/* * QEMU sPAPR PCI host originated from Uninorth PCI host * * Copyright (c) 2011 Alexey Kardashevskiy, IBM Corporation. * Copyright (C) 2011 David Gibson, IBM Corporation. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal * in the Software without restriction, including without limitation the rights * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell * copies of the Software, and to permit persons to whom the Software is * furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN * THE SOFTWARE. */ #include "qemu/osdep.h" #include "qapi/error.h" #include "cpu.h" #include "hw/irq.h" #include "hw/sysbus.h" #include "migration/vmstate.h" #include "hw/pci/pci.h" #include "hw/pci/msi.h" #include "hw/pci/msix.h" #include "hw/pci/pci_host.h" #include "hw/ppc/spapr.h" #include "hw/pci-host/spapr.h" #include "exec/address-spaces.h" #include "exec/ram_addr.h" #include #include "trace.h" #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/qmp/qerror.h" #include "hw/ppc/fdt.h" #include "hw/pci/pci_bridge.h" #include "hw/pci/pci_bus.h" #include "hw/pci/pci_ids.h" #include "hw/ppc/spapr_drc.h" #include "hw/qdev-properties.h" #include "sysemu/device_tree.h" #include "sysemu/kvm.h" #include "sysemu/hostmem.h" #include "sysemu/numa.h" #include "hw/ppc/spapr_numa.h" /* Copied from the kernel arch/powerpc/platforms/pseries/msi.c */ #define RTAS_QUERY_FN 0 #define RTAS_CHANGE_FN 1 #define RTAS_RESET_FN 2 #define RTAS_CHANGE_MSI_FN 3 #define RTAS_CHANGE_MSIX_FN 4 /* Interrupt types to return on RTAS_CHANGE_* */ #define RTAS_TYPE_MSI 1 #define RTAS_TYPE_MSIX 2 SpaprPhbState *spapr_pci_find_phb(SpaprMachineState *spapr, uint64_t buid) { SpaprPhbState *sphb; QLIST_FOREACH(sphb, &spapr->phbs, list) { if (sphb->buid != buid) { continue; } return sphb; } return NULL; } PCIDevice *spapr_pci_find_dev(SpaprMachineState *spapr, uint64_t buid, uint32_t config_addr) { SpaprPhbState *sphb = spapr_pci_find_phb(spapr, buid); PCIHostState *phb = PCI_HOST_BRIDGE(sphb); int bus_num = (config_addr >> 16) & 0xFF; int devfn = (config_addr >> 8) & 0xFF; if (!phb) { return NULL; } return pci_find_device(phb->bus, bus_num, devfn); } static uint32_t rtas_pci_cfgaddr(uint32_t arg) { /* This handles the encoding of extended config space addresses */ return ((arg >> 20) & 0xf00) | (arg & 0xff); } static void finish_read_pci_config(SpaprMachineState *spapr, uint64_t buid, uint32_t addr, uint32_t size, target_ulong rets) { PCIDevice *pci_dev; uint32_t val; if ((size != 1) && (size != 2) && (size != 4)) { /* access must be 1, 2 or 4 bytes */ rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } pci_dev = spapr_pci_find_dev(spapr, buid, addr); addr = rtas_pci_cfgaddr(addr); if (!pci_dev || (addr % size) || (addr >= pci_config_size(pci_dev))) { /* Access must be to a valid device, within bounds and * naturally aligned */ rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } val = pci_host_config_read_common(pci_dev, addr, pci_config_size(pci_dev), size); rtas_st(rets, 0, RTAS_OUT_SUCCESS); rtas_st(rets, 1, val); } static void rtas_ibm_read_pci_config(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { uint64_t buid; uint32_t size, addr; if ((nargs != 4) || (nret != 2)) { rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } buid = rtas_ldq(args, 1); size = rtas_ld(args, 3); addr = rtas_ld(args, 0); finish_read_pci_config(spapr, buid, addr, size, rets); } static void rtas_read_pci_config(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { uint32_t size, addr; if ((nargs != 2) || (nret != 2)) { rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } size = rtas_ld(args, 1); addr = rtas_ld(args, 0); finish_read_pci_config(spapr, 0, addr, size, rets); } static void finish_write_pci_config(SpaprMachineState *spapr, uint64_t buid, uint32_t addr, uint32_t size, uint32_t val, target_ulong rets) { PCIDevice *pci_dev; if ((size != 1) && (size != 2) && (size != 4)) { /* access must be 1, 2 or 4 bytes */ rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } pci_dev = spapr_pci_find_dev(spapr, buid, addr); addr = rtas_pci_cfgaddr(addr); if (!pci_dev || (addr % size) || (addr >= pci_config_size(pci_dev))) { /* Access must be to a valid device, within bounds and * naturally aligned */ rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } pci_host_config_write_common(pci_dev, addr, pci_config_size(pci_dev), val, size); rtas_st(rets, 0, RTAS_OUT_SUCCESS); } static void rtas_ibm_write_pci_config(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { uint64_t buid; uint32_t val, size, addr; if ((nargs != 5) || (nret != 1)) { rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } buid = rtas_ldq(args, 1); val = rtas_ld(args, 4); size = rtas_ld(args, 3); addr = rtas_ld(args, 0); finish_write_pci_config(spapr, buid, addr, size, val, rets); } static void rtas_write_pci_config(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { uint32_t val, size, addr; if ((nargs != 3) || (nret != 1)) { rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } val = rtas_ld(args, 2); size = rtas_ld(args, 1); addr = rtas_ld(args, 0); finish_write_pci_config(spapr, 0, addr, size, val, rets); } /* * Set MSI/MSIX message data. * This is required for msi_notify()/msix_notify() which * will write at the addresses via spapr_msi_write(). * * If hwaddr == 0, all entries will have .data == first_irq i.e. * table will be reset. */ static void spapr_msi_setmsg(PCIDevice *pdev, hwaddr addr, bool msix, unsigned first_irq, unsigned req_num) { unsigned i; MSIMessage msg = { .address = addr, .data = first_irq }; if (!msix) { msi_set_message(pdev, msg); trace_spapr_pci_msi_setup(pdev->name, 0, msg.address); return; } for (i = 0; i < req_num; ++i) { msix_set_message(pdev, i, msg); trace_spapr_pci_msi_setup(pdev->name, i, msg.address); if (addr) { ++msg.data; } } } static void rtas_ibm_change_msi(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); uint32_t config_addr = rtas_ld(args, 0); uint64_t buid = rtas_ldq(args, 1); unsigned int func = rtas_ld(args, 3); unsigned int req_num = rtas_ld(args, 4); /* 0 == remove all */ unsigned int seq_num = rtas_ld(args, 5); unsigned int ret_intr_type; unsigned int irq, max_irqs = 0; SpaprPhbState *phb = NULL; PCIDevice *pdev = NULL; SpaprPciMsi *msi; int *config_addr_key; Error *err = NULL; int i; /* Fins SpaprPhbState */ phb = spapr_pci_find_phb(spapr, buid); if (phb) { pdev = spapr_pci_find_dev(spapr, buid, config_addr); } if (!phb || !pdev) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); return; } switch (func) { case RTAS_CHANGE_FN: if (msi_present(pdev)) { ret_intr_type = RTAS_TYPE_MSI; } else if (msix_present(pdev)) { ret_intr_type = RTAS_TYPE_MSIX; } else { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); return; } break; case RTAS_CHANGE_MSI_FN: if (msi_present(pdev)) { ret_intr_type = RTAS_TYPE_MSI; } else { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); return; } break; case RTAS_CHANGE_MSIX_FN: if (msix_present(pdev)) { ret_intr_type = RTAS_TYPE_MSIX; } else { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); return; } break; default: error_report("rtas_ibm_change_msi(%u) is not implemented", func); rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); return; } msi = (SpaprPciMsi *) g_hash_table_lookup(phb->msi, &config_addr); /* Releasing MSIs */ if (!req_num) { if (!msi) { trace_spapr_pci_msi("Releasing wrong config", config_addr); rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } if (msi_present(pdev)) { spapr_msi_setmsg(pdev, 0, false, 0, 0); } if (msix_present(pdev)) { spapr_msi_setmsg(pdev, 0, true, 0, 0); } g_hash_table_remove(phb->msi, &config_addr); trace_spapr_pci_msi("Released MSIs", config_addr); rtas_st(rets, 0, RTAS_OUT_SUCCESS); rtas_st(rets, 1, 0); return; } /* Enabling MSI */ /* Check if the device supports as many IRQs as requested */ if (ret_intr_type == RTAS_TYPE_MSI) { max_irqs = msi_nr_vectors_allocated(pdev); } else if (ret_intr_type == RTAS_TYPE_MSIX) { max_irqs = pdev->msix_entries_nr; } if (!max_irqs) { error_report("Requested interrupt type %d is not enabled for device %x", ret_intr_type, config_addr); rtas_st(rets, 0, -1); /* Hardware error */ return; } /* Correct the number if the guest asked for too many */ if (req_num > max_irqs) { trace_spapr_pci_msi_retry(config_addr, req_num, max_irqs); req_num = max_irqs; irq = 0; /* to avoid misleading trace */ goto out; } /* Allocate MSIs */ if (smc->legacy_irq_allocation) { irq = spapr_irq_find(spapr, req_num, ret_intr_type == RTAS_TYPE_MSI, &err); } else { irq = spapr_irq_msi_alloc(spapr, req_num, ret_intr_type == RTAS_TYPE_MSI, &err); } if (err) { error_reportf_err(err, "Can't allocate MSIs for device %x: ", config_addr); rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } for (i = 0; i < req_num; i++) { spapr_irq_claim(spapr, irq + i, false, &err); if (err) { if (i) { spapr_irq_free(spapr, irq, i); } if (!smc->legacy_irq_allocation) { spapr_irq_msi_free(spapr, irq, req_num); } error_reportf_err(err, "Can't allocate MSIs for device %x: ", config_addr); rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } } /* Release previous MSIs */ if (msi) { g_hash_table_remove(phb->msi, &config_addr); } /* Setup MSI/MSIX vectors in the device (via cfgspace or MSIX BAR) */ spapr_msi_setmsg(pdev, SPAPR_PCI_MSI_WINDOW, ret_intr_type == RTAS_TYPE_MSIX, irq, req_num); /* Add MSI device to cache */ msi = g_new(SpaprPciMsi, 1); msi->first_irq = irq; msi->num = req_num; config_addr_key = g_new(int, 1); *config_addr_key = config_addr; g_hash_table_insert(phb->msi, config_addr_key, msi); out: rtas_st(rets, 0, RTAS_OUT_SUCCESS); rtas_st(rets, 1, req_num); rtas_st(rets, 2, ++seq_num); if (nret > 3) { rtas_st(rets, 3, ret_intr_type); } trace_spapr_pci_rtas_ibm_change_msi(config_addr, func, req_num, irq); } static void rtas_ibm_query_interrupt_source_number(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { uint32_t config_addr = rtas_ld(args, 0); uint64_t buid = rtas_ldq(args, 1); unsigned int intr_src_num = -1, ioa_intr_num = rtas_ld(args, 3); SpaprPhbState *phb = NULL; PCIDevice *pdev = NULL; SpaprPciMsi *msi; /* Find SpaprPhbState */ phb = spapr_pci_find_phb(spapr, buid); if (phb) { pdev = spapr_pci_find_dev(spapr, buid, config_addr); } if (!phb || !pdev) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); return; } /* Find device descriptor and start IRQ */ msi = (SpaprPciMsi *) g_hash_table_lookup(phb->msi, &config_addr); if (!msi || !msi->first_irq || !msi->num || (ioa_intr_num >= msi->num)) { trace_spapr_pci_msi("Failed to return vector", config_addr); rtas_st(rets, 0, RTAS_OUT_HW_ERROR); return; } intr_src_num = msi->first_irq + ioa_intr_num; trace_spapr_pci_rtas_ibm_query_interrupt_source_number(ioa_intr_num, intr_src_num); rtas_st(rets, 0, RTAS_OUT_SUCCESS); rtas_st(rets, 1, intr_src_num); rtas_st(rets, 2, 1);/* 0 == level; 1 == edge */ } static void rtas_ibm_set_eeh_option(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprPhbState *sphb; uint32_t addr, option; uint64_t buid; int ret; if ((nargs != 4) || (nret != 1)) { goto param_error_exit; } buid = rtas_ldq(args, 1); addr = rtas_ld(args, 0); option = rtas_ld(args, 3); sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } if (!spapr_phb_eeh_available(sphb)) { goto param_error_exit; } ret = spapr_phb_vfio_eeh_set_option(sphb, addr, option); rtas_st(rets, 0, ret); return; param_error_exit: rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } static void rtas_ibm_get_config_addr_info2(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprPhbState *sphb; PCIDevice *pdev; uint32_t addr, option; uint64_t buid; if ((nargs != 4) || (nret != 2)) { goto param_error_exit; } buid = rtas_ldq(args, 1); sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } if (!spapr_phb_eeh_available(sphb)) { goto param_error_exit; } /* * We always have PE address of form "00BB0001". "BB" * represents the bus number of PE's primary bus. */ option = rtas_ld(args, 3); switch (option) { case RTAS_GET_PE_ADDR: addr = rtas_ld(args, 0); pdev = spapr_pci_find_dev(spapr, buid, addr); if (!pdev) { goto param_error_exit; } rtas_st(rets, 1, (pci_bus_num(pci_get_bus(pdev)) << 16) + 1); break; case RTAS_GET_PE_MODE: rtas_st(rets, 1, RTAS_PE_MODE_SHARED); break; default: goto param_error_exit; } rtas_st(rets, 0, RTAS_OUT_SUCCESS); return; param_error_exit: rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } static void rtas_ibm_read_slot_reset_state2(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprPhbState *sphb; uint64_t buid; int state, ret; if ((nargs != 3) || (nret != 4 && nret != 5)) { goto param_error_exit; } buid = rtas_ldq(args, 1); sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } if (!spapr_phb_eeh_available(sphb)) { goto param_error_exit; } ret = spapr_phb_vfio_eeh_get_state(sphb, &state); rtas_st(rets, 0, ret); if (ret != RTAS_OUT_SUCCESS) { return; } rtas_st(rets, 1, state); rtas_st(rets, 2, RTAS_EEH_SUPPORT); rtas_st(rets, 3, RTAS_EEH_PE_UNAVAIL_INFO); if (nret >= 5) { rtas_st(rets, 4, RTAS_EEH_PE_RECOVER_INFO); } return; param_error_exit: rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } static void rtas_ibm_set_slot_reset(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprPhbState *sphb; uint32_t option; uint64_t buid; int ret; if ((nargs != 4) || (nret != 1)) { goto param_error_exit; } buid = rtas_ldq(args, 1); option = rtas_ld(args, 3); sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } if (!spapr_phb_eeh_available(sphb)) { goto param_error_exit; } ret = spapr_phb_vfio_eeh_reset(sphb, option); rtas_st(rets, 0, ret); return; param_error_exit: rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } static void rtas_ibm_configure_pe(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprPhbState *sphb; uint64_t buid; int ret; if ((nargs != 3) || (nret != 1)) { goto param_error_exit; } buid = rtas_ldq(args, 1); sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } if (!spapr_phb_eeh_available(sphb)) { goto param_error_exit; } ret = spapr_phb_vfio_eeh_configure(sphb); rtas_st(rets, 0, ret); return; param_error_exit: rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } /* To support it later */ static void rtas_ibm_slot_error_detail(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { SpaprPhbState *sphb; int option; uint64_t buid; if ((nargs != 8) || (nret != 1)) { goto param_error_exit; } buid = rtas_ldq(args, 1); sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } if (!spapr_phb_eeh_available(sphb)) { goto param_error_exit; } option = rtas_ld(args, 7); switch (option) { case RTAS_SLOT_TEMP_ERR_LOG: case RTAS_SLOT_PERM_ERR_LOG: break; default: goto param_error_exit; } /* We don't have error log yet */ rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND); return; param_error_exit: rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } static void pci_spapr_set_irq(void *opaque, int irq_num, int level) { /* * Here we use the number returned by pci_swizzle_map_irq_fn to find a * corresponding qemu_irq. */ SpaprPhbState *phb = opaque; SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); trace_spapr_pci_lsi_set(phb->dtbusname, irq_num, phb->lsi_table[irq_num].irq); qemu_set_irq(spapr_qirq(spapr, phb->lsi_table[irq_num].irq), level); } static PCIINTxRoute spapr_route_intx_pin_to_irq(void *opaque, int pin) { SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(opaque); PCIINTxRoute route; route.mode = PCI_INTX_ENABLED; route.irq = sphb->lsi_table[pin].irq; return route; } /* * MSI/MSIX memory region implementation. * The handler handles both MSI and MSIX. * The vector number is encoded in least bits in data. */ static void spapr_msi_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); uint32_t irq = data; trace_spapr_pci_msi_write(addr, data, irq); qemu_irq_pulse(spapr_qirq(spapr, irq)); } static const MemoryRegionOps spapr_msi_ops = { /* There is no .read as the read result is undefined by PCI spec */ .read = NULL, .write = spapr_msi_write, .endianness = DEVICE_LITTLE_ENDIAN }; /* * PHB PCI device */ static AddressSpace *spapr_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn) { SpaprPhbState *phb = opaque; return &phb->iommu_as; } static char *spapr_phb_vfio_get_loc_code(SpaprPhbState *sphb, PCIDevice *pdev) { char *path = NULL, *buf = NULL, *host = NULL; /* Get the PCI VFIO host id */ host = object_property_get_str(OBJECT(pdev), "host", NULL); if (!host) { goto err_out; } /* Construct the path of the file that will give us the DT location */ path = g_strdup_printf("/sys/bus/pci/devices/%s/devspec", host); g_free(host); if (!g_file_get_contents(path, &buf, NULL, NULL)) { goto err_out; } g_free(path); /* Construct and read from host device tree the loc-code */ path = g_strdup_printf("/proc/device-tree%s/ibm,loc-code", buf); g_free(buf); if (!g_file_get_contents(path, &buf, NULL, NULL)) { goto err_out; } return buf; err_out: g_free(path); return NULL; } static char *spapr_phb_get_loc_code(SpaprPhbState *sphb, PCIDevice *pdev) { char *buf; const char *devtype = "qemu"; uint32_t busnr = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(pdev)))); if (object_dynamic_cast(OBJECT(pdev), "vfio-pci")) { buf = spapr_phb_vfio_get_loc_code(sphb, pdev); if (buf) { return buf; } devtype = "vfio"; } /* * For emulated devices and VFIO-failure case, make up * the loc-code. */ buf = g_strdup_printf("%s_%s:%04x:%02x:%02x.%x", devtype, pdev->name, sphb->index, busnr, PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); return buf; } /* Macros to operate with address in OF binding to PCI */ #define b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p)) #define b_n(x) b_x((x), 31, 1) /* 0 if relocatable */ #define b_p(x) b_x((x), 30, 1) /* 1 if prefetchable */ #define b_t(x) b_x((x), 29, 1) /* 1 if the address is aliased */ #define b_ss(x) b_x((x), 24, 2) /* the space code */ #define b_bbbbbbbb(x) b_x((x), 16, 8) /* bus number */ #define b_ddddd(x) b_x((x), 11, 5) /* device number */ #define b_fff(x) b_x((x), 8, 3) /* function number */ #define b_rrrrrrrr(x) b_x((x), 0, 8) /* register number */ /* for 'reg' OF properties */ #define RESOURCE_CELLS_SIZE 2 #define RESOURCE_CELLS_ADDRESS 3 typedef struct ResourceFields { uint32_t phys_hi; uint32_t phys_mid; uint32_t phys_lo; uint32_t size_hi; uint32_t size_lo; } QEMU_PACKED ResourceFields; typedef struct ResourceProps { ResourceFields reg[8]; uint32_t reg_len; } ResourceProps; /* fill in the 'reg' OF properties for * a PCI device. 'reg' describes resource requirements for a * device's IO/MEM regions. * * the property is an array of ('phys-addr', 'size') pairs describing * the addressable regions of the PCI device, where 'phys-addr' is a * RESOURCE_CELLS_ADDRESS-tuple of 32-bit integers corresponding to * (phys.hi, phys.mid, phys.lo), and 'size' is a * RESOURCE_CELLS_SIZE-tuple corresponding to (size.hi, size.lo). * * phys.hi = 0xYYXXXXZZ, where: * 0xYY = npt000ss * ||| | * ||| +-- space code * ||| | * ||| + 00 if configuration space * ||| + 01 if IO region, * ||| + 10 if 32-bit MEM region * ||| + 11 if 64-bit MEM region * ||| * ||+------ for non-relocatable IO: 1 if aliased * || for relocatable IO: 1 if below 64KB * || for MEM: 1 if below 1MB * |+------- 1 if region is prefetchable * +-------- 1 if region is non-relocatable * 0xXXXX = bbbbbbbb dddddfff, encoding bus, slot, and function * bits respectively * 0xZZ = rrrrrrrr, the register number of the BAR corresponding * to the region * * phys.mid and phys.lo correspond respectively to the hi/lo portions * of the actual address of the region. * * note also that addresses defined in this property are, at least * for PAPR guests, relative to the PHBs IO/MEM windows, and * correspond directly to the addresses in the BARs. * * in accordance with PCI Bus Binding to Open Firmware, * IEEE Std 1275-1994, section 4.1.1, as implemented by PAPR+ v2.7, * Appendix C. */ static void populate_resource_props(PCIDevice *d, ResourceProps *rp) { int bus_num = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(d)))); uint32_t dev_id = (b_bbbbbbbb(bus_num) | b_ddddd(PCI_SLOT(d->devfn)) | b_fff(PCI_FUNC(d->devfn))); ResourceFields *reg; int i, reg_idx = 0; /* config space region */ reg = &rp->reg[reg_idx++]; reg->phys_hi = cpu_to_be32(dev_id); reg->phys_mid = 0; reg->phys_lo = 0; reg->size_hi = 0; reg->size_lo = 0; for (i = 0; i < PCI_NUM_REGIONS; i++) { if (!d->io_regions[i].size) { continue; } reg = &rp->reg[reg_idx++]; reg->phys_hi = cpu_to_be32(dev_id | b_rrrrrrrr(pci_bar(d, i))); if (d->io_regions[i].type & PCI_BASE_ADDRESS_SPACE_IO) { reg->phys_hi |= cpu_to_be32(b_ss(1)); } else if (d->io_regions[i].type & PCI_BASE_ADDRESS_MEM_TYPE_64) { reg->phys_hi |= cpu_to_be32(b_ss(3)); } else { reg->phys_hi |= cpu_to_be32(b_ss(2)); } reg->phys_mid = 0; reg->phys_lo = 0; reg->size_hi = cpu_to_be32(d->io_regions[i].size >> 32); reg->size_lo = cpu_to_be32(d->io_regions[i].size); } rp->reg_len = reg_idx * sizeof(ResourceFields); } typedef struct PCIClass PCIClass; typedef struct PCISubClass PCISubClass; typedef struct PCIIFace PCIIFace; struct PCIIFace { int iface; const char *name; }; struct PCISubClass { int subclass; const char *name; const PCIIFace *iface; }; struct PCIClass { const char *name; const PCISubClass *subc; }; static const PCISubClass undef_subclass[] = { { PCI_CLASS_NOT_DEFINED_VGA, "display", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass mass_subclass[] = { { PCI_CLASS_STORAGE_SCSI, "scsi", NULL }, { PCI_CLASS_STORAGE_IDE, "ide", NULL }, { PCI_CLASS_STORAGE_FLOPPY, "fdc", NULL }, { PCI_CLASS_STORAGE_IPI, "ipi", NULL }, { PCI_CLASS_STORAGE_RAID, "raid", NULL }, { PCI_CLASS_STORAGE_ATA, "ata", NULL }, { PCI_CLASS_STORAGE_SATA, "sata", NULL }, { PCI_CLASS_STORAGE_SAS, "sas", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass net_subclass[] = { { PCI_CLASS_NETWORK_ETHERNET, "ethernet", NULL }, { PCI_CLASS_NETWORK_TOKEN_RING, "token-ring", NULL }, { PCI_CLASS_NETWORK_FDDI, "fddi", NULL }, { PCI_CLASS_NETWORK_ATM, "atm", NULL }, { PCI_CLASS_NETWORK_ISDN, "isdn", NULL }, { PCI_CLASS_NETWORK_WORLDFIP, "worldfip", NULL }, { PCI_CLASS_NETWORK_PICMG214, "picmg", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass displ_subclass[] = { { PCI_CLASS_DISPLAY_VGA, "vga", NULL }, { PCI_CLASS_DISPLAY_XGA, "xga", NULL }, { PCI_CLASS_DISPLAY_3D, "3d-controller", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass media_subclass[] = { { PCI_CLASS_MULTIMEDIA_VIDEO, "video", NULL }, { PCI_CLASS_MULTIMEDIA_AUDIO, "sound", NULL }, { PCI_CLASS_MULTIMEDIA_PHONE, "telephony", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass mem_subclass[] = { { PCI_CLASS_MEMORY_RAM, "memory", NULL }, { PCI_CLASS_MEMORY_FLASH, "flash", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass bridg_subclass[] = { { PCI_CLASS_BRIDGE_HOST, "host", NULL }, { PCI_CLASS_BRIDGE_ISA, "isa", NULL }, { PCI_CLASS_BRIDGE_EISA, "eisa", NULL }, { PCI_CLASS_BRIDGE_MC, "mca", NULL }, { PCI_CLASS_BRIDGE_PCI, "pci", NULL }, { PCI_CLASS_BRIDGE_PCMCIA, "pcmcia", NULL }, { PCI_CLASS_BRIDGE_NUBUS, "nubus", NULL }, { PCI_CLASS_BRIDGE_CARDBUS, "cardbus", NULL }, { PCI_CLASS_BRIDGE_RACEWAY, "raceway", NULL }, { PCI_CLASS_BRIDGE_PCI_SEMITP, "semi-transparent-pci", NULL }, { PCI_CLASS_BRIDGE_IB_PCI, "infiniband", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass comm_subclass[] = { { PCI_CLASS_COMMUNICATION_SERIAL, "serial", NULL }, { PCI_CLASS_COMMUNICATION_PARALLEL, "parallel", NULL }, { PCI_CLASS_COMMUNICATION_MULTISERIAL, "multiport-serial", NULL }, { PCI_CLASS_COMMUNICATION_MODEM, "modem", NULL }, { PCI_CLASS_COMMUNICATION_GPIB, "gpib", NULL }, { PCI_CLASS_COMMUNICATION_SC, "smart-card", NULL }, { 0xFF, NULL, NULL, }, }; static const PCIIFace pic_iface[] = { { PCI_CLASS_SYSTEM_PIC_IOAPIC, "io-apic" }, { PCI_CLASS_SYSTEM_PIC_IOXAPIC, "io-xapic" }, { 0xFF, NULL }, }; static const PCISubClass sys_subclass[] = { { PCI_CLASS_SYSTEM_PIC, "interrupt-controller", pic_iface }, { PCI_CLASS_SYSTEM_DMA, "dma-controller", NULL }, { PCI_CLASS_SYSTEM_TIMER, "timer", NULL }, { PCI_CLASS_SYSTEM_RTC, "rtc", NULL }, { PCI_CLASS_SYSTEM_PCI_HOTPLUG, "hot-plug-controller", NULL }, { PCI_CLASS_SYSTEM_SDHCI, "sd-host-controller", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass inp_subclass[] = { { PCI_CLASS_INPUT_KEYBOARD, "keyboard", NULL }, { PCI_CLASS_INPUT_PEN, "pen", NULL }, { PCI_CLASS_INPUT_MOUSE, "mouse", NULL }, { PCI_CLASS_INPUT_SCANNER, "scanner", NULL }, { PCI_CLASS_INPUT_GAMEPORT, "gameport", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass dock_subclass[] = { { PCI_CLASS_DOCKING_GENERIC, "dock", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass cpu_subclass[] = { { PCI_CLASS_PROCESSOR_PENTIUM, "pentium", NULL }, { PCI_CLASS_PROCESSOR_POWERPC, "powerpc", NULL }, { PCI_CLASS_PROCESSOR_MIPS, "mips", NULL }, { PCI_CLASS_PROCESSOR_CO, "co-processor", NULL }, { 0xFF, NULL, NULL }, }; static const PCIIFace usb_iface[] = { { PCI_CLASS_SERIAL_USB_UHCI, "usb-uhci" }, { PCI_CLASS_SERIAL_USB_OHCI, "usb-ohci", }, { PCI_CLASS_SERIAL_USB_EHCI, "usb-ehci" }, { PCI_CLASS_SERIAL_USB_XHCI, "usb-xhci" }, { PCI_CLASS_SERIAL_USB_UNKNOWN, "usb-unknown" }, { PCI_CLASS_SERIAL_USB_DEVICE, "usb-device" }, { 0xFF, NULL }, }; static const PCISubClass ser_subclass[] = { { PCI_CLASS_SERIAL_FIREWIRE, "firewire", NULL }, { PCI_CLASS_SERIAL_ACCESS, "access-bus", NULL }, { PCI_CLASS_SERIAL_SSA, "ssa", NULL }, { PCI_CLASS_SERIAL_USB, "usb", usb_iface }, { PCI_CLASS_SERIAL_FIBER, "fibre-channel", NULL }, { PCI_CLASS_SERIAL_SMBUS, "smb", NULL }, { PCI_CLASS_SERIAL_IB, "infiniband", NULL }, { PCI_CLASS_SERIAL_IPMI, "ipmi", NULL }, { PCI_CLASS_SERIAL_SERCOS, "sercos", NULL }, { PCI_CLASS_SERIAL_CANBUS, "canbus", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass wrl_subclass[] = { { PCI_CLASS_WIRELESS_IRDA, "irda", NULL }, { PCI_CLASS_WIRELESS_CIR, "consumer-ir", NULL }, { PCI_CLASS_WIRELESS_RF_CONTROLLER, "rf-controller", NULL }, { PCI_CLASS_WIRELESS_BLUETOOTH, "bluetooth", NULL }, { PCI_CLASS_WIRELESS_BROADBAND, "broadband", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass sat_subclass[] = { { PCI_CLASS_SATELLITE_TV, "satellite-tv", NULL }, { PCI_CLASS_SATELLITE_AUDIO, "satellite-audio", NULL }, { PCI_CLASS_SATELLITE_VOICE, "satellite-voice", NULL }, { PCI_CLASS_SATELLITE_DATA, "satellite-data", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass crypt_subclass[] = { { PCI_CLASS_CRYPT_NETWORK, "network-encryption", NULL }, { PCI_CLASS_CRYPT_ENTERTAINMENT, "entertainment-encryption", NULL }, { 0xFF, NULL, NULL }, }; static const PCISubClass spc_subclass[] = { { PCI_CLASS_SP_DPIO, "dpio", NULL }, { PCI_CLASS_SP_PERF, "counter", NULL }, { PCI_CLASS_SP_SYNCH, "measurement", NULL }, { PCI_CLASS_SP_MANAGEMENT, "management-card", NULL }, { 0xFF, NULL, NULL }, }; static const PCIClass pci_classes[] = { { "legacy-device", undef_subclass }, { "mass-storage", mass_subclass }, { "network", net_subclass }, { "display", displ_subclass, }, { "multimedia-device", media_subclass }, { "memory-controller", mem_subclass }, { "unknown-bridge", bridg_subclass }, { "communication-controller", comm_subclass}, { "system-peripheral", sys_subclass }, { "input-controller", inp_subclass }, { "docking-station", dock_subclass }, { "cpu", cpu_subclass }, { "serial-bus", ser_subclass }, { "wireless-controller", wrl_subclass }, { "intelligent-io", NULL }, { "satellite-device", sat_subclass }, { "encryption", crypt_subclass }, { "data-processing-controller", spc_subclass }, }; static const char *dt_name_from_class(uint8_t class, uint8_t subclass, uint8_t iface) { const PCIClass *pclass; const PCISubClass *psubclass; const PCIIFace *piface; const char *name; if (class >= ARRAY_SIZE(pci_classes)) { return "pci"; } pclass = pci_classes + class; name = pclass->name; if (pclass->subc == NULL) { return name; } psubclass = pclass->subc; while ((psubclass->subclass & 0xff) != 0xff) { if ((psubclass->subclass & 0xff) == subclass) { name = psubclass->name; break; } psubclass++; } piface = psubclass->iface; if (piface == NULL) { return name; } while ((piface->iface & 0xff) != 0xff) { if ((piface->iface & 0xff) == iface) { name = piface->name; break; } piface++; } return name; } /* * DRC helper functions */ static uint32_t drc_id_from_devfn(SpaprPhbState *phb, uint8_t chassis, int32_t devfn) { return (phb->index << 16) | (chassis << 8) | devfn; } static SpaprDrc *drc_from_devfn(SpaprPhbState *phb, uint8_t chassis, int32_t devfn) { return spapr_drc_by_id(TYPE_SPAPR_DRC_PCI, drc_id_from_devfn(phb, chassis, devfn)); } static uint8_t chassis_from_bus(PCIBus *bus) { if (pci_bus_is_root(bus)) { return 0; } else { PCIDevice *bridge = pci_bridge_get_device(bus); return object_property_get_uint(OBJECT(bridge), "chassis_nr", &error_abort); } } static SpaprDrc *drc_from_dev(SpaprPhbState *phb, PCIDevice *dev) { uint8_t chassis = chassis_from_bus(pci_get_bus(dev)); return drc_from_devfn(phb, chassis, dev->devfn); } static void add_drcs(SpaprPhbState *phb, PCIBus *bus) { Object *owner; int i; uint8_t chassis; if (!phb->dr_enabled) { return; } chassis = chassis_from_bus(bus); if (pci_bus_is_root(bus)) { owner = OBJECT(phb); } else { owner = OBJECT(pci_bridge_get_device(bus)); } for (i = 0; i < PCI_SLOT_MAX * PCI_FUNC_MAX; i++) { spapr_dr_connector_new(owner, TYPE_SPAPR_DRC_PCI, drc_id_from_devfn(phb, chassis, i)); } } static void remove_drcs(SpaprPhbState *phb, PCIBus *bus) { int i; uint8_t chassis; if (!phb->dr_enabled) { return; } chassis = chassis_from_bus(bus); for (i = PCI_SLOT_MAX * PCI_FUNC_MAX - 1; i >= 0; i--) { SpaprDrc *drc = drc_from_devfn(phb, chassis, i); if (drc) { object_unparent(OBJECT(drc)); } } } typedef struct PciWalkFdt { void *fdt; int offset; SpaprPhbState *sphb; int err; } PciWalkFdt; static int spapr_dt_pci_device(SpaprPhbState *sphb, PCIDevice *dev, void *fdt, int parent_offset); static void spapr_dt_pci_device_cb(PCIBus *bus, PCIDevice *pdev, void *opaque) { PciWalkFdt *p = opaque; int err; if (p->err) { /* Something's already broken, don't keep going */ return; } err = spapr_dt_pci_device(p->sphb, pdev, p->fdt, p->offset); if (err < 0) { p->err = err; } } /* Augment PCI device node with bridge specific information */ static int spapr_dt_pci_bus(SpaprPhbState *sphb, PCIBus *bus, void *fdt, int offset) { Object *owner; PciWalkFdt cbinfo = { .fdt = fdt, .offset = offset, .sphb = sphb, .err = 0, }; int ret; _FDT(fdt_setprop_cell(fdt, offset, "#address-cells", RESOURCE_CELLS_ADDRESS)); _FDT(fdt_setprop_cell(fdt, offset, "#size-cells", RESOURCE_CELLS_SIZE)); assert(bus); pci_for_each_device_reverse(bus, pci_bus_num(bus), spapr_dt_pci_device_cb, &cbinfo); if (cbinfo.err) { return cbinfo.err; } if (pci_bus_is_root(bus)) { owner = OBJECT(sphb); } else { owner = OBJECT(pci_bridge_get_device(bus)); } ret = spapr_dt_drc(fdt, offset, owner, SPAPR_DR_CONNECTOR_TYPE_PCI); if (ret) { return ret; } return offset; } /* create OF node for pci device and required OF DT properties */ static int spapr_dt_pci_device(SpaprPhbState *sphb, PCIDevice *dev, void *fdt, int parent_offset) { int offset; const gchar *basename; gchar *nodename; int slot = PCI_SLOT(dev->devfn); int func = PCI_FUNC(dev->devfn); PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev); ResourceProps rp; SpaprDrc *drc = drc_from_dev(sphb, dev); uint32_t vendor_id = pci_default_read_config(dev, PCI_VENDOR_ID, 2); uint32_t device_id = pci_default_read_config(dev, PCI_DEVICE_ID, 2); uint32_t revision_id = pci_default_read_config(dev, PCI_REVISION_ID, 1); uint32_t ccode = pci_default_read_config(dev, PCI_CLASS_PROG, 3); uint32_t irq_pin = pci_default_read_config(dev, PCI_INTERRUPT_PIN, 1); uint32_t subsystem_id = pci_default_read_config(dev, PCI_SUBSYSTEM_ID, 2); uint32_t subsystem_vendor_id = pci_default_read_config(dev, PCI_SUBSYSTEM_VENDOR_ID, 2); uint32_t cache_line_size = pci_default_read_config(dev, PCI_CACHE_LINE_SIZE, 1); uint32_t pci_status = pci_default_read_config(dev, PCI_STATUS, 2); gchar *loc_code; basename = dt_name_from_class((ccode >> 16) & 0xff, (ccode >> 8) & 0xff, ccode & 0xff); if (func != 0) { nodename = g_strdup_printf("%s@%x,%x", basename, slot, func); } else { nodename = g_strdup_printf("%s@%x", basename, slot); } _FDT(offset = fdt_add_subnode(fdt, parent_offset, nodename)); g_free(nodename); /* in accordance with PAPR+ v2.7 13.6.3, Table 181 */ _FDT(fdt_setprop_cell(fdt, offset, "vendor-id", vendor_id)); _FDT(fdt_setprop_cell(fdt, offset, "device-id", device_id)); _FDT(fdt_setprop_cell(fdt, offset, "revision-id", revision_id)); _FDT(fdt_setprop_cell(fdt, offset, "class-code", ccode)); if (irq_pin) { _FDT(fdt_setprop_cell(fdt, offset, "interrupts", irq_pin)); } if (subsystem_id) { _FDT(fdt_setprop_cell(fdt, offset, "subsystem-id", subsystem_id)); } if (subsystem_vendor_id) { _FDT(fdt_setprop_cell(fdt, offset, "subsystem-vendor-id", subsystem_vendor_id)); } _FDT(fdt_setprop_cell(fdt, offset, "cache-line-size", cache_line_size)); /* the following fdt cells are masked off the pci status register */ _FDT(fdt_setprop_cell(fdt, offset, "devsel-speed", PCI_STATUS_DEVSEL_MASK & pci_status)); if (pci_status & PCI_STATUS_FAST_BACK) { _FDT(fdt_setprop(fdt, offset, "fast-back-to-back", NULL, 0)); } if (pci_status & PCI_STATUS_66MHZ) { _FDT(fdt_setprop(fdt, offset, "66mhz-capable", NULL, 0)); } if (pci_status & PCI_STATUS_UDF) { _FDT(fdt_setprop(fdt, offset, "udf-supported", NULL, 0)); } loc_code = spapr_phb_get_loc_code(sphb, dev); _FDT(fdt_setprop_string(fdt, offset, "ibm,loc-code", loc_code)); g_free(loc_code); if (drc) { _FDT(fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", spapr_drc_index(drc))); } if (msi_present(dev)) { uint32_t max_msi = msi_nr_vectors_allocated(dev); if (max_msi) { _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi", max_msi)); } } if (msix_present(dev)) { uint32_t max_msix = dev->msix_entries_nr; if (max_msix) { _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi-x", max_msix)); } } populate_resource_props(dev, &rp); _FDT(fdt_setprop(fdt, offset, "reg", (uint8_t *)rp.reg, rp.reg_len)); if (sphb->pcie_ecs && pci_is_express(dev)) { _FDT(fdt_setprop_cell(fdt, offset, "ibm,pci-config-space-type", 0x1)); } spapr_phb_nvgpu_populate_pcidev_dt(dev, fdt, offset, sphb); if (!pc->is_bridge) { /* Properties only for non-bridges */ uint32_t min_grant = pci_default_read_config(dev, PCI_MIN_GNT, 1); uint32_t max_latency = pci_default_read_config(dev, PCI_MAX_LAT, 1); _FDT(fdt_setprop_cell(fdt, offset, "min-grant", min_grant)); _FDT(fdt_setprop_cell(fdt, offset, "max-latency", max_latency)); return offset; } else { PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev)); return spapr_dt_pci_bus(sphb, sec_bus, fdt, offset); } } /* Callback to be called during DRC release. */ void spapr_phb_remove_pci_device_cb(DeviceState *dev) { HotplugHandler *hotplug_ctrl = qdev_get_hotplug_handler(dev); hotplug_handler_unplug(hotplug_ctrl, dev, &error_abort); object_unparent(OBJECT(dev)); } int spapr_pci_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, void *fdt, int *fdt_start_offset, Error **errp) { HotplugHandler *plug_handler = qdev_get_hotplug_handler(drc->dev); SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(plug_handler); PCIDevice *pdev = PCI_DEVICE(drc->dev); *fdt_start_offset = spapr_dt_pci_device(sphb, pdev, fdt, 0); return 0; } static void spapr_pci_bridge_plug(SpaprPhbState *phb, PCIBridge *bridge) { PCIBus *bus = pci_bridge_get_sec_bus(bridge); add_drcs(phb, bus); } /* Returns non-zero if the value of "chassis_nr" is already in use */ static int check_chassis_nr(Object *obj, void *opaque) { int new_chassis_nr = object_property_get_uint(opaque, "chassis_nr", &error_abort); int chassis_nr = object_property_get_uint(obj, "chassis_nr", NULL); if (!object_dynamic_cast(obj, TYPE_PCI_BRIDGE)) { return 0; } /* Skip unsupported bridge types */ if (!chassis_nr) { return 0; } /* Skip self */ if (obj == opaque) { return 0; } return chassis_nr == new_chassis_nr; } static bool bridge_has_valid_chassis_nr(Object *bridge, Error **errp) { int chassis_nr = object_property_get_uint(bridge, "chassis_nr", NULL); /* * slotid_cap_init() already ensures that "chassis_nr" isn't null for * standard PCI bridges, so this really tells if "chassis_nr" is present * or not. */ if (!chassis_nr) { error_setg(errp, "PCI Bridge lacks a \"chassis_nr\" property"); error_append_hint(errp, "Try -device pci-bridge instead.\n"); return false; } /* We want unique values for "chassis_nr" */ if (object_child_foreach_recursive(object_get_root(), check_chassis_nr, bridge)) { error_setg(errp, "Bridge chassis %d already in use", chassis_nr); return false; } return true; } static void spapr_pci_plug(HotplugHandler *plug_handler, DeviceState *plugged_dev, Error **errp) { SpaprPhbState *phb = SPAPR_PCI_HOST_BRIDGE(DEVICE(plug_handler)); PCIDevice *pdev = PCI_DEVICE(plugged_dev); PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(plugged_dev); SpaprDrc *drc = drc_from_dev(phb, pdev); PCIBus *bus = PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))); uint32_t slotnr = PCI_SLOT(pdev->devfn); /* if DR is disabled we don't need to do anything in the case of * hotplug or coldplug callbacks */ if (!phb->dr_enabled) { /* if this is a hotplug operation initiated by the user * we need to let them know it's not enabled */ if (plugged_dev->hotplugged) { error_setg(errp, QERR_BUS_NO_HOTPLUG, object_get_typename(OBJECT(phb))); } return; } g_assert(drc); if (pc->is_bridge) { if (!bridge_has_valid_chassis_nr(OBJECT(plugged_dev), errp)) { return; } spapr_pci_bridge_plug(phb, PCI_BRIDGE(plugged_dev)); } /* Following the QEMU convention used for PCIe multifunction * hotplug, we do not allow functions to be hotplugged to a * slot that already has function 0 present */ if (plugged_dev->hotplugged && bus->devices[PCI_DEVFN(slotnr, 0)] && PCI_FUNC(pdev->devfn) != 0) { error_setg(errp, "PCI: slot %d function 0 already occupied by %s," " additional functions can no longer be exposed to guest.", slotnr, bus->devices[PCI_DEVFN(slotnr, 0)]->name); return; } if (!spapr_drc_attach(drc, DEVICE(pdev), errp)) { return; } /* If this is function 0, signal hotplug for all the device functions. * Otherwise defer sending the hotplug event. */ if (!spapr_drc_hotplugged(plugged_dev)) { spapr_drc_reset(drc); } else if (PCI_FUNC(pdev->devfn) == 0) { int i; uint8_t chassis = chassis_from_bus(pci_get_bus(pdev)); for (i = 0; i < 8; i++) { SpaprDrc *func_drc; SpaprDrcClass *func_drck; SpaprDREntitySense state; func_drc = drc_from_devfn(phb, chassis, PCI_DEVFN(slotnr, i)); func_drck = SPAPR_DR_CONNECTOR_GET_CLASS(func_drc); state = func_drck->dr_entity_sense(func_drc); if (state == SPAPR_DR_ENTITY_SENSE_PRESENT) { spapr_hotplug_req_add_by_index(func_drc); } } } } static void spapr_pci_bridge_unplug(SpaprPhbState *phb, PCIBridge *bridge) { PCIBus *bus = pci_bridge_get_sec_bus(bridge); remove_drcs(phb, bus); } static void spapr_pci_unplug(HotplugHandler *plug_handler, DeviceState *plugged_dev, Error **errp) { PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(plugged_dev); SpaprPhbState *phb = SPAPR_PCI_HOST_BRIDGE(DEVICE(plug_handler)); /* some version guests do not wait for completion of a device * cleanup (generally done asynchronously by the kernel) before * signaling to QEMU that the device is safe, but instead sleep * for some 'safe' period of time. unfortunately on a busy host * this sleep isn't guaranteed to be long enough, resulting in * bad things like IRQ lines being left asserted during final * device removal. to deal with this we call reset just prior * to finalizing the device, which will put the device back into * an 'idle' state, as the device cleanup code expects. */ pci_device_reset(PCI_DEVICE(plugged_dev)); if (pc->is_bridge) { spapr_pci_bridge_unplug(phb, PCI_BRIDGE(plugged_dev)); return; } qdev_unrealize(plugged_dev); } static void spapr_pci_unplug_request(HotplugHandler *plug_handler, DeviceState *plugge/* * QEMU System Emulator * * Copyright (c) 2003-2008 Fabrice Bellard * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal * in the Software without restriction, including without limitation the rights * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell * copies of the Software, and to permit persons to whom the Software is * furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN * THE SOFTWARE. */ #include "qemu/osdep.h" #include "qemu/main-loop.h" #include "qemu/module.h" #include "qapi/error.h" #include "chardev/char-win.h" static void win_chr_read(Chardev *chr, DWORD len) { WinChardev *s = WIN_CHARDEV(chr); int max_size = qemu_chr_be_can_write(chr); int ret, err; uint8_t buf[CHR_READ_BUF_LEN]; DWORD size; if (len > max_size) { len = max_size; } if (len == 0) { return; } ZeroMemory(&s->orecv, sizeof(s->orecv)); s->orecv.hEvent = s->hrecv; ret = ReadFile(s->file, buf, len, &size, &s->orecv); if (!ret) { err = GetLastError(); if (err == ERROR_IO_PENDING) { ret = GetOverlappedResult(s->file, &s->orecv, &size, TRUE); } } if (size > 0) { qemu_chr_be_write(chr, buf, size); } } static int win_chr_serial_poll(void *opaque) { Chardev *chr = CHARDEV(opaque); WinChardev *s = WIN_CHARDEV(opaque); COMSTAT status; DWORD comerr; ClearCommError(s->file, &comerr, &status); if (status.cbInQue > 0) { win_chr_read(chr, status.cbInQue); return 1; } return 0; } int win_chr_serial_init(Chardev *chr, const char *filename, Error **errp) { WinChardev *s = WIN_CHARDEV(chr); COMMCONFIG comcfg; COMMTIMEOUTS cto = { 0, 0, 0, 0, 0}; COMSTAT comstat; DWORD size; DWORD err; s->hsend = CreateEvent(NULL, TRUE, FALSE, NULL); if (!s->hsend) { error_setg(errp, "Failed CreateEvent"); goto fail; } s->hrecv = CreateEvent(NULL, TRUE, FALSE, NULL); if (!s->hrecv) { error_setg(errp, "Failed CreateEvent"); goto fail; } s->file = CreateFile(filename, GENERIC_READ | GENERIC_WRITE, 0, NULL, OPEN_EXISTING, FILE_FLAG_OVERLAPPED, 0); if (s->file == INVALID_HANDLE_VALUE) { error_setg_win32(errp, GetLastError(), "Failed CreateFile"); s->file = NULL; goto fail; } if (!SetupComm(s->file, NRECVBUF, NSENDBUF)) { error_setg(errp, "Failed SetupComm"); goto fail; } ZeroMemory(&comcfg, sizeof(COMMCONFIG)); size = sizeof(COMMCONFIG); GetDefaultCommConfig(filename, &comcfg, &size); comcfg.dcb.DCBlength = sizeof(DCB); CommConfigDialog(filename, NULL, &comcfg); if (!SetCommState(s->file, &comcfg.dcb)) { error_setg(errp, "Failed SetCommState"); goto fail; } if (!SetCommMask(s->file, EV_ERR)) { error_setg(errp, "Failed SetCommMask"); goto fail; } cto.ReadIntervalTimeout = MAXDWORD; if (!SetCommTimeouts(s->file, &cto)) { error_setg(errp, "Failed SetCommTimeouts"); goto fail; } if (!ClearCommError(s->file, &err, &comstat)) { error_setg(errp, "Failed ClearCommError"); goto fail; } qemu_add_polling_cb(win_chr_serial_poll, chr); return 0; fail: return -1; } int win_chr_pipe_poll(void *opaque) { Chardev *chr = CHARDEV(opaque); WinChardev *s = WIN_CHARDEV(opaque); DWORD size; PeekNamedPipe(s->file, NULL, 0, NULL, &size, NULL); if (size > 0) { win_chr_read(chr, size); return 1; } return 0; } /* Called with chr_write_lock held. */ static int win_chr_write(Chardev *chr, const uint8_t *buf, int len1) { WinChardev *s = WIN_CHARDEV(chr); DWORD len, ret, size, err; len = len1; ZeroMemory(&s->osend, sizeof(s->osend)); s->osend.hEvent = s->hsend; while (len > 0) { if (s->hsend) { ret = WriteFile(s->file, buf, len, &size, &s->osend); } else { ret = WriteFile(s->file, buf, len, &size, NULL); } if (!ret) { err = GetLastError(); if (err == ERROR_IO_PENDING) { ret = GetOverlappedResult(s->file, &s->osend, &size, TRUE); if (ret) { buf += size; len -= size; } else { break; } } else { break; } } else { buf += size; len -= size; } } return len1 - len; } static void char_win_finalize(Object *obj) { Chardev *chr = CHARDEV(obj); WinChardev *s = WIN_CHARDEV(chr); if (s->hsend) { CloseHandle(s->hsend); } if (s->hrecv) { CloseHandle(s->hrecv); } if (!s->keep_open && s->file) { CloseHandle(s->file); } if (s->fpipe) { qemu_del_polling_cb(win_chr_pipe_poll, chr); } else { qemu_del_polling_cb(win_chr_serial_poll, chr); } qemu_chr_be_event(chr, CHR_EVENT_CLOSED); } void win_chr_set_file(Chardev *chr, HANDLE file, bool keep_open) { WinChardev *s = WIN_CHARDEV(chr); s->keep_open = keep_open; s->file = file; } static void char_win_class_init(ObjectClass *oc, void *data) { ChardevClass *cc = CHARDEV_CLASS(oc); cc->chr_write = win_chr_write; } static const TypeInfo char_win_type_info = { .name = TYPE_CHARDEV_WIN, .parent = TYPE_CHARDEV, .instance_size = sizeof(WinChardev), .instance_finalize = char_win_finalize, .class_init = char_win_class_init, .abstract = true, }; static void register_types(void) { type_register_static(&char_win_type_info); } type_init(register_types); return 0; } void spapr_pci_rtas_init(void) { spapr_rtas_register(RTAS_READ_PCI_CONFIG, "read-pci-config", rtas_read_pci_config); spapr_rtas_register(RTAS_WRITE_PCI_CONFIG, "write-pci-config", rtas_write_pci_config); spapr_rtas_register(RTAS_IBM_READ_PCI_CONFIG, "ibm,read-pci-config", rtas_ibm_read_pci_config); spapr_rtas_register(RTAS_IBM_WRITE_PCI_CONFIG, "ibm,write-pci-config", rtas_ibm_write_pci_config); if (msi_nonbroken) { spapr_rtas_register(RTAS_IBM_QUERY_INTERRUPT_SOURCE_NUMBER, "ibm,query-interrupt-source-number", rtas_ibm_query_interrupt_source_number); spapr_rtas_register(RTAS_IBM_CHANGE_MSI, "ibm,change-msi", rtas_ibm_change_msi); } spapr_rtas_register(RTAS_IBM_SET_EEH_OPTION, "ibm,set-eeh-option", rtas_ibm_set_eeh_option); spapr_rtas_register(RTAS_IBM_GET_CONFIG_ADDR_INFO2, "ibm,get-config-addr-info2", rtas_ibm_get_config_addr_info2); spapr_rtas_register(RTAS_IBM_READ_SLOT_RESET_STATE2, "ibm,read-slot-reset-state2", rtas_ibm_read_slot_reset_state2); spapr_rtas_register(RTAS_IBM_SET_SLOT_RESET, "ibm,set-slot-reset", rtas_ibm_set_slot_reset); spapr_rtas_register(RTAS_IBM_CONFIGURE_PE, "ibm,configure-pe", rtas_ibm_configure_pe); spapr_rtas_register(RTAS_IBM_SLOT_ERROR_DETAIL, "ibm,slot-error-detail", rtas_ibm_slot_error_detail); } static void spapr_pci_register_types(void) { type_register_static(&spapr_phb_info); } type_init(spapr_pci_register_types) static int spapr_switch_one_vga(DeviceState *dev, void *opaque) { bool be = *(bool *)opaque; if (object_dynamic_cast(OBJECT(dev), "VGA") || object_dynamic_cast(OBJECT(dev), "secondary-vga") || object_dynamic_cast(OBJECT(dev), "bochs-display") || object_dynamic_cast(OBJECT(dev), "virtio-vga")) { object_property_set_bool(OBJECT(dev), "big-endian-framebuffer", be, &error_abort); } return 0; } void spapr_pci_switch_vga(bool big_endian) { SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); SpaprPhbState *sphb; /* * For backward compatibility with existing guests, we switch * the endianness of the VGA controller when changing the guest * interrupt mode */ QLIST_FOREACH(sphb, &spapr->phbs, list) { BusState *bus = &PCI_HOST_BRIDGE(sphb)->bus->qbus; qbus_walk_children(bus, spapr_switch_one_vga, NULL, NULL, NULL, &big_endian); } }