diff options
Diffstat (limited to 'hw/pci-host/pnv_phb4.c')
| -rw-r--r-- | hw/pci-host/pnv_phb4.c | 778 |
1 files changed, 579 insertions, 199 deletions
diff --git a/hw/pci-host/pnv_phb4.c b/hw/pci-host/pnv_phb4.c index 5c375a9f28..075499d36d 100644 --- a/hw/pci-host/pnv_phb4.c +++ b/hw/pci-host/pnv_phb4.c @@ -10,7 +10,6 @@ #include "qemu/log.h" #include "qapi/visitor.h" #include "qapi/error.h" -#include "qemu-common.h" #include "monitor/monitor.h" #include "target/ppc/cpu.h" #include "hw/pci-host/pnv_phb4_regs.h" @@ -28,25 +27,13 @@ qemu_log_mask(LOG_GUEST_ERROR, "phb4[%d:%d]: " fmt "\n", \ (phb)->chip_id, (phb)->phb_id, ## __VA_ARGS__) -/* - * QEMU version of the GETFIELD/SETFIELD macros - * - * These are common with the PnvXive model. - */ -static inline uint64_t GETFIELD(uint64_t mask, uint64_t word) -{ - return (word & mask) >> ctz64(mask); -} - -static inline uint64_t SETFIELD(uint64_t mask, uint64_t word, - uint64_t value) -{ - return (word & ~mask) | ((value << ctz64(mask)) & mask); -} +#define phb_pec_error(pec, fmt, ...) \ + qemu_log_mask(LOG_GUEST_ERROR, "phb4_pec[%d:%d]: " fmt "\n", \ + (pec)->chip_id, (pec)->index, ## __VA_ARGS__) static PCIDevice *pnv_phb4_find_cfg_dev(PnvPHB4 *phb) { - PCIHostState *pci = PCI_HOST_BRIDGE(phb); + PCIHostState *pci = PCI_HOST_BRIDGE(phb->phb_base); uint64_t addr = phb->regs[PHB_CONFIG_ADDRESS >> 3]; uint8_t bus, devfn; @@ -142,16 +129,19 @@ static uint64_t pnv_phb4_config_read(PnvPHB4 *phb, unsigned off, static void pnv_phb4_rc_config_write(PnvPHB4 *phb, unsigned off, unsigned size, uint64_t val) { - PCIHostState *pci = PCI_HOST_BRIDGE(phb); + PCIHostState *pci = PCI_HOST_BRIDGE(phb->phb_base); PCIDevice *pdev; if (size != 4) { - phb_error(phb, "rc_config_write invalid size %d\n", size); + phb_error(phb, "rc_config_write invalid size %d", size); return; } pdev = pci_find_device(pci->bus, 0, 0); - assert(pdev); + if (!pdev) { + phb_error(phb, "rc_config_write device not found"); + return; + } pci_host_config_write_common(pdev, off, PHB_RC_CONFIG_SIZE, bswap32(val), 4); @@ -160,17 +150,20 @@ static void pnv_phb4_rc_config_write(PnvPHB4 *phb, unsigned off, static uint64_t pnv_phb4_rc_config_read(PnvPHB4 *phb, unsigned off, unsigned size) { - PCIHostState *pci = PCI_HOST_BRIDGE(phb); + PCIHostState *pci = PCI_HOST_BRIDGE(phb->phb_base); PCIDevice *pdev; uint64_t val; if (size != 4) { - phb_error(phb, "rc_config_read invalid size %d\n", size); + phb_error(phb, "rc_config_read invalid size %d", size); return ~0ull; } pdev = pci_find_device(pci->bus, 0, 0); - assert(pdev); + if (!pdev) { + phb_error(phb, "rc_config_read device not found"); + return ~0ull; + } val = pci_host_config_read_common(pdev, off, PHB_RC_CONFIG_SIZE, 4); return bswap32(val); @@ -214,19 +207,19 @@ static void pnv_phb4_check_mbt(PnvPHB4 *phb, uint32_t index) start = base | (phb->regs[PHB_M64_UPPER_BITS >> 3]); } - /* TODO: Figure out how to implemet/decode AOMASK */ + /* TODO: Figure out how to implement/decode AOMASK */ /* Check if it matches an enabled MMIO region in the PEC stack */ - if (memory_region_is_mapped(&phb->stack->mmbar0) && - base >= phb->stack->mmio0_base && - (base + size) <= (phb->stack->mmio0_base + phb->stack->mmio0_size)) { - parent = &phb->stack->mmbar0; - base -= phb->stack->mmio0_base; - } else if (memory_region_is_mapped(&phb->stack->mmbar1) && - base >= phb->stack->mmio1_base && - (base + size) <= (phb->stack->mmio1_base + phb->stack->mmio1_size)) { - parent = &phb->stack->mmbar1; - base -= phb->stack->mmio1_base; + if (memory_region_is_mapped(&phb->mmbar0) && + base >= phb->mmio0_base && + (base + size) <= (phb->mmio0_base + phb->mmio0_size)) { + parent = &phb->mmbar0; + base -= phb->mmio0_base; + } else if (memory_region_is_mapped(&phb->mmbar1) && + base >= phb->mmio1_base && + (base + size) <= (phb->mmio1_base + phb->mmio1_size)) { + parent = &phb->mmbar1; + base -= phb->mmio1_base; } else { phb_error(phb, "PHB MBAR %d out of parent bounds", index); return; @@ -398,7 +391,7 @@ static void pnv_phb4_ioda_write(PnvPHB4 *phb, uint64_t val) case IODA3_TBL_MBT: *tptr = val; - /* Copy accross the valid bit to the other half */ + /* Copy across the valid bit to the other half */ phb->ioda_MBT[idx ^ 1] &= 0x7fffffffffffffffull; phb->ioda_MBT[idx ^ 1] |= 0x8000000000000000ull & val; @@ -475,6 +468,15 @@ static void pnv_phb4_update_xsrc(PnvPHB4 *phb) flags = 0; } + /* + * When the PQ disable configuration bit is set, the check on the + * PQ state bits is disabled on the PHB side (for MSI only) and it + * is performed on the IC side instead. + */ + if (phb->regs[PHB_CTRLR >> 3] & PHB_CTRLR_IRQ_PQ_DISABLE) { + flags |= XIVE_SRC_PQ_DISABLE; + } + phb->xsrc.esb_shift = shift; phb->xsrc.esb_flags = flags; @@ -662,7 +664,7 @@ static uint64_t pnv_phb4_reg_read(void *opaque, hwaddr off, unsigned size) switch (off) { case PHB_VERSION: - return phb->version; + return PNV_PHB4_PEC_GET_CLASS(phb->pec)->version; /* Read-only */ case PHB_PHB4_GEN_CAP: @@ -847,6 +849,315 @@ const MemoryRegionOps pnv_phb4_xscom_ops = { .endianness = DEVICE_BIG_ENDIAN, }; +static uint64_t pnv_pec_stk_nest_xscom_read(void *opaque, hwaddr addr, + unsigned size) +{ + PnvPHB4 *phb = PNV_PHB4(opaque); + uint32_t reg = addr >> 3; + + /* All registers are read-able */ + return phb->nest_regs[reg]; +} + +/* + * Return the 'stack_no' of a PHB4. 'stack_no' is the order + * the PHB4 occupies in the PEC. This is the reverse of what + * pnv_phb4_pec_get_phb_id() does. + * + * E.g. a phb with phb_id = 4 and pec->index = 1 (PEC1) will + * be the second phb (stack_no = 1) of the PEC. + */ +static int pnv_phb4_get_phb_stack_no(PnvPHB4 *phb) +{ + PnvPhb4PecState *pec = phb->pec; + PnvPhb4PecClass *pecc = PNV_PHB4_PEC_GET_CLASS(pec); + int index = pec->index; + int stack_no = phb->phb_id; + + while (index--) { + stack_no -= pecc->num_phbs[index]; + } + + return stack_no; +} + +static void pnv_phb4_update_regions(PnvPHB4 *phb) +{ + /* Unmap first always */ + if (memory_region_is_mapped(&phb->mr_regs)) { + memory_region_del_subregion(&phb->phbbar, &phb->mr_regs); + } + if (memory_region_is_mapped(&phb->xsrc.esb_mmio)) { + memory_region_del_subregion(&phb->intbar, &phb->xsrc.esb_mmio); + } + + /* Map registers if enabled */ + if (memory_region_is_mapped(&phb->phbbar)) { + memory_region_add_subregion(&phb->phbbar, 0, &phb->mr_regs); + } + + /* Map ESB if enabled */ + if (memory_region_is_mapped(&phb->intbar)) { + memory_region_add_subregion(&phb->intbar, 0, &phb->xsrc.esb_mmio); + } + + /* Check/update m32 */ + pnv_phb4_check_all_mbt(phb); +} + +static void pnv_pec_phb_update_map(PnvPHB4 *phb) +{ + PnvPhb4PecState *pec = phb->pec; + MemoryRegion *sysmem = get_system_memory(); + uint64_t bar_en = phb->nest_regs[PEC_NEST_STK_BAR_EN]; + int stack_no = pnv_phb4_get_phb_stack_no(phb); + uint64_t bar, mask, size; + char name[64]; + + /* + * NOTE: This will really not work well if those are remapped + * after the PHB has created its sub regions. We could do better + * if we had a way to resize regions but we don't really care + * that much in practice as the stuff below really only happens + * once early during boot + */ + + /* Handle unmaps */ + if (memory_region_is_mapped(&phb->mmbar0) && + !(bar_en & PEC_NEST_STK_BAR_EN_MMIO0)) { + memory_region_del_subregion(sysmem, &phb->mmbar0); + } + if (memory_region_is_mapped(&phb->mmbar1) && + !(bar_en & PEC_NEST_STK_BAR_EN_MMIO1)) { + memory_region_del_subregion(sysmem, &phb->mmbar1); + } + if (memory_region_is_mapped(&phb->phbbar) && + !(bar_en & PEC_NEST_STK_BAR_EN_PHB)) { + memory_region_del_subregion(sysmem, &phb->phbbar); + } + if (memory_region_is_mapped(&phb->intbar) && + !(bar_en & PEC_NEST_STK_BAR_EN_INT)) { + memory_region_del_subregion(sysmem, &phb->intbar); + } + + /* Update PHB */ + pnv_phb4_update_regions(phb); + + /* Handle maps */ + if (!memory_region_is_mapped(&phb->mmbar0) && + (bar_en & PEC_NEST_STK_BAR_EN_MMIO0)) { + bar = phb->nest_regs[PEC_NEST_STK_MMIO_BAR0] >> 8; + mask = phb->nest_regs[PEC_NEST_STK_MMIO_BAR0_MASK]; + size = ((~mask) >> 8) + 1; + snprintf(name, sizeof(name), "pec-%d.%d-phb-%d-mmio0", + pec->chip_id, pec->index, stack_no); + memory_region_init(&phb->mmbar0, OBJECT(phb), name, size); + memory_region_add_subregion(sysmem, bar, &phb->mmbar0); + phb->mmio0_base = bar; + phb->mmio0_size = size; + } + if (!memory_region_is_mapped(&phb->mmbar1) && + (bar_en & PEC_NEST_STK_BAR_EN_MMIO1)) { + bar = phb->nest_regs[PEC_NEST_STK_MMIO_BAR1] >> 8; + mask = phb->nest_regs[PEC_NEST_STK_MMIO_BAR1_MASK]; + size = ((~mask) >> 8) + 1; + snprintf(name, sizeof(name), "pec-%d.%d-phb-%d-mmio1", + pec->chip_id, pec->index, stack_no); + memory_region_init(&phb->mmbar1, OBJECT(phb), name, size); + memory_region_add_subregion(sysmem, bar, &phb->mmbar1); + phb->mmio1_base = bar; + phb->mmio1_size = size; + } + if (!memory_region_is_mapped(&phb->phbbar) && + (bar_en & PEC_NEST_STK_BAR_EN_PHB)) { + bar = phb->nest_regs[PEC_NEST_STK_PHB_REGS_BAR] >> 8; + size = PNV_PHB4_NUM_REGS << 3; + snprintf(name, sizeof(name), "pec-%d.%d-phb-%d", + pec->chip_id, pec->index, stack_no); + memory_region_init(&phb->phbbar, OBJECT(phb), name, size); + memory_region_add_subregion(sysmem, bar, &phb->phbbar); + } + if (!memory_region_is_mapped(&phb->intbar) && + (bar_en & PEC_NEST_STK_BAR_EN_INT)) { + bar = phb->nest_regs[PEC_NEST_STK_INT_BAR] >> 8; + size = PNV_PHB4_MAX_INTs << 16; + snprintf(name, sizeof(name), "pec-%d.%d-phb-%d-int", + phb->pec->chip_id, phb->pec->index, stack_no); + memory_region_init(&phb->intbar, OBJECT(phb), name, size); + memory_region_add_subregion(sysmem, bar, &phb->intbar); + } + + /* Update PHB */ + pnv_phb4_update_regions(phb); +} + +static void pnv_pec_stk_nest_xscom_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + PnvPHB4 *phb = PNV_PHB4(opaque); + PnvPhb4PecState *pec = phb->pec; + uint32_t reg = addr >> 3; + + switch (reg) { + case PEC_NEST_STK_PCI_NEST_FIR: + phb->nest_regs[PEC_NEST_STK_PCI_NEST_FIR] = val & PPC_BITMASK(0, 27); + break; + case PEC_NEST_STK_PCI_NEST_FIR_CLR: + phb->nest_regs[PEC_NEST_STK_PCI_NEST_FIR] &= val; + break; + case PEC_NEST_STK_PCI_NEST_FIR_SET: + phb->nest_regs[PEC_NEST_STK_PCI_NEST_FIR] |= val; + break; + case PEC_NEST_STK_PCI_NEST_FIR_MSK: + phb->nest_regs[PEC_NEST_STK_PCI_NEST_FIR_MSK] = val & + PPC_BITMASK(0, 27); + break; + case PEC_NEST_STK_PCI_NEST_FIR_MSKC: + phb->nest_regs[PEC_NEST_STK_PCI_NEST_FIR_MSK] &= val; + break; + case PEC_NEST_STK_PCI_NEST_FIR_MSKS: + phb->nest_regs[PEC_NEST_STK_PCI_NEST_FIR_MSK] |= val; + break; + case PEC_NEST_STK_PCI_NEST_FIR_ACT0: + case PEC_NEST_STK_PCI_NEST_FIR_ACT1: + phb->nest_regs[reg] = val & PPC_BITMASK(0, 27); + break; + case PEC_NEST_STK_PCI_NEST_FIR_WOF: + phb->nest_regs[reg] = 0; + break; + case PEC_NEST_STK_ERR_REPORT_0: + case PEC_NEST_STK_ERR_REPORT_1: + case PEC_NEST_STK_PBCQ_GNRL_STATUS: + /* Flag error ? */ + break; + case PEC_NEST_STK_PBCQ_MODE: + phb->nest_regs[reg] = val & PPC_BITMASK(0, 7); + break; + case PEC_NEST_STK_MMIO_BAR0: + case PEC_NEST_STK_MMIO_BAR0_MASK: + case PEC_NEST_STK_MMIO_BAR1: + case PEC_NEST_STK_MMIO_BAR1_MASK: + if (phb->nest_regs[PEC_NEST_STK_BAR_EN] & + (PEC_NEST_STK_BAR_EN_MMIO0 | + PEC_NEST_STK_BAR_EN_MMIO1)) { + phb_pec_error(pec, "Changing enabled BAR unsupported"); + } + phb->nest_regs[reg] = val & PPC_BITMASK(0, 39); + break; + case PEC_NEST_STK_PHB_REGS_BAR: + if (phb->nest_regs[PEC_NEST_STK_BAR_EN] & PEC_NEST_STK_BAR_EN_PHB) { + phb_pec_error(pec, "Changing enabled BAR unsupported"); + } + phb->nest_regs[reg] = val & PPC_BITMASK(0, 41); + break; + case PEC_NEST_STK_INT_BAR: + if (phb->nest_regs[PEC_NEST_STK_BAR_EN] & PEC_NEST_STK_BAR_EN_INT) { + phb_pec_error(pec, "Changing enabled BAR unsupported"); + } + phb->nest_regs[reg] = val & PPC_BITMASK(0, 27); + break; + case PEC_NEST_STK_BAR_EN: + phb->nest_regs[reg] = val & PPC_BITMASK(0, 3); + pnv_pec_phb_update_map(phb); + break; + case PEC_NEST_STK_DATA_FRZ_TYPE: + /* Not used for now */ + phb->nest_regs[reg] = val & PPC_BITMASK(0, 27); + break; + case PEC_NEST_STK_PBCQ_SPARSE_PAGE: + phb->nest_regs[reg] = val & PPC_BITMASK(3, 5); + break; + case PEC_NEST_STK_PBCQ_CACHE_INJ: + phb->nest_regs[reg] = val & PPC_BITMASK(0, 7); + break; + default: + qemu_log_mask(LOG_UNIMP, "phb4_pec: nest_xscom_write 0x%"HWADDR_PRIx + "=%"PRIx64"\n", addr, val); + } +} + +static const MemoryRegionOps pnv_pec_stk_nest_xscom_ops = { + .read = pnv_pec_stk_nest_xscom_read, + .write = pnv_pec_stk_nest_xscom_write, + .valid.min_access_size = 8, + .valid.max_access_size = 8, + .impl.min_access_size = 8, + .impl.max_access_size = 8, + .endianness = DEVICE_BIG_ENDIAN, +}; + +static uint64_t pnv_pec_stk_pci_xscom_read(void *opaque, hwaddr addr, + unsigned size) +{ + PnvPHB4 *phb = PNV_PHB4(opaque); + uint32_t reg = addr >> 3; + + /* All registers are read-able */ + return phb->pci_regs[reg]; +} + +static void pnv_pec_stk_pci_xscom_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + PnvPHB4 *phb = PNV_PHB4(opaque); + uint32_t reg = addr >> 3; + switch (reg) { + case PEC_PCI_STK_PCI_FIR: + phb->pci_regs[reg] = val & PPC_BITMASK(0, 5); + break; + case PEC_PCI_STK_PCI_FIR_CLR: + phb->pci_regs[PEC_PCI_STK_PCI_FIR] &= val; + break; + case PEC_PCI_STK_PCI_FIR_SET: + phb->pci_regs[PEC_PCI_STK_PCI_FIR] |= val; + break; + case PEC_PCI_STK_PCI_FIR_MSK: + phb->pci_regs[reg] = val & PPC_BITMASK(0, 5); + break; + case PEC_PCI_STK_PCI_FIR_MSKC: + phb->pci_regs[PEC_PCI_STK_PCI_FIR_MSK] &= val; + break; + case PEC_PCI_STK_PCI_FIR_MSKS: + phb->pci_regs[PEC_PCI_STK_PCI_FIR_MSK] |= val; + break; + case PEC_PCI_STK_PCI_FIR_ACT0: + case PEC_PCI_STK_PCI_FIR_ACT1: + phb->pci_regs[reg] = val & PPC_BITMASK(0, 5); + break; + case PEC_PCI_STK_PCI_FIR_WOF: + phb->pci_regs[reg] = 0; + break; + case PEC_PCI_STK_ETU_RESET: + phb->pci_regs[reg] = val & PPC_BIT(0); + /* TODO: Implement reset */ + break; + case PEC_PCI_STK_PBAIB_ERR_REPORT: + break; + case PEC_PCI_STK_PBAIB_TX_CMD_CRED: + phb->pci_regs[reg] = val & + ((PPC_BITMASK(0, 2) | PPC_BITMASK(10, 18) + | PPC_BITMASK(26, 34) | PPC_BITMASK(41, 50) + | PPC_BITMASK(58, 63))); + break; + case PEC_PCI_STK_PBAIB_TX_DAT_CRED: + phb->pci_regs[reg] = val & (PPC_BITMASK(33, 34) | PPC_BITMASK(44, 47)); + break; + default: + qemu_log_mask(LOG_UNIMP, "phb4_pec_stk: pci_xscom_write 0x%"HWADDR_PRIx + "=%"PRIx64"\n", addr, val); + } +} + +static const MemoryRegionOps pnv_pec_stk_pci_xscom_ops = { + .read = pnv_pec_stk_pci_xscom_read, + .write = pnv_pec_stk_pci_xscom_write, + .valid.min_access_size = 8, + .valid.max_access_size = 8, + .impl.min_access_size = 8, + .impl.max_access_size = 8, + .endianness = DEVICE_BIG_ENDIAN, +}; + static int pnv_phb4_map_irq(PCIDevice *pci_dev, int irq_num) { /* Check that out properly ... */ @@ -891,7 +1202,8 @@ static bool pnv_phb4_resolve_pe(PnvPhb4DMASpace *ds) bus_num = pci_bus_num(ds->bus); addr = rtt & PHB_RTT_BASE_ADDRESS_MASK; addr += 2 * PCI_BUILD_BDF(bus_num, ds->devfn); - if (dma_memory_read(&address_space_memory, addr, &rte, sizeof(rte))) { + if (dma_memory_read(&address_space_memory, addr, &rte, + sizeof(rte), MEMTXATTRS_UNSPECIFIED)) { phb_error(ds->phb, "Failed to read RTT entry at 0x%"PRIx64, addr); /* Set error bits ? fence ? ... */ return false; @@ -957,11 +1269,13 @@ static void pnv_phb4_translate_tve(PnvPhb4DMASpace *ds, hwaddr addr, /* TODO: Limit to support IO page sizes */ /* TODO: Multi-level untested */ - while ((lev--) >= 0) { + do { + lev--; + /* Grab the TCE address */ taddr = base | (((addr >> sh) & ((1ul << tbl_shift) - 1)) << 3); if (dma_memory_read(&address_space_memory, taddr, &tce, - sizeof(tce))) { + sizeof(tce), MEMTXATTRS_UNSPECIFIED)) { phb_error(ds->phb, "Failed to read TCE at 0x%"PRIx64, taddr); return; } @@ -978,21 +1292,22 @@ static void pnv_phb4_translate_tve(PnvPhb4DMASpace *ds, hwaddr addr, } sh -= tbl_shift; base = tce & ~0xfffull; - } + } while (lev >= 0); /* We exit the loop with TCE being the final TCE */ - tce_mask = ~((1ull << tce_shift) - 1); - tlb->iova = addr & tce_mask; - tlb->translated_addr = tce & tce_mask; - tlb->addr_mask = ~tce_mask; - tlb->perm = tce & 3; if ((is_write & !(tce & 2)) || ((!is_write) && !(tce & 1))) { phb_error(ds->phb, "TCE access fault at 0x%"PRIx64, taddr); phb_error(ds->phb, " xlate %"PRIx64":%c TVE=%"PRIx64, addr, is_write ? 'W' : 'R', tve); phb_error(ds->phb, " tta=%"PRIx64" lev=%d tts=%d tps=%d", tta, lev, tts, tps); + return; } + tce_mask = ~((1ull << tce_shift) - 1); + tlb->iova = addr & tce_mask; + tlb->translated_addr = tce & tce_mask; + tlb->addr_mask = ~tce_mask; + tlb->perm = tce & 3; } } @@ -1062,6 +1377,23 @@ static const TypeInfo pnv_phb4_iommu_memory_region_info = { }; /* + * Return the index/phb-id of a PHB4 that belongs to a + * pec->stacks[stack_index] stack. + */ +int pnv_phb4_pec_get_phb_id(PnvPhb4PecState *pec, int stack_index) +{ + PnvPhb4PecClass *pecc = PNV_PHB4_PEC_GET_CLASS(pec); + int index = pec->index; + int offset = 0; + + while (index--) { + offset += pecc->num_phbs[index]; + } + + return offset + stack_index; +} + +/* * MSI/MSIX memory region implementation. * The handler handles both MSI and MSIX. */ @@ -1086,7 +1418,7 @@ static void pnv_phb4_msi_write(void *opaque, hwaddr addr, return; } - /* TODO: check PE/MSI assignement */ + /* TODO: check PE/MSI assignment */ qemu_irq_pulse(phb->qirqs[src]); } @@ -1127,7 +1459,7 @@ static AddressSpace *pnv_phb4_dma_iommu(PCIBus *bus, void *opaque, int devfn) ds = pnv_phb4_dma_find(phb, bus, devfn); if (ds == NULL) { - ds = g_malloc0(sizeof(PnvPhb4DMASpace)); + ds = g_new0(PnvPhb4DMASpace, 1); ds->bus = bus; ds->devfn = devfn; ds->pe_num = PHB_INVALID_PE; @@ -1150,6 +1482,56 @@ static AddressSpace *pnv_phb4_dma_iommu(PCIBus *bus, void *opaque, int devfn) return &ds->dma_as; } +static void pnv_phb4_xscom_realize(PnvPHB4 *phb) +{ + PnvPhb4PecState *pec = phb->pec; + PnvPhb4PecClass *pecc = PNV_PHB4_PEC_GET_CLASS(pec); + int stack_no = pnv_phb4_get_phb_stack_no(phb); + uint32_t pec_nest_base; + uint32_t pec_pci_base; + char name[64]; + + assert(pec); + + /* Initialize the XSCOM regions for the stack registers */ + snprintf(name, sizeof(name), "xscom-pec-%d.%d-nest-phb-%d", + pec->chip_id, pec->index, stack_no); + pnv_xscom_region_init(&phb->nest_regs_mr, OBJECT(phb), + &pnv_pec_stk_nest_xscom_ops, phb, name, + PHB4_PEC_NEST_STK_REGS_COUNT); + + snprintf(name, sizeof(name), "xscom-pec-%d.%d-pci-phb-%d", + pec->chip_id, pec->index, stack_no); + pnv_xscom_region_init(&phb->pci_regs_mr, OBJECT(phb), + &pnv_pec_stk_pci_xscom_ops, phb, name, + PHB4_PEC_PCI_STK_REGS_COUNT); + + /* PHB pass-through */ + snprintf(name, sizeof(name), "xscom-pec-%d.%d-phb-%d", + pec->chip_id, pec->index, stack_no); + pnv_xscom_region_init(&phb->phb_regs_mr, OBJECT(phb), + &pnv_phb4_xscom_ops, phb, name, 0x40); + + pec_nest_base = pecc->xscom_nest_base(pec); + pec_pci_base = pecc->xscom_pci_base(pec); + + /* Populate the XSCOM address space. */ + pnv_xscom_add_subregion(pec->chip, + pec_nest_base + 0x40 * (stack_no + 1), + &phb->nest_regs_mr); + pnv_xscom_add_subregion(pec->chip, + pec_pci_base + 0x40 * (stack_no + 1), + &phb->pci_regs_mr); + pnv_xscom_add_subregion(pec->chip, + pec_pci_base + PNV9_XSCOM_PEC_PCI_STK0 + + 0x40 * stack_no, + &phb->phb_regs_mr); +} + +static PCIIOMMUOps pnv_phb4_iommu_ops = { + .get_address_space = pnv_phb4_dma_iommu, +}; + static void pnv_phb4_instance_init(Object *obj) { PnvPHB4 *phb = PNV_PHB4(obj); @@ -1158,39 +1540,18 @@ static void pnv_phb4_instance_init(Object *obj) /* XIVE interrupt source object */ object_initialize_child(obj, "source", &phb->xsrc, TYPE_XIVE_SOURCE); - - /* Root Port */ - object_initialize_child(obj, "root", &phb->root, TYPE_PNV_PHB4_ROOT_PORT); - - qdev_prop_set_int32(DEVICE(&phb->root), "addr", PCI_DEVFN(0, 0)); - qdev_prop_set_bit(DEVICE(&phb->root), "multifunction", false); } -static void pnv_phb4_realize(DeviceState *dev, Error **errp) +void pnv_phb4_bus_init(DeviceState *dev, PnvPHB4 *phb) { - PnvPHB4 *phb = PNV_PHB4(dev); PCIHostState *pci = PCI_HOST_BRIDGE(dev); - XiveSource *xsrc = &phb->xsrc; - int nr_irqs; char name[32]; - assert(phb->stack); - - /* Set the "big_phb" flag */ - phb->big_phb = phb->phb_id == 0 || phb->phb_id == 3; - - /* Controller Registers */ - snprintf(name, sizeof(name), "phb4-%d.%d-regs", phb->chip_id, - phb->phb_id); - memory_region_init_io(&phb->mr_regs, OBJECT(phb), &pnv_phb4_reg_ops, phb, - name, 0x2000); - /* * PHB4 doesn't support IO space. However, qemu gets very upset if * we don't have an IO region to anchor IO BARs onto so we just * initialize one which we never hook up to anything */ - snprintf(name, sizeof(name), "phb4-%d.%d-pci-io", phb->chip_id, phb->phb_id); memory_region_init(&phb->pci_io, OBJECT(phb), name, 0x10000); @@ -1200,16 +1561,35 @@ static void pnv_phb4_realize(DeviceState *dev, Error **errp) memory_region_init(&phb->pci_mmio, OBJECT(phb), name, PCI_MMIO_TOTAL_SIZE); - pci->bus = pci_register_root_bus(dev, "root-bus", + pci->bus = pci_register_root_bus(dev, dev->id ? dev->id : NULL, pnv_phb4_set_irq, pnv_phb4_map_irq, phb, &phb->pci_mmio, &phb->pci_io, 0, 4, TYPE_PNV_PHB4_ROOT_BUS); - pci_setup_iommu(pci->bus, pnv_phb4_dma_iommu, phb); - /* Add a single Root port */ - qdev_prop_set_uint8(DEVICE(&phb->root), "chassis", phb->chip_id); - qdev_prop_set_uint16(DEVICE(&phb->root), "slot", phb->phb_id); - qdev_realize(DEVICE(&phb->root), BUS(pci->bus), &error_fatal); + object_property_set_int(OBJECT(pci->bus), "phb-id", phb->phb_id, + &error_abort); + object_property_set_int(OBJECT(pci->bus), "chip-id", phb->chip_id, + &error_abort); + + pci_setup_iommu(pci->bus, &pnv_phb4_iommu_ops, phb); + pci->bus->flags |= PCI_BUS_EXTENDED_CONFIG_SPACE; +} + +static void pnv_phb4_realize(DeviceState *dev, Error **errp) +{ + PnvPHB4 *phb = PNV_PHB4(dev); + XiveSource *xsrc = &phb->xsrc; + int nr_irqs; + char name[32]; + + /* Set the "big_phb" flag */ + phb->big_phb = phb->phb_id == 0 || phb->phb_id == 3; + + /* Controller Registers */ + snprintf(name, sizeof(name), "phb4-%d.%d-regs", phb->chip_id, + phb->phb_id); + memory_region_init_io(&phb->mr_regs, OBJECT(phb), &pnv_phb4_reg_ops, phb, + name, 0x2000); /* Setup XIVE Source */ if (phb->big_phb) { @@ -1226,39 +1606,68 @@ static void pnv_phb4_realize(DeviceState *dev, Error **errp) pnv_phb4_update_xsrc(phb); phb->qirqs = qemu_allocate_irqs(xive_source_set_irq, xsrc, xsrc->nr_irqs); + + pnv_phb4_xscom_realize(phb); } -static void pnv_phb4_reset(DeviceState *dev) +/* + * Address base trigger mode (POWER10) + * + * Trigger directly the IC ESB page + */ +static void pnv_phb4_xive_notify_abt(PnvPHB4 *phb, uint32_t srcno, + bool pq_checked) { - PnvPHB4 *phb = PNV_PHB4(dev); - PCIDevice *root_dev = PCI_DEVICE(&phb->root); + uint64_t notif_port = phb->regs[PHB_INT_NOTIFY_ADDR >> 3]; + uint64_t data = 0; /* trigger data : don't care */ + hwaddr addr; + MemTxResult result; + int esb_shift; + + if (notif_port & PHB_INT_NOTIFY_ADDR_64K) { + esb_shift = 16; + } else { + esb_shift = 12; + } + + /* Compute the address of the IC ESB management page */ + addr = (notif_port & ~PHB_INT_NOTIFY_ADDR_64K); + addr |= (1ull << (esb_shift + 1)) * srcno; + addr |= (1ull << esb_shift); /* - * Configure PCI device id at reset using a property. + * When the PQ state bits are checked on the PHB, the associated + * PQ state bits on the IC should be ignored. Use the unconditional + * trigger offset to inject a trigger on the IC. This is always + * the case for LSIs */ - pci_config_set_vendor_id(root_dev->config, PCI_VENDOR_ID_IBM); - pci_config_set_device_id(root_dev->config, phb->device_id); -} + if (pq_checked) { + addr |= XIVE_ESB_INJECT; + } -static const char *pnv_phb4_root_bus_path(PCIHostState *host_bridge, - PCIBus *rootbus) -{ - PnvPHB4 *phb = PNV_PHB4(host_bridge); + trace_pnv_phb4_xive_notify_ic(addr, data); - snprintf(phb->bus_path, sizeof(phb->bus_path), "00%02x:%02x", - phb->chip_id, phb->phb_id); - return phb->bus_path; + address_space_stq_be(&address_space_memory, addr, data, + MEMTXATTRS_UNSPECIFIED, &result); + if (result != MEMTX_OK) { + phb_error(phb, "trigger failed @%"HWADDR_PRIx "\n", addr); + return; + } } -static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno) +static void pnv_phb4_xive_notify_ic(PnvPHB4 *phb, uint32_t srcno, + bool pq_checked) { - PnvPHB4 *phb = PNV_PHB4(xf); uint64_t notif_port = phb->regs[PHB_INT_NOTIFY_ADDR >> 3]; uint32_t offset = phb->regs[PHB_INT_NOTIFY_INDEX >> 3]; - uint64_t data = XIVE_TRIGGER_PQ | offset | srcno; + uint64_t data = offset | srcno; MemTxResult result; - trace_pnv_phb4_xive_notify(notif_port, data); + if (pq_checked) { + data |= XIVE_TRIGGER_PQ; + } + + trace_pnv_phb4_xive_notify_ic(notif_port, data); address_space_stq_be(&address_space_memory, notif_port, data, MEMTXATTRS_UNSPECIFIED, &result); @@ -1268,35 +1677,42 @@ static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno) } } +static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno, + bool pq_checked) +{ + PnvPHB4 *phb = PNV_PHB4(xf); + + if (phb->regs[PHB_CTRLR >> 3] & PHB_CTRLR_IRQ_ABT_MODE) { + pnv_phb4_xive_notify_abt(phb, srcno, pq_checked); + } else { + pnv_phb4_xive_notify_ic(phb, srcno, pq_checked); + } +} + static Property pnv_phb4_properties[] = { - DEFINE_PROP_UINT32("index", PnvPHB4, phb_id, 0), - DEFINE_PROP_UINT32("chip-id", PnvPHB4, chip_id, 0), - DEFINE_PROP_UINT64("version", PnvPHB4, version, 0), - DEFINE_PROP_UINT16("device-id", PnvPHB4, device_id, 0), - DEFINE_PROP_LINK("stack", PnvPHB4, stack, TYPE_PNV_PHB4_PEC_STACK, - PnvPhb4PecStack *), - DEFINE_PROP_END_OF_LIST(), + DEFINE_PROP_UINT32("index", PnvPHB4, phb_id, 0), + DEFINE_PROP_UINT32("chip-id", PnvPHB4, chip_id, 0), + DEFINE_PROP_LINK("pec", PnvPHB4, pec, TYPE_PNV_PHB4_PEC, + PnvPhb4PecState *), + DEFINE_PROP_LINK("phb-base", PnvPHB4, phb_base, TYPE_PNV_PHB, PnvPHB *), + DEFINE_PROP_END_OF_LIST(), }; static void pnv_phb4_class_init(ObjectClass *klass, void *data) { - PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass); DeviceClass *dc = DEVICE_CLASS(klass); XiveNotifierClass *xfc = XIVE_NOTIFIER_CLASS(klass); - hc->root_bus_path = pnv_phb4_root_bus_path; dc->realize = pnv_phb4_realize; device_class_set_props(dc, pnv_phb4_properties); - set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); dc->user_creatable = false; - dc->reset = pnv_phb4_reset; xfc->notify = pnv_phb4_xive_notify; } static const TypeInfo pnv_phb4_type_info = { .name = TYPE_PNV_PHB4, - .parent = TYPE_PCIE_HOST_BRIDGE, + .parent = TYPE_DEVICE, .instance_init = pnv_phb4_instance_init, .instance_size = sizeof(PnvPHB4), .class_init = pnv_phb4_class_init, @@ -1306,132 +1722,96 @@ static const TypeInfo pnv_phb4_type_info = { } }; -static void pnv_phb4_root_bus_class_init(ObjectClass *klass, void *data) -{ - BusClass *k = BUS_CLASS(klass); - - /* - * PHB4 has only a single root complex. Enforce the limit on the - * parent bus - */ - k->max_dev = 1; -} - -static const TypeInfo pnv_phb4_root_bus_info = { - .name = TYPE_PNV_PHB4_ROOT_BUS, - .parent = TYPE_PCIE_BUS, - .class_init = pnv_phb4_root_bus_class_init, - .interfaces = (InterfaceInfo[]) { - { INTERFACE_PCIE_DEVICE }, - { } - }, +static const TypeInfo pnv_phb5_type_info = { + .name = TYPE_PNV_PHB5, + .parent = TYPE_PNV_PHB4, + .instance_size = sizeof(PnvPHB4), }; -static void pnv_phb4_root_port_reset(DeviceState *dev) +static void pnv_phb4_root_bus_get_prop(Object *obj, Visitor *v, + const char *name, + void *opaque, Error **errp) { - PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(dev); - PCIDevice *d = PCI_DEVICE(dev); - uint8_t *conf = d->config; - - rpc->parent_reset(dev); - - pci_byte_test_and_set_mask(conf + PCI_IO_BASE, - PCI_IO_RANGE_MASK & 0xff); - pci_byte_test_and_clear_mask(conf + PCI_IO_LIMIT, - PCI_IO_RANGE_MASK & 0xff); - pci_set_word(conf + PCI_MEMORY_BASE, 0); - pci_set_word(conf + PCI_MEMORY_LIMIT, 0xfff0); - pci_set_word(conf + PCI_PREF_MEMORY_BASE, 0x1); - pci_set_word(conf + PCI_PREF_MEMORY_LIMIT, 0xfff1); - pci_set_long(conf + PCI_PREF_BASE_UPPER32, 0x1); /* Hack */ - pci_set_long(conf + PCI_PREF_LIMIT_UPPER32, 0xffffffff); + PnvPHB4RootBus *bus = PNV_PHB4_ROOT_BUS(obj); + uint64_t value = 0; + + if (strcmp(name, "phb-id") == 0) { + value = bus->phb_id; + } else { + value = bus->chip_id; + } + + visit_type_size(v, name, &value, errp); } -static void pnv_phb4_root_port_realize(DeviceState *dev, Error **errp) +static void pnv_phb4_root_bus_set_prop(Object *obj, Visitor *v, + const char *name, + void *opaque, Error **errp) + { - PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(dev); - Error *local_err = NULL; + PnvPHB4RootBus *bus = PNV_PHB4_ROOT_BUS(obj); + uint64_t value; - rpc->parent_realize(dev, &local_err); - if (local_err) { - error_propagate(errp, local_err); + if (!visit_type_size(v, name, &value, errp)) { return; } + + if (strcmp(name, "phb-id") == 0) { + bus->phb_id = value; + } else { + bus->chip_id = value; + } } -static void pnv_phb4_root_port_class_init(ObjectClass *klass, void *data) +static void pnv_phb4_root_bus_class_init(ObjectClass *klass, void *data) { - DeviceClass *dc = DEVICE_CLASS(klass); - PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - PCIERootPortClass *rpc = PCIE_ROOT_PORT_CLASS(klass); - - dc->desc = "IBM PHB4 PCIE Root Port"; - dc->user_creatable = false; - - device_class_set_parent_realize(dc, pnv_phb4_root_port_realize, - &rpc->parent_realize); - device_class_set_parent_reset(dc, pnv_phb4_root_port_reset, - &rpc->parent_reset); + BusClass *k = BUS_CLASS(klass); - k->vendor_id = PCI_VENDOR_ID_IBM; - k->device_id = PNV_PHB4_DEVICE_ID; - k->revision = 0; + object_class_property_add(klass, "phb-id", "int", + pnv_phb4_root_bus_get_prop, + pnv_phb4_root_bus_set_prop, + NULL, NULL); - rpc->exp_offset = 0x48; - rpc->aer_offset = 0x100; + object_class_property_add(klass, "chip-id", "int", + pnv_phb4_root_bus_get_prop, + pnv_phb4_root_bus_set_prop, + NULL, NULL); - dc->reset = &pnv_phb4_root_port_reset; + /* + * PHB4 has only a single root complex. Enforce the limit on the + * parent bus + */ + k->max_dev = 1; } -static const TypeInfo pnv_phb4_root_port_info = { - .name = TYPE_PNV_PHB4_ROOT_PORT, - .parent = TYPE_PCIE_ROOT_PORT, - .instance_size = sizeof(PnvPHB4RootPort), - .class_init = pnv_phb4_root_port_class_init, +static const TypeInfo pnv_phb4_root_bus_info = { + .name = TYPE_PNV_PHB4_ROOT_BUS, + .parent = TYPE_PCIE_BUS, + .instance_size = sizeof(PnvPHB4RootBus), + .class_init = pnv_phb4_root_bus_class_init, }; static void pnv_phb4_register_types(void) { type_register_static(&pnv_phb4_root_bus_info); - type_register_static(&pnv_phb4_root_port_info); type_register_static(&pnv_phb4_type_info); + type_register_static(&pnv_phb5_type_info); type_register_static(&pnv_phb4_iommu_memory_region_info); } type_init(pnv_phb4_register_types); -void pnv_phb4_update_regions(PnvPhb4PecStack *stack) -{ - PnvPHB4 *phb = &stack->phb; - - /* Unmap first always */ - if (memory_region_is_mapped(&phb->mr_regs)) { - memory_region_del_subregion(&stack->phbbar, &phb->mr_regs); - } - if (memory_region_is_mapped(&phb->xsrc.esb_mmio)) { - memory_region_del_subregion(&stack->intbar, &phb->xsrc.esb_mmio); - } - - /* Map registers if enabled */ - if (memory_region_is_mapped(&stack->phbbar)) { - memory_region_add_subregion(&stack->phbbar, 0, &phb->mr_regs); - } - - /* Map ESB if enabled */ - if (memory_region_is_mapped(&stack->intbar)) { - memory_region_add_subregion(&stack->intbar, 0, &phb->xsrc.esb_mmio); - } - - /* Check/update m32 */ - pnv_phb4_check_all_mbt(phb); -} - void pnv_phb4_pic_print_info(PnvPHB4 *phb, Monitor *mon) { + uint64_t notif_port = + phb->regs[PHB_INT_NOTIFY_ADDR >> 3] & ~PHB_INT_NOTIFY_ADDR_64K; uint32_t offset = phb->regs[PHB_INT_NOTIFY_INDEX >> 3]; + bool abt = !!(phb->regs[PHB_CTRLR >> 3] & PHB_CTRLR_IRQ_ABT_MODE); - monitor_printf(mon, "PHB4[%x:%x] Source %08x .. %08x\n", + monitor_printf(mon, "PHB4[%x:%x] Source %08x .. %08x %s @%"HWADDR_PRIx"\n", phb->chip_id, phb->phb_id, - offset, offset + phb->xsrc.nr_irqs - 1); + offset, offset + phb->xsrc.nr_irqs - 1, + abt ? "ABT" : "", + notif_port); xive_source_pic_print_info(&phb->xsrc, 0, mon); } |