb; int64_t rc; + struct pci_dev *gpdev = NULL; /* * Note: NPU has just a single TVE in the hardware which means that @@ -301,7 +308,7 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe) * if it was enabled at the moment of ownership change. */ if (npe->table_group.tables[0]) { - pnv_npu_unset_window(npe, 0); + pnv_npu_unset_window(&npe->table_group, 0); return; } @@ -314,30 +321,315 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe) return; } pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false); + + get_gpu_pci_dev_and_pe(npe, &gpdev); + if (gpdev) + pnv_npu2_unmap_lpar_dev(gpdev); } -struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe) +static void pnv_npu_release_ownership(struct iommu_table_group *table_group) { - struct pnv_phb *phb = npe->phb; - struct pci_bus *pbus = phb->hose->bus; - struct pci_dev *npdev, *gpdev = NULL, *gptmp; - struct pnv_ioda_pe *gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); + struct pci_dev *gpdev = NULL; + + get_gpu_pci_dev_and_pe(npe, &gpdev); + if (gpdev) + pnv_npu2_map_lpar_dev(gpdev, 0, MSR_DR | MSR_PR | MSR_HV); +} + +static struct iommu_table_group_ops pnv_pci_npu_ops = { + .set_window = pnv_npu_set_window, + .unset_window = pnv_npu_unset_window, + .take_ownership = pnv_npu_take_ownership, + .release_ownership = pnv_npu_release_ownership, +}; +#endif /* !CONFIG_IOMMU_API */ + +/* + * NPU2 ATS + */ +/* Maximum possible number of ATSD MMIO registers per NPU */ +#define NV_NMMU_ATSD_REGS 8 +#define NV_NPU_MAX_PE_NUM 16 + +/* + * A compound NPU IOMMU group which might consist of 1 GPU + 2xNPUs (POWER8) or + * up to 3 x (GPU + 2xNPUs) (POWER9). + */ +struct npu_comp { + struct iommu_table_group table_group; + int pe_num; + struct pnv_ioda_pe *pe[NV_NPU_MAX_PE_NUM]; +}; + +/* An NPU descriptor, valid for POWER9 only */ +struct npu { + int index; + __be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS]; + unsigned int mmio_atsd_count; + + /* Bitmask for MMIO register usage */ + unsigned long mmio_atsd_usage; + + /* Do we need to explicitly flush the nest mmu? */ + bool nmmu_flush; + + struct npu_comp npucomp; +}; + +#ifdef CONFIG_IOMMU_API +static long pnv_npu_peers_create_table_userspace( + struct iommu_table_group *table_group, + int num, __u32 page_shift, __u64 window_size, __u32 levels, + struct iommu_table **ptbl) +{ + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + if (!npucomp->pe_num || !npucomp->pe[0] || + !npucomp->pe[0]->table_group.ops || + !npucomp->pe[0]->table_group.ops->create_table) + return -EFAULT; + + return npucomp->pe[0]->table_group.ops->create_table( + &npucomp->pe[0]->table_group, num, page_shift, + window_size, levels, ptbl); +} + +static long pnv_npu_peers_set_window(struct iommu_table_group *table_group, + int num, struct iommu_table *tbl) +{ + int i, j; + long ret = 0; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + if (!pe->table_group.ops->set_window) + continue; + + ret = pe->table_group.ops->set_window(&pe->table_group, + num, tbl); + if (ret) + break; + } + + if (ret) { + for (j = 0; j < i; ++j) { + struct pnv_ioda_pe *pe = npucomp->pe[j]; + + if (!pe->table_group.ops->unset_window) + continue; + + ret = pe->table_group.ops->unset_window( + &pe->table_group, num); + if (ret) + break; + } + } else { + table_group->tables[num] = iommu_tce_table_get(tbl); + } + + return ret; +} - if (!gpe || !gpdev) +static long pnv_npu_peers_unset_window(struct iommu_table_group *table_group, + int num) +{ + int i, j; + long ret = 0; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + WARN_ON(npucomp->table_group.tables[num] != + table_group->tables[num]); + if (!npucomp->table_group.tables[num]) + continue; + + if (!pe->table_group.ops->unset_window) + continue; + + ret = pe->table_group.ops->unset_window(&pe->table_group, num); + if (ret) + break; + } + + if (ret) { + for (j = 0; j < i; ++j) { + struct pnv_ioda_pe *pe = npucomp->pe[j]; + + if (!npucomp->table_group.tables[num]) + continue; + + if (!pe->table_group.ops->set_window) + continue; + + ret = pe->table_group.ops->set_window(&pe->table_group, + num, table_group->tables[num]); + if (ret) + break; + } + } else if (table_group->tables[num]) { + iommu_tce_table_put(table_group->tables[num]); + table_group->tables[num] = NULL; + } + + return ret; +} + +static void pnv_npu_peers_take_ownership(struct iommu_table_group *table_group) +{ + int i; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + if (!pe->table_group.ops->take_ownership) + continue; + pe->table_group.ops->take_ownership(&pe->table_group); + } +} + +static void pnv_npu_peers_release_ownership( + struct iommu_table_group *table_group) +{ + int i; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + if (!pe->table_group.ops->release_ownership) + continue; + pe->table_group.ops->release_ownership(&pe->table_group); + } +} + +static struct iommu_table_group_ops pnv_npu_peers_ops = { + .get_table_size = pnv_pci_ioda2_get_table_size, + .create_table = pnv_npu_peers_create_table_userspace, + .set_window = pnv_npu_peers_set_window, + .unset_window = pnv_npu_peers_unset_window, + .take_ownership = pnv_npu_peers_take_ownership, + .release_ownership = pnv_npu_peers_release_ownership, +}; + +static void pnv_comp_attach_table_group(struct npu_comp *npucomp, + struct pnv_ioda_pe *pe) +{ + if (WARN_ON(npucomp->pe_num == NV_NPU_MAX_PE_NUM)) + return; + + npucomp->pe[npucomp->pe_num] = pe; + ++npucomp->pe_num; +} + +struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe) +{ + struct iommu_table_group *table_group; + struct npu_comp *npucomp; + struct pci_dev *gpdev = NULL; + struct pci_controller *hose; + struct pci_dev *npdev = NULL; + + list_for_each_entry(gpdev, &pe->pbus->devices, bus_list) { + npdev = pnv_pci_get_npu_dev(gpdev, 0); + if (npdev) + break; + } + + if (!npdev) + /* It is not an NPU attached device, skip */ + return NULL; + + hose = pci_bus_to_host(npdev->bus); + + if (hose->npu) { + table_group = &hose->npu->npucomp.table_group; + + if (!table_group->group) { + table_group->ops = &pnv_npu_peers_ops; + iommu_register_group(table_group, + hose->global_number, + pe->pe_number); + } + } else { + /* Create a group for 1 GPU and attached NPUs for POWER8 */ + pe->npucomp = kzalloc(sizeof(pe->npucomp), GFP_KERNEL); + table_group = &pe->npucomp->table_group; + table_group->ops = &pnv_npu_peers_ops; + iommu_register_group(table_group, hose->global_number, + pe->pe_number); + } + + /* Steal capabilities from a GPU PE */ + table_group->max_dynamic_windows_supported = + pe->table_group.max_dynamic_windows_supported; + table_group->tce32_start = pe->table_group.tce32_start; + table_group->tce32_size = pe->table_group.tce32_size; + table_group->max_levels = pe->table_group.max_levels; + if (!table_group->pgsizes) + table_group->pgsizes = pe->table_group.pgsizes; + + npucomp = container_of(table_group, struct npu_comp, table_group); + pnv_comp_attach_table_group(npucomp, pe); + + return table_group; +} + +struct iommu_table_group *pnv_npu_compound_attach(struct pnv_ioda_pe *pe) +{ + struct iommu_table_group *table_group; + struct npu_comp *npucomp; + struct pci_dev *gpdev = NULL; + struct pci_dev *npdev; + struct pnv_ioda_pe *gpe = get_gpu_pci_dev_and_pe(pe, &gpdev); + + WARN_ON(!(pe->flags & PNV_IODA_PE_DEV)); + if (!gpe) return NULL; - list_for_each_entry(npdev, &pbus->devices, bus_list) { - gptmp = pnv_pci_get_gpu_dev(npdev); + /* + * IODA2 bridges get this set up from pci_controller_ops::setup_bridge + * but NPU bridges do not have this hook defined so we do it here. + * We do not setup other table group parameters as they won't be used + * anyway - NVLink bridges are subordinate PEs. + */ + pe->table_group.ops = &pnv_pci_npu_ops; + + table_group = iommu_group_get_iommudata( + iommu_group_get(&gpdev->dev)); + + /* + * On P9 NPU PHB and PCI PHB support different page sizes, + * keep only matching. We expect here that NVLink bridge PE pgsizes is + * initialized by the caller. + */ + table_group->pgsizes &= pe->table_group.pgsizes; + npucomp = container_of(table_group, struct npu_comp, table_group); + pnv_comp_attach_table_group(npucomp, pe); + + list_for_each_entry(npdev, &pe->phb->hose->bus->devices, bus_list) { + struct pci_dev *gpdevtmp = pnv_pci_get_gpu_dev(npdev); - if (gptmp != gpdev) + if (gpdevtmp != gpdev) continue; - pe_info(gpe, "Attached NPU %s\n", dev_name(&npdev->dev)); - iommu_group_add_device(gpe->table_group.group, &npdev->dev); + iommu_add_device(table_group, &npdev->dev); } - return gpe; + return table_group; } +#endif /* CONFIG_IOMMU_API */ /* Maximum number of nvlinks per npu */ #define NV_MAX_LINKS 6 @@ -490,7 +782,6 @@ static void acquire_atsd_reg(struct npu_context *npu_context, int i, j; struct npu *npu; struct pci_dev *npdev; - struct pnv_phb *nphb; for (i = 0; i <= max_npu2_index; i++) { mmio_atsd_reg[i].reg = -1; @@ -505,8 +796,10 @@ static void acquire_atsd_reg(struct npu_context *npu_context, if (!npdev) continue; - nphb = pci_bus_to_host(npdev->bus)->private_data; - npu = &nphb->npu; + npu = pci_bus_to_host(npdev->bus)->npu; + if (!npu) + continue; + mmio_atsd_reg[i].npu = npu; mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu); while (mmio_atsd_reg[i].reg < 0) { @@ -671,9 +964,9 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, u32 nvlink_index; struct device_node *nvlink_dn; struct mm_struct *mm = current->mm; - struct pnv_phb *nphb; struct npu *npu; struct npu_context *npu_context; + struct pci_controller *hose; /* * At present we don't support GPUs connected to multiple NPUs and I'm @@ -681,13 +974,14 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, */ struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); - if (!firmware_has_feature(FW_FEATURE_OPAL)) - return ERR_PTR(-ENODEV); - if (!npdev) /* No nvlink associated with this GPU device */ return ERR_PTR(-ENODEV); + /* We only support DR/PR/HV in pnv_npu2_map_lpar_dev() */ + if (flags & ~(MSR_DR | MSR_PR | MSR_HV)) + return ERR_PTR(-EINVAL); + nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0); if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index", &nvlink_index))) @@ -701,20 +995,10 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, return ERR_PTR(-EINVAL); } - nphb = pci_bus_to_host(npdev->bus)->private_data; - npu = &nphb->npu; - - /* - * Setup the NPU context table for a particular GPU. These need to be - * per-GPU as we need the tables to filter ATSDs when there are no - * active contexts on a particular GPU. It is safe for these to be - * called concurrently with destroy as the OPAL call takes appropriate - * locks and refcounts on init/destroy. - */ - rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags, - PCI_DEVID(gpdev->bus->number, gpdev->devfn)); - if (rc < 0) - return ERR_PTR(-ENOSPC); + hose = pci_bus_to_host(npdev->bus); + npu = hose->npu; + if (!npu) + return ERR_PTR(-ENODEV); /* * We store the npu pci device so we can more easily get at the @@ -726,9 +1010,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, if (npu_context->release_cb != cb || npu_context->priv != priv) { spin_unlock(&npu_context_lock); - opal_npu_destroy_context(nphb->opal_id, mm->context.id, - PCI_DEVID(gpdev->bus->number, - gpdev->devfn)); return ERR_PTR(-EINVAL); } @@ -754,9 +1035,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, if (rc) { kfree(npu_context); - opal_npu_destroy_context(nphb->opal_id, mm->context.id, - PCI_DEVID(gpdev->bus->number, - gpdev->devfn)); return ERR_PTR(rc); } @@ -776,7 +1054,7 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, */ WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], npdev); - if (!nphb->npu.nmmu_flush) { + if (!npu->nmmu_flush) { /* * If we're not explicitly flushing ourselves we need to mark * the thread for global flushes @@ -809,27 +1087,24 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context, struct pci_dev *gpdev) { int removed; - struct pnv_phb *nphb; struct npu *npu; struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); struct device_node *nvlink_dn; u32 nvlink_index; + struct pci_controller *hose; if (WARN_ON(!npdev)) return; - if (!firmware_has_feature(FW_FEATURE_OPAL)) + hose = pci_bus_to_host(npdev->bus); + npu = hose->npu; + if (!npu) return; - - nphb = pci_bus_to_host(npdev->bus)->private_data; - npu = &nphb->npu; nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0); if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index", &nvlink_index))) return; WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL); - opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id, - PCI_DEVID(gpdev->bus->number, gpdev->devfn)); spin_lock(&npu_context_lock); removed = kref_put(&npu_context->kref, pnv_npu2_release_context); spin_unlock(&npu_context_lock); @@ -857,13 +1132,12 @@ int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, u64 rc = 0, result = 0; int i, is_write; struct page *page[1]; + const char __user *u; + char c; /* mmap_sem should be held so the struct_mm must be present */ struct mm_struct *mm = context->mm; - if (!firmware_has_feature(FW_FEATURE_OPAL)) - return -ENODEV; - WARN_ON(!rwsem_is_locked(&mm->mmap_sem)); for (i = 0; i < count; i++) { @@ -872,18 +1146,17 @@ int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, is_write ? FOLL_WRITE : 0, page, NULL, NULL); - /* - * To support virtualised environments we will have to do an - * access to the page to ensure it gets faulted into the - * hypervisor. For the moment virtualisation is not supported in - * other areas so leave the access out. - */ if (rc != 1) { status[i] = rc; result = -EFAULT; continue; } + /* Make sure partition scoped tree gets a pte */ + u = page_address(page[0]); + if (__get_user(c, u)) + result = -EFAULT; + status[i] = 0; put_page(page[0]); } @@ -892,42 +1165,127 @@ int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, } EXPORT_SYMBOL(pnv_npu2_handle_fault); -int pnv_npu2_init(struct pnv_phb *phb) +int pnv_npu2_init(struct pci_controller *hose) { unsigned int i; u64 mmio_atsd; - struct device_node *dn; - struct pci_dev *gpdev; static int npu_index; - uint64_t rc = 0; - - phb->npu.nmmu_flush = - of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush"); - for_each_child_of_node(phb->hose->dn, dn) { - gpdev = pnv_pci_get_gpu_dev(get_pci_dev(dn)); - if (gpdev) { - rc = opal_npu_map_lpar(phb->opal_id, - PCI_DEVID(gpdev->bus->number, gpdev->devfn), - 0, 0); - if (rc) - dev_err(&gpdev->dev, - "Error %lld mapping device to LPAR\n", - rc); - } - } + struct npu *npu; + int ret; + + npu = kzalloc(sizeof(*npu), GFP_KERNEL); + if (!npu) + return -ENOMEM; - for (i = 0; !of_property_read_u64_index(phb->hose->dn, "ibm,mmio-atsd", - i, &mmio_atsd); i++) - phb->npu.mmio_atsd_regs[i] = ioremap(mmio_atsd, 32); + npu->nmmu_flush = of_property_read_bool(hose->dn, "ibm,nmmu-flush"); - pr_info("NPU%lld: Found %d MMIO ATSD registers", phb->opal_id, i); - phb->npu.mmio_atsd_count = i; - phb->npu.mmio_atsd_usage = 0; + for (i = 0; i < ARRAY_SIZE(npu->mmio_atsd_regs) && + !of_property_read_u64_index(hose->dn, "ibm,mmio-atsd", + i, &mmio_atsd); i++) + npu->mmio_atsd_regs[i] = ioremap(mmio_atsd, 32); + + pr_info("NPU%d: Found %d MMIO ATSD registers", hose->global_number, i); + npu->mmio_atsd_count = i; + npu->mmio_atsd_usage = 0; npu_index++; - if (WARN_ON(npu_index >= NV_MAX_NPUS)) - return -ENOSPC; + if (WARN_ON(npu_index >= NV_MAX_NPUS)) { + ret = -ENOSPC; + goto fail_exit; + } max_npu2_index = npu_index; - phb->npu.index = npu_index; + npu->index = npu_index; + hose->npu = npu; + + return 0; + +fail_exit: + for (i = 0; i < npu->mmio_atsd_count; ++i) + iounmap(npu->mmio_atsd_regs[i]); + + kfree(npu); + + return ret; +} + +int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid, + unsigned long msr) +{ + int ret; + struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); + struct pci_controller *hose; + struct pnv_phb *nphb; + + if (!npdev) + return -ENODEV; + + hose = pci_bus_to_host(npdev->bus); + nphb = hose->private_data; + + dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=%u\n", + nphb->opal_id, lparid); + /* + * Currently we only support radix and non-zero LPCR only makes sense + * for hash tables so skiboot expects the LPCR parameter to be a zero. + */ + ret = opal_npu_map_lpar(nphb->opal_id, + PCI_DEVID(gpdev->bus->number, gpdev->devfn), lparid, + 0 /* LPCR bits */); + if (ret) { + dev_err(&gpdev->dev, "Error %d mapping device to LPAR\n", ret); + return ret; + } + + dev_dbg(&gpdev->dev, "init context opalid=%llu msr=%lx\n", + nphb->opal_id, msr); + ret = opal_npu_init_context(nphb->opal_id, 0/*__unused*/, msr, + PCI_DEVID(gpdev->bus->number, gpdev->devfn)); + if (ret < 0) + dev_err(&gpdev->dev, "Failed to init context: %d\n", ret); + else + ret = 0; return 0; } +EXPORT_SYMBOL_GPL(pnv_npu2_map_lpar_dev); + +void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr) +{ + struct pci_dev *gpdev; + + list_for_each_entry(gpdev, &gpe->pbus->devices, bus_list) + pnv_npu2_map_lpar_dev(gpdev, 0, msr); +} + +int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev) +{ + int ret; + struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); + struct pci_controller *hose; + struct pnv_phb *nphb; + + if (!npdev) + return -ENODEV; + + hose = pci_bus_to_host(npdev->bus); + nphb = hose->private_data; + + dev_dbg(&gpdev->dev, "destroy context opalid=%llu\n", + nphb->opal_id); + ret = opal_npu_destroy_context(nphb->opal_id, 0/*__unused*/, + PCI_DEVID(gpdev->bus->number, gpdev->devfn)); + if (ret < 0) { + dev_err(&gpdev->dev, "Failed to destroy context: %d\n", ret); + return ret; + } + + /* Set LPID to 0 anyway, just to be safe */ + dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=0\n", nphb->opal_id); + ret = opal_npu_map_lpar(nphb->opal_id, + PCI_DEVID(gpdev->bus->number, gpdev->devfn), 0 /*LPID*/, + 0 /* LPCR bits */); + if (ret) + dev_err(&gpdev->dev, "Error %d mapping device to LPAR\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(pnv_npu2_unmap_lpar_dev); diff --git a/arch/powerpc/platforms/powernv/opal-power.c b/arch/powerpc/platforms/powernv/opal-power.c index 58dc3308237f..89ab1da57657 100644 --- a/arch/powerpc/platforms/powernv/opal-power.c +++ b/arch/powerpc/platforms/powernv/opal-power.c @@ -138,7 +138,7 @@ static struct notifier_block opal_power_control_nb = { .priority = 0, }; -static int __init opal_power_control_init(void) +int __init opal_power_control_init(void) { int ret, supported = 0; struct device_node *np; @@ -176,4 +176,3 @@ static int __init opal_power_control_init(void) return 0; } -machine_subsys_initcall(powernv, opal_power_control_init); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index beed86f4224b..79586f127521 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -877,7 +877,7 @@ static int __init opal_init(void) consoles = of_find_node_by_path("/ibm,opal/consoles"); if (consoles) { for_each_child_of_node(consoles, np) { - if (strcmp(np->name, "serial")) + if (!of_node_name_eq(np, "serial")) continue; of_platform_device_create(np, NULL, NULL); } @@ -960,6 +960,9 @@ static int __init opal_init(void) /* Initialise OPAL sensor groups */ opal_sensor_groups_init(); + /* Initialise OPAL Power control interface */ + opal_power_control_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index fe9691040f54..697449afb3f7 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -299,7 +299,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, if (alloc_userspace_copy) { offset = 0; uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - levels, tce_table_size, &offset, + tmplevels, tce_table_size, &offset, &total_allocated_uas); if (!uas) goto free_tces_exit; @@ -368,6 +368,7 @@ void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, found = false; for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { if (table_group->tables[i] == tbl) { + iommu_tce_table_put(tbl); table_group->tables[i] = NULL; found = true; break; @@ -393,7 +394,7 @@ long pnv_pci_link_table_and_group(int node, int num, tgl->table_group = table_group; list_add_rcu(&tgl->next, &tbl->it_group_list); - table_group->tables[num] = tbl; + table_group->tables[num] = iommu_tce_table_get(tbl); return 0; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index dd807446801e..1d6406a051f1 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -190,7 +190,8 @@ static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe) unsigned int pe_num = pe->pe_number; WARN_ON(pe->pdev); - + WARN_ON(pe->npucomp); /* NPUs are not supposed to be freed */ + kfree(pe->npucomp); memset(pe, 0, sizeof(struct pnv_ioda_pe)); clear_bit(pe_num, phb->ioda.pe_alloc); } @@ -517,8 +518,6 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) phb->init_m64 = pnv_ioda1_init_m64; else phb->init_m64 = pnv_ioda2_init_m64; - phb->reserve_m64_pe = pnv_ioda_reserve_m64_pe; - phb->pick_m64_pe = pnv_ioda_pick_m64_pe; } static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no) @@ -604,8 +603,8 @@ static int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt) static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no) { struct pnv_ioda_pe *slave, *pe; - u8 fstate, state; - __be16 pcierr; + u8 fstate = 0, state; + __be16 pcierr = 0; s64 rc; /* Sanity check on PE number */ @@ -663,10 +662,6 @@ static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no) return state; } -/* Currently those 2 are only used when MSIs are enabled, this will change - * but in the meantime, we need to protect them to avoid warnings - */ -#ifdef CONFIG_PCI_MSI struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); @@ -679,7 +674,6 @@ struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) return NULL; return &phb->ioda.pe_array[pdn->pe_number]; } -#endif /* CONFIG_PCI_MSI */ static int pnv_ioda_set_one_peltv(struct pnv_phb *phb, struct pnv_ioda_pe *parent, @@ -1160,8 +1154,8 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all) pe = &phb->ioda.pe_array[phb->ioda.root_pe_idx]; /* Check if PE is determined by M64 */ - if (!pe && phb->pick_m64_pe) - pe = phb->pick_m64_pe(bus, all); + if (!pe) + pe = pnv_ioda_pick_m64_pe(bus, all); /* The PE number isn't pinned by M64 */ if (!pe) @@ -1273,19 +1267,20 @@ static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus) static void pnv_pci_ioda_setup_PEs(void) { - struct pci_controller *hose, *tmp; + struct pci_controller *hose; struct pnv_phb *phb; struct pci_bus *bus; struct pci_dev *pdev; + struct pnv_ioda_pe *pe; - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + 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) - pnv_npu2_init(phb); + WARN_ON_ONCE(pnv_npu2_init(hose)); } if (phb->type == PNV_PHB_NPU_OCAPI) { bus = hose->bus; @@ -1293,6 +1288,14 @@ static void pnv_pci_ioda_setup_PEs(void) pnv_ioda_setup_dev_PE(pdev); } } + 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_PCI_IOV @@ -1531,6 +1534,11 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev) static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe); +#ifdef CONFIG_IOMMU_API +static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe, + struct iommu_table_group *table_group, struct pci_bus *bus); + +#endif static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) { struct pci_bus *bus; @@ -1584,6 +1592,9 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) mutex_unlock(&phb->ioda.pe_list_mutex); pnv_pci_ioda2_setup_dma_pe(phb, pe); +#ifdef CONFIG_IOMMU_API + pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL); +#endif } } @@ -1923,21 +1934,16 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev) return mask; } -static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, - struct pci_bus *bus, - bool add_to_group) +static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) { struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { set_iommu_table_base(&dev->dev, pe->table_group.tables[0]); set_dma_offset(&dev->dev, pe->tce_bypass_base); - if (add_to_group) - iommu_add_device(&dev->dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) - pnv_ioda_setup_bus_dma(pe, dev->subordinate, - add_to_group); + pnv_ioda_setup_bus_dma(pe, dev->subordinate); } } @@ -2366,16 +2372,8 @@ found: pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift; iommu_init_table(tbl, phb->hose->node); - if (pe->flags & PNV_IODA_PE_DEV) { - /* - * Setting table base here only for carrying iommu_group - * further down to let iommu_add_device() do the job. - * pnv_pci_ioda_dma_dev_setup will override it later anyway. - */ - set_iommu_table_base(&pe->pdev->dev, tbl); - iommu_add_device(&pe->pdev->dev); - } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) - pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) + pnv_ioda_setup_bus_dma(pe, pe->pbus); return; fail: @@ -2527,14 +2525,6 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) if (!pnv_iommu_bypass_disabled) pnv_pci_ioda2_set_bypass(pe, true); - /* - * Setting table base here only for carrying iommu_group - * further down to let iommu_add_device() do the job. - * pnv_pci_ioda_dma_dev_setup will override it later anyway. - */ - if (pe->flags & PNV_IODA_PE_DEV) - set_iommu_table_base(&pe->pdev->dev, tbl); - return 0; } @@ -2565,7 +2555,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, #endif #ifdef CONFIG_IOMMU_API -static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, +unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, __u64 window_size, __u32 levels) { unsigned long bytes = 0; @@ -2616,7 +2606,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) pnv_pci_ioda2_set_bypass(pe, false); pnv_pci_ioda2_unset_window(&pe->table_group, 0); if (pe->pbus) - pnv_ioda_setup_bus_dma(pe, pe->pbus, false); + pnv_ioda_setup_bus_dma(pe, pe->pbus); iommu_tce_table_put(tbl); } @@ -2627,7 +2617,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) pnv_pci_ioda2_setup_default_config(pe); if (pe->pbus) - pnv_ioda_setup_bus_dma(pe, pe->pbus, false); + pnv_ioda_setup_bus_dma(pe, pe->pbus); } static struct iommu_table_group_ops pnv_pci_ioda2_ops = { @@ -2639,131 +2629,100 @@ static struct iommu_table_group_ops pnv_pci_ioda2_ops = { .release_ownership = pnv_ioda2_release_ownership, }; -static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque) +static void pnv_ioda_setup_bus_iommu_group_add_devices(struct pnv_ioda_pe *pe, + struct iommu_table_group *table_group, + struct pci_bus *bus) { - 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_NVLINK) - return 0; + struct pci_dev *dev; - *ptmppe = &phb->ioda.pe_array[pdn->pe_number]; + list_for_each_entry(dev, &bus->devices, bus_list) { + iommu_add_device(table_group, &dev->dev); - return 1; + if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) + pnv_ioda_setup_bus_iommu_group_add_devices(pe, + table_group, dev->subordinate); + } } -/* - * 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) +static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe, + struct iommu_table_group *table_group, struct pci_bus *bus) { - 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); + if (pe->flags & PNV_IODA_PE_DEV) + iommu_add_device(table_group, &pe->pdev->dev); - return npe; + if ((pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) || bus) + pnv_ioda_setup_bus_iommu_group_add_devices(pe, table_group, + bus); } -static long pnv_pci_ioda2_npu_set_window(struct iommu_table_group *table_group, - int num, struct iommu_table *tbl) -{ - struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group); - int num2 = (num == 0) ? 1 : 0; - long ret = pnv_pci_ioda2_set_window(table_group, num, tbl); - - if (ret) - return ret; - - if (table_group->tables[num2]) - pnv_npu_unset_window(npe, num2); - - ret = pnv_npu_set_window(npe, num, tbl); - if (ret) { - pnv_pci_ioda2_unset_window(table_group, num); - if (table_group->tables[num2]) - pnv_npu_set_window(npe, num2, - table_group->tables[num2]); - } - - return ret; -} +static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb); -static long pnv_pci_ioda2_npu_unset_window( - struct iommu_table_group *table_group, - int num) +static void pnv_pci_ioda_setup_iommu_api(void) { - struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group); - int num2 = (num == 0) ? 1 : 0; - long ret = pnv_pci_ioda2_unset_window(table_group, num); - - if (ret) - return ret; - - if (!npe->table_group.tables[num]) - return 0; - - ret = pnv_npu_unset_window(npe, num); - if (ret) - return ret; - - if (table_group->tables[num2]) - ret = pnv_npu_set_window(npe, num2, table_group->tables[num2]); - - return ret; -} + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; -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. + * There are 4 types of PEs: + * - PNV_IODA_PE_BUS: a downstream port with an adapter, + * created from pnv_pci_setup_bridge(); + * - PNV_IODA_PE_BUS_ALL: a PCI-PCIX bridge with devices behind it, + * created from pnv_pci_setup_bridge(); + * - PNV_IODA_PE_VF: a SRIOV virtual function, + * created from pnv_pcibios_sriov_enable(); + * - PNV_IODA_PE_DEV: an NPU or OCAPI device, + * created from pnv_pci_ioda_fixup(). + * + * Normally a PE is represented by an IOMMU group, however for + * devices with side channels the groups need to be more strict. */ - pnv_npu_take_ownership(gpe_table_group_to_npe(table_group)); - pnv_ioda2_take_ownership(table_group); -} + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; -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_userspace, - .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, -}; + if (phb->type == PNV_PHB_NPU_NVLINK) + continue; -static void pnv_pci_ioda_setup_iommu_api(void) -{ - struct pci_controller *hose, *tmp; - struct pnv_phb *phb; - struct pnv_ioda_pe *pe, *gpe; + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + struct iommu_table_group *table_group; + + table_group = pnv_try_setup_npu_table_group(pe); + if (!table_group) { + if (!pnv_pci_ioda_pe_dma_weight(pe)) + continue; + + table_group = &pe->table_group; + iommu_register_group(&pe->table_group, + pe->phb->hose->global_number, + pe->pe_number); + } + pnv_ioda_setup_bus_iommu_group(pe, table_group, + pe->pbus); + } + } /* * 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) { + list_for_each_entry(hose, &hose_list, list_node) { + unsigned long pgsizes; + phb = hose->private_data; if (phb->type != PNV_PHB_NPU_NVLINK) continue; + pgsizes = pnv_ioda_parse_tce_sizes(phb); 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; + /* + * IODA2 bridges get this set up from + * pci_controller_ops::setup_bridge but NPU bridges + * do not have this hook defined so we do it here. + */ + pe->table_group.pgsizes = pgsizes; + pnv_npu_compound_attach(pe); } } } @@ -2810,9 +2769,6 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, /* TVE #1 is selected by PCI address bit 59 */ pe->tce_bypass_base = 1ull << 59; - iommu_register_group(&pe->table_group, phb->hose->global_number, - pe->pe_number); - /* The PE will reserve all possible 32-bits space */ pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n", phb->ioda.m32_pci_base); @@ -2833,10 +2789,9 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, return; if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) - pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + pnv_ioda_setup_bus_dma(pe, pe->pbus); } -#ifdef CONFIG_PCI_MSI int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq) { struct pnv_phb *phb = container_of(chip, struct pnv_phb, @@ -2982,9 +2937,6 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", count, phb->msi_base); } -#else -static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } -#endif /* CONFIG_PCI_MSI */ #ifdef CONFIG_PCI_IOV static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) @@ -3402,8 +3354,7 @@ static void pnv_pci_setup_bridge(struct pci_bus *bus, unsigned long type) return; /* Reserve PEs according to used M64 resources */ - if (phb->reserve_m64_pe) - phb->reserve_m64_pe(bus, NULL, all); + pnv_ioda_reserve_m64_pe(bus, NULL, all); /* * Assign PE. We might run here because of partial hotplug. @@ -3687,6 +3638,15 @@ 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; @@ -3698,10 +3658,8 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, .dma_bus_setup = pnv_pci_dma_bus_setup, -#ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, -#endif .enable_device_hook = pnv_pci_enable_device_hook, .release_device = pnv_pci_release_device, .window_alignment = pnv_pci_window_alignment, @@ -3722,15 +3680,14 @@ static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask) static const struct pci_controller_ops pnv_npu_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, -#ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, -#endif .enable_device_hook = pnv_pci_enable_device_hook, .window_alignment = pnv_pci_window_alignment, .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 = { diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 13aef2323bbc..45fb70b4bfa7 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -160,7 +160,6 @@ exit: } EXPORT_SYMBOL_GPL(pnv_pci_set_power_state); -#ifdef CONFIG_PCI_MSI int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); @@ -229,7 +228,6 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev) msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1); } } -#endif /* CONFIG_PCI_MSI */ /* Nicely print the contents of the PE State Tables (PEST). */ static void pnv_pci_dump_pest(__be64 pestA[], __be64 pestB[], int pest_size) @@ -602,8 +600,8 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) static void pnv_pci_config_check_eeh(struct pci_dn *pdn) { struct pnv_phb *phb = pdn->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; unsigned int pe_no; s64 rc; @@ -1127,4 +1125,45 @@ void __init pnv_pci_init(void) set_pci_dma_ops(&dma_iommu_ops); } -machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); +static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + struct pci_dev *pdev; + struct pci_dn *pdn; + struct pnv_ioda_pe *pe; + struct pci_controller *hose; + struct pnv_phb *phb; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + pdev = to_pci_dev(dev); + pdn = pci_get_pdn(pdev); + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + + WARN_ON_ONCE(!phb); + if (!pdn || pdn->pe_number == IODA_INVALID_PE || !phb) + return 0; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + iommu_add_device(&pe->table_group, dev); + return 0; + case BUS_NOTIFY_DEL_DEVICE: + iommu_del_device(dev); + return 0; + default: + return 0; + } +} + +static struct notifier_block pnv_tce_iommu_bus_nb = { + .notifier_call = pnv_tce_iommu_bus_notifier, +}; + +static int __init pnv_tce_iommu_bus_notifier_init(void) +{ + bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); + return 0; +} +machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 8b37b28e3831..8e36da379252 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -8,9 +8,6 @@ struct pci_dn; -/* Maximum possible number of ATSD MMIO registers per NPU */ -#define NV_NMMU_ATSD_REGS 8 - enum pnv_phb_type { PNV_PHB_IODA1 = 0, PNV_PHB_IODA2 = 1, @@ -65,6 +62,7 @@ struct pnv_ioda_pe { /* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */ struct iommu_table_group table_group; + struct npu_comp *npucomp; /* 64-bit TCE bypass region */ bool tce_bypass_enabled; @@ -106,20 +104,14 @@ struct pnv_phb { struct dentry *dbgfs; #endif -#ifdef CONFIG_PCI_MSI unsigned int msi_base; unsigned int msi32_support; struct msi_bitmap msi_bmp; -#endif int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, unsigned int hwirq, unsigned int virq, unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); - void (*fixup_phb)(struct pci_controller *hose); int (*init_m64)(struct pnv_phb *phb); - void (*reserve_m64_pe)(struct pci_bus *bus, - unsigned long *pe_bitmap, bool all); - struct pnv_ioda_pe *(*pick_m64_pe)(struct pci_bus *bus, bool all); int (*get_pe_state)(struct pnv_phb *phb, int pe_no); void (*freeze_pe)(struct pnv_phb *phb, int pe_no); int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt); @@ -180,19 +172,6 @@ struct pnv_phb { unsigned int diag_data_size; u8 *diag_data; - /* Nvlink2 data */ - struct npu { - int index; - __be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS]; - unsigned int mmio_atsd_count; - - /* Bitmask for MMIO register usage */ - unsigned long mmio_atsd_usage; - - /* Do we need to explicitly flush the nest mmu? */ - bool nmmu_flush; - } npu; - int p2p_target_count; }; @@ -210,6 +189,7 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_init_npu_phb(struct device_node *np); extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np); +extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); @@ -220,6 +200,8 @@ extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev); extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq); extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); +extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, + __u64 window_size, __u32 levels); extern int pnv_eeh_post_init(void); extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, @@ -235,12 +217,10 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass); extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm); extern struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe); -extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num, - struct iommu_table *tbl); -extern long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num); -extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe); -extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe); -extern int pnv_npu2_init(struct pnv_phb *phb); +extern struct iommu_table_group *pnv_try_setup_npu_table_group( + struct pnv_ioda_pe *pe); +extern struct iommu_table_group *pnv_npu_compound_attach( + struct pnv_ioda_pe *pe); /* pci-ioda-tce.c */ #define POWERNV_IOMMU_DEFAULT_LEVELS 1 diff --git a/arch/powerpc/platforms/powernv/vas-debug.c b/arch/powerpc/platforms/powernv/vas-debug.c index 4f7276ebdf9c..4d3929fbc08f 100644 --- a/arch/powerpc/platforms/powernv/vas-debug.c +++ b/arch/powerpc/platforms/powernv/vas-debug.c @@ -30,7 +30,7 @@ static char *cop_to_str(int cop) } } -static int info_dbg_show(struct seq_file *s, void *private) +static int info_show(struct seq_file *s, void *private) { struct vas_window *window = s->private; @@ -49,17 +49,7 @@ unlock: return 0; } -static int info_dbg_open(struct inode *inode, struct file *file) -{ - return single_open(file, info_dbg_show, inode->i_private); -} - -static const struct file_operations info_fops = { - .open = info_dbg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(info); static inline void print_reg(struct seq_file *s, struct vas_window *win, char *name, u32 reg) @@ -67,7 +57,7 @@ static inline void print_reg(struct seq_file *s, struct vas_window *win, seq_printf(s, "0x%016llx %s\n", read_hvwc_reg(win, name, reg), name); } -static int hvwc_dbg_show(struct seq_file *s, void *private) +static int hvwc_show(struct seq_file *s, void *private) { struct vas_window *window = s->private; @@ -115,17 +105,7 @@ unlock: return 0; } -static int hvwc_dbg_open(struct inode *inode, struct file *file) -{ - return single_open(file, hvwc_dbg_show, inode->i_private); -} - -static const struct file_operations hvwc_fops = { - .open = hvwc_dbg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(hvwc); void vas_window_free_dbgdir(struct vas_window *window) { |