diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2022-07-07 06:21:05 +0530 |
|---|---|---|
| committer | Richard Henderson <richard.henderson@linaro.org> | 2022-07-07 06:21:05 +0530 |
| commit | 8e9398e3b1a860b8c29c670c1b6c36afe8d87849 (patch) | |
| tree | 7f7e081e7cebdc04955398b711eb8fb5d2640574 | |
| parent | 0e3723005bfea2f70157bf951f3e6be03bbf6e74 (diff) | |
| parent | 0b83377f46042529adbbf3a77f7ffb6f1e8a0aaa (diff) | |
| download | qemu-8e9398e3b1a860b8c29c670c1b6c36afe8d87849.zip qemu-8e9398e3b1a860b8c29c670c1b6c36afe8d87849.tar.gz qemu-8e9398e3b1a860b8c29c670c1b6c36afe8d87849.tar.bz2 | |
Merge tag 'pull-ppc-20220706' of https://gitlab.com/danielhb/qemu into staging
ppc patch queue for 2022-07-06:
This queue consists of improvements and bug fixes in TCG, powernv and
pSeries, with some fixes in other areas as well.
- tcg and target/ppc: BCDA and mffscdrn implementations, Remove CONFIG_INT128
conditional code
- fix '-cpu max' alias
- remove '-cpu default' alias
- spapr: fixes in DDW handling, H_WATCHDOG support
- powernv: cleanups in the pnv-phb3/4 models
- fix core type of MPC8555 and MPC8560 models
# -----BEGIN PGP SIGNATURE-----
#
# iHUEABYKAB0WIQQX6/+ZI9AYAK8oOBk82cqW3gMxZAUCYsXrpgAKCRA82cqW3gMx
# ZBe9AP4oqMTFw7r9EQPJU4QFMUeAVABl4o0xNb2wLyYov9CtKAD+LoVERSmtLTJ1
# kFpgBrRTWKVylaLEdZQoTdFlJeBwzQg=
# =GPG1
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 07 Jul 2022 01:38:06 AM +0530
# gpg: using EDDSA key 17EBFF9923D01800AF2838193CD9CA96DE033164
# gpg: Good signature from "Daniel Henrique Barboza <danielhb413@gmail.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 17EB FF99 23D0 1800 AF28 3819 3CD9 CA96 DE03 3164
* tag 'pull-ppc-20220706' of https://gitlab.com/danielhb/qemu: (34 commits)
target/ppc: Fix MPC8555 and MPC8560 core type to e500v1
target/ppc/cpu-models: Remove the "default" CPU alias
target/ppc: Return default CPU for max CPU
target/ppc: implement cdtbcd
target/ppc: implement cbcdtd
target/ppc: implement addg6s
target/ppc: Add flag for ISA v2.06 BCDA instructions
tests/tcg/ppc64: Add mffsce test
target/ppc: Implement mffscdrn[i] instructions
target/ppc: Move mffs[.] to decodetree
target/ppc: Move mffsl to decodetree
target/ppc: Move mffsce to decodetree
target/ppc: Move mffscrn[i] to decodetree
target/ppc: Fix insn32.decode style issues
ppc/spapr: Implement H_WATCHDOG
ppc: Define SETFIELD for the ppc target
target/ppc: use int128.h methods in vsubcuq
target/ppc: use int128.h methods in vsubecuq and vsubeuqm
target/ppc: use int128.h methods in vsubuqm
target/ppc: use int128.h methods in vaddcuq
...
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
33 files changed, 885 insertions, 576 deletions
diff --git a/hw/intc/pnv_xive.c b/hw/intc/pnv_xive.c index 1ce1d7b..c7b75ed 100644 --- a/hw/intc/pnv_xive.c +++ b/hw/intc/pnv_xive.c @@ -67,26 +67,6 @@ static const XiveVstInfo vst_infos[] = { (xive)->chip->chip_id, ## __VA_ARGS__); /* - * QEMU version of the GETFIELD/SETFIELD macros - * - * TODO: It might be better to use the existing extract64() and - * deposit64() but this means that all the register definitions will - * change and become incompatible with the ones found in skiboot. - * - * Keep it as it is for now until we find a common ground. - */ -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); -} - -/* * When PC_TCTXT_CHIPID_OVERRIDE is configured, the PC_TCTXT_CHIPID * field overrides the hardwired chip ID in the Powerbus operations * and for CAM compares diff --git a/hw/intc/pnv_xive2.c b/hw/intc/pnv_xive2.c index f31c53c..f22ce5c 100644 --- a/hw/intc/pnv_xive2.c +++ b/hw/intc/pnv_xive2.c @@ -76,26 +76,6 @@ static const XiveVstInfo vst_infos[] = { (xive)->chip->chip_id, ## __VA_ARGS__); /* - * QEMU version of the GETFIELD/SETFIELD macros - * - * TODO: It might be better to use the existing extract64() and - * deposit64() but this means that all the register definitions will - * change and become incompatible with the ones found in skiboot. - * - * Keep it as it is for now until we find a common ground. - */ -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); -} - -/* * TODO: Document block id override */ static uint32_t pnv_xive2_block_id(PnvXive2 *xive) diff --git a/hw/pci-host/pnv_phb3.c b/hw/pci-host/pnv_phb3.c index 26ac9b7..d58d3c1 100644 --- a/hw/pci-host/pnv_phb3.c +++ b/hw/pci-host/pnv_phb3.c @@ -1052,7 +1052,8 @@ static void pnv_phb3_realize(DeviceState *dev, Error **errp) pci_setup_iommu(pci->bus, pnv_phb3_dma_iommu, phb); - pnv_phb_attach_root_port(PCI_HOST_BRIDGE(phb), TYPE_PNV_PHB3_ROOT_PORT); + pnv_phb_attach_root_port(pci, TYPE_PNV_PHB3_ROOT_PORT, + phb->phb_id, phb->chip_id); } void pnv_phb3_update_regions(PnvPHB3 *phb) @@ -1129,33 +1130,14 @@ static const TypeInfo pnv_phb3_root_bus_info = { .name = TYPE_PNV_PHB3_ROOT_BUS, .parent = TYPE_PCIE_BUS, .class_init = pnv_phb3_root_bus_class_init, - .interfaces = (InterfaceInfo[]) { - { INTERFACE_PCIE_DEVICE }, - { } - }, }; static void pnv_phb3_root_port_realize(DeviceState *dev, Error **errp) { PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(dev); PCIDevice *pci = PCI_DEVICE(dev); - PCIBus *bus = pci_get_bus(pci); - PnvPHB3 *phb = NULL; Error *local_err = NULL; - phb = (PnvPHB3 *) object_dynamic_cast(OBJECT(bus->qbus.parent), - TYPE_PNV_PHB3); - - if (!phb) { - error_setg(errp, -"pnv_phb3_root_port devices must be connected to pnv-phb3 buses"); - return; - } - - /* Set unique chassis/slot values for the root port */ - qdev_prop_set_uint8(&pci->qdev, "chassis", phb->chip_id); - qdev_prop_set_uint16(&pci->qdev, "slot", phb->phb_id); - rpc->parent_realize(dev, &local_err); if (local_err) { error_propagate(errp, local_err); diff --git a/hw/pci-host/pnv_phb4.c b/hw/pci-host/pnv_phb4.c index 6594016..67ddde4 100644 --- a/hw/pci-host/pnv_phb4.c +++ b/hw/pci-host/pnv_phb4.c @@ -31,22 +31,6 @@ qemu_log_mask(LOG_GUEST_ERROR, "phb4_pec[%d:%d]: " fmt "\n", \ (pec)->chip_id, (pec)->index, ## __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); -} - static PCIDevice *pnv_phb4_find_cfg_dev(PnvPHB4 *phb) { PCIHostState *pci = PCI_HOST_BRIDGE(phb); @@ -1547,6 +1531,7 @@ static void pnv_phb4_instance_init(Object *obj) static void pnv_phb4_realize(DeviceState *dev, Error **errp) { PnvPHB4 *phb = PNV_PHB4(dev); + PnvPhb4PecClass *pecc = PNV_PHB4_PEC_GET_CLASS(phb->pec); PCIHostState *pci = PCI_HOST_BRIDGE(dev); XiveSource *xsrc = &phb->xsrc; int nr_irqs; @@ -1583,6 +1568,10 @@ static void pnv_phb4_realize(DeviceState *dev, Error **errp) pci_setup_iommu(pci->bus, pnv_phb4_dma_iommu, phb); pci->bus->flags |= PCI_BUS_EXTENDED_CONFIG_SPACE; + /* Add a single Root port if running with defaults */ + pnv_phb_attach_root_port(pci, pecc->rp_model, + phb->phb_id, phb->chip_id); + /* Setup XIVE Source */ if (phb->big_phb) { nr_irqs = PNV_PHB4_MAX_INTs; @@ -1747,10 +1736,6 @@ 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 void pnv_phb4_root_port_reset(DeviceState *dev) @@ -1777,23 +1762,8 @@ static void pnv_phb4_root_port_reset(DeviceState *dev) static void pnv_phb4_root_port_realize(DeviceState *dev, Error **errp) { PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(dev); - PCIDevice *pci = PCI_DEVICE(dev); - PCIBus *bus = pci_get_bus(pci); - PnvPHB4 *phb = NULL; Error *local_err = NULL; - phb = (PnvPHB4 *) object_dynamic_cast(OBJECT(bus->qbus.parent), - TYPE_PNV_PHB4); - - if (!phb) { - error_setg(errp, "%s must be connected to pnv-phb4 buses", dev->id); - return; - } - - /* Set unique chassis/slot values for the root port */ - qdev_prop_set_uint8(&pci->qdev, "chassis", phb->chip_id); - qdev_prop_set_uint16(&pci->qdev, "slot", phb->phb_id); - rpc->parent_realize(dev, &local_err); if (local_err) { error_propagate(errp, local_err); diff --git a/hw/pci-host/pnv_phb4_pec.c b/hw/pci-host/pnv_phb4_pec.c index 8b7e823..c9aaf1c 100644 --- a/hw/pci-host/pnv_phb4_pec.c +++ b/hw/pci-host/pnv_phb4_pec.c @@ -130,9 +130,6 @@ static void pnv_pec_default_phb_realize(PnvPhb4PecState *pec, if (!sysbus_realize(SYS_BUS_DEVICE(phb), errp)) { return; } - - /* Add a single Root port if running with defaults */ - pnv_phb_attach_root_port(PCI_HOST_BRIDGE(phb), pecc->rp_model); } static void pnv_pec_realize(DeviceState *dev, Error **errp) diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index 7c08a78..d3f77c8 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -652,25 +652,19 @@ static ISABus *pnv_isa_create(PnvChip *chip, Error **errp) return PNV_CHIP_GET_CLASS(chip)->isa_create(chip, errp); } -static int pnv_chip_power8_pic_print_info_child(Object *child, void *opaque) -{ - Monitor *mon = opaque; - PnvPHB3 *phb3 = (PnvPHB3 *) object_dynamic_cast(child, TYPE_PNV_PHB3); - - if (phb3) { - pnv_phb3_msi_pic_print_info(&phb3->msis, mon); - ics_pic_print_info(&phb3->lsis, mon); - } - return 0; -} - static void pnv_chip_power8_pic_print_info(PnvChip *chip, Monitor *mon) { Pnv8Chip *chip8 = PNV8_CHIP(chip); + int i; ics_pic_print_info(&chip8->psi.ics, mon); - object_child_foreach(OBJECT(chip), - pnv_chip_power8_pic_print_info_child, mon); + + for (i = 0; i < chip8->num_phbs; i++) { + PnvPHB3 *phb3 = &chip8->phbs[i]; + + pnv_phb3_msi_pic_print_info(&phb3->msis, mon); + ics_pic_print_info(&phb3->lsis, mon); + } } static int pnv_chip_power9_pic_print_info_child(Object *child, void *opaque) @@ -1189,10 +1183,26 @@ static void pnv_chip_icp_realize(Pnv8Chip *chip8, Error **errp) } } -/* Attach a root port device */ -void pnv_phb_attach_root_port(PCIHostState *pci, const char *name) +/* + * Attach a root port device. + * + * 'index' will be used both as a PCIE slot value and to calculate + * QOM id. 'chip_id' is going to be used as PCIE chassis for the + * root port. + */ +void pnv_phb_attach_root_port(PCIHostState *pci, const char *name, + int index, int chip_id) { PCIDevice *root = pci_new(PCI_DEVFN(0, 0), name); + g_autofree char *default_id = g_strdup_printf("%s[%d]", name, index); + const char *dev_id = DEVICE(root)->id; + + object_property_add_child(OBJECT(pci->bus), dev_id ? dev_id : default_id, + OBJECT(root)); + + /* Set unique chassis/slot values for the root port */ + qdev_prop_set_uint8(DEVICE(root), "chassis", chip_id); + qdev_prop_set_uint16(DEVICE(root), "slot", index); pci_realize_and_unref(root, pci->bus, &error_fatal); } @@ -1934,44 +1944,28 @@ PowerPCCPU *pnv_chip_find_cpu(PnvChip *chip, uint32_t pir) return NULL; } -typedef struct ForeachPhb3Args { - int irq; - ICSState *ics; -} ForeachPhb3Args; - -static int pnv_ics_get_child(Object *child, void *opaque) -{ - ForeachPhb3Args *args = opaque; - PnvPHB3 *phb3 = (PnvPHB3 *) object_dynamic_cast(child, TYPE_PNV_PHB3); - - if (phb3) { - if (ics_valid_irq(&phb3->lsis, args->irq)) { - args->ics = &phb3->lsis; - } - if (ics_valid_irq(ICS(&phb3->msis), args->irq)) { - args->ics = ICS(&phb3->msis); - } - } - return args->ics ? 1 : 0; -} - static ICSState *pnv_ics_get(XICSFabric *xi, int irq) { PnvMachineState *pnv = PNV_MACHINE(xi); - ForeachPhb3Args args = { irq, NULL }; - int i; + int i, j; for (i = 0; i < pnv->num_chips; i++) { - PnvChip *chip = pnv->chips[i]; Pnv8Chip *chip8 = PNV8_CHIP(pnv->chips[i]); if (ics_valid_irq(&chip8->psi.ics, irq)) { return &chip8->psi.ics; } - object_child_foreach(OBJECT(chip), pnv_ics_get_child, &args); - if (args.ics) { - return args.ics; + for (j = 0; j < chip8->num_phbs; j++) { + PnvPHB3 *phb3 = &chip8->phbs[j]; + + if (ics_valid_irq(&phb3->lsis, irq)) { + return &phb3->lsis; + } + + if (ics_valid_irq(ICS(&phb3->msis), irq)) { + return ICS(&phb3->msis); + } } } return NULL; @@ -1990,28 +1984,22 @@ PnvChip *pnv_get_chip(PnvMachineState *pnv, uint32_t chip_id) return NULL; } -static int pnv_ics_resend_child(Object *child, void *opaque) -{ - PnvPHB3 *phb3 = (PnvPHB3 *) object_dynamic_cast(child, TYPE_PNV_PHB3); - - if (phb3) { - ics_resend(&phb3->lsis); - ics_resend(ICS(&phb3->msis)); - } - return 0; -} - static void pnv_ics_resend(XICSFabric *xi) { PnvMachineState *pnv = PNV_MACHINE(xi); - int i; + int i, j; for (i = 0; i < pnv->num_chips; i++) { - PnvChip *chip = pnv->chips[i]; Pnv8Chip *chip8 = PNV8_CHIP(pnv->chips[i]); ics_resend(&chip8->psi.ics); - object_child_foreach(OBJECT(chip), pnv_ics_resend_child, NULL); + + for (j = 0; j < chip8->num_phbs; j++) { + PnvPHB3 *phb3 = &chip8->phbs[j]; + + ics_resend(&phb3->lsis); + ics_resend(ICS(&phb3->msis)); + } } } diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index fd4942e..9a5382d 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -898,6 +898,8 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt) add_str(hypertas, "hcall-hpt-resize"); } + add_str(hypertas, "hcall-watchdog"); + _FDT(fdt_setprop(fdt, rtas, "ibm,hypertas-functions", hypertas->str, hypertas->len)); g_string_free(hypertas, TRUE); @@ -3051,6 +3053,8 @@ static void spapr_machine_init(MachineState *machine) spapr->vof->fw_size = fw_size; /* for claim() on itself */ spapr_register_hypercall(KVMPPC_H_VOF_CLIENT, spapr_h_vof_client); } + + spapr_watchdog_init(spapr); } #define DEFAULT_KVM_TYPE "auto" diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index 81e5a1a..63e34d4 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -279,7 +279,7 @@ static const VMStateDescription vmstate_spapr_tce_table_ex = { static const VMStateDescription vmstate_spapr_tce_table = { .name = "spapr_iommu", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, .pre_save = spapr_tce_table_pre_save, .post_load = spapr_tce_table_post_load, @@ -292,6 +292,7 @@ static const VMStateDescription vmstate_spapr_tce_table = { VMSTATE_BOOL(bypass, SpaprTceTable), VMSTATE_VARRAY_UINT32_ALLOC(mig_table, SpaprTceTable, mig_nb_table, 0, vmstate_info_uint64, uint64_t), + VMSTATE_BOOL_V(def_win, SpaprTceTable, 3), VMSTATE_END_OF_LIST() }, diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index b2f5fbe..67e9d46 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -2067,6 +2067,7 @@ void spapr_phb_dma_reset(SpaprPhbState *sphb) tcet = spapr_tce_find_by_liobn(sphb->dma_liobn[0]); spapr_tce_table_enable(tcet, SPAPR_TCE_PAGE_SHIFT, sphb->dma_win_addr, sphb->dma_win_size >> SPAPR_TCE_PAGE_SHIFT); + tcet->def_win = true; } static void spapr_phb_reset(DeviceState *qdev) @@ -2359,8 +2360,9 @@ int spapr_dt_phb(SpaprMachineState *spapr, SpaprPhbState *phb, cpu_to_be32(RTAS_IBM_REMOVE_PE_DMA_WINDOW) }; uint32_t ddw_extensions[] = { - cpu_to_be32(1), - cpu_to_be32(RTAS_IBM_RESET_PE_DMA_WINDOW) + cpu_to_be32(2), + cpu_to_be32(RTAS_IBM_RESET_PE_DMA_WINDOW), + cpu_to_be32(1), /* 1: ibm,query-pe-dma-window 6 outputs, PAPR 2.8 */ }; SpaprTceTable *tcet; SpaprDrc *drc; diff --git a/hw/ppc/spapr_rtas_ddw.c b/hw/ppc/spapr_rtas_ddw.c index 13d339c..7ba1138 100644 --- a/hw/ppc/spapr_rtas_ddw.c +++ b/hw/ppc/spapr_rtas_ddw.c @@ -100,7 +100,7 @@ static void rtas_ibm_query_pe_dma_window(PowerPCCPU *cpu, uint64_t buid; uint32_t avail, addr, pgmask = 0; - if ((nargs != 3) || (nret != 5)) { + if ((nargs != 3) || ((nret != 5) && (nret != 6))) { goto param_error_exit; } @@ -118,9 +118,20 @@ static void rtas_ibm_query_pe_dma_window(PowerPCCPU *cpu, rtas_st(rets, 0, RTAS_OUT_SUCCESS); rtas_st(rets, 1, avail); - rtas_st(rets, 2, 0x80000000); /* The largest window we can possibly have */ - rtas_st(rets, 3, pgmask); - rtas_st(rets, 4, 0); /* DMA migration mask, not supported */ + if (nret == 6) { + /* + * Set the Max TCE number as 1<<(58-21) = 0x20.0000.0000 + * 1<<59 is the huge window start and 21 is 2M page shift. + */ + rtas_st(rets, 2, 0x00000020); + rtas_st(rets, 3, 0x00000000); + rtas_st(rets, 4, pgmask); + rtas_st(rets, 5, 0); /* DMA migration mask, not supported */ + } else { + rtas_st(rets, 2, 0x80000000); + rtas_st(rets, 3, pgmask); + rtas_st(rets, 4, 0); /* DMA migration mask, not supported */ + } trace_spapr_iommu_ddw_query(buid, addr, avail, 0x80000000, pgmask); return; @@ -215,6 +226,7 @@ static void rtas_ibm_remove_pe_dma_window(PowerPCCPU *cpu, SpaprPhbState *sphb; SpaprTceTable *tcet; uint32_t liobn; + bool def_win_removed; if ((nargs != 1) || (nret != 1)) { goto param_error_exit; @@ -231,9 +243,23 @@ static void rtas_ibm_remove_pe_dma_window(PowerPCCPU *cpu, goto param_error_exit; } + def_win_removed = tcet->def_win; spapr_tce_table_disable(tcet); trace_spapr_iommu_ddw_remove(liobn); + /* + * PAPR+/LoPAPR says: + * The platform must restore the default DMA window for the PE on a call + * to the ibm,remove-pe-dma-window RTAS call when all of the following + * are true: + * a. The call removes the last DMA window remaining for the PE. + * b. The DMA window being removed is not the default window + */ + if (spapr_phb_get_active_win_num(sphb) == 0 && !def_win_removed) { + spapr_phb_dma_reset(sphb); + trace_spapr_iommu_ddw_reset(sphb->buid, 0); + } + rtas_st(rets, 0, RTAS_OUT_SUCCESS); return; diff --git a/hw/watchdog/meson.build b/hw/watchdog/meson.build index 054c403..8974b5c 100644 --- a/hw/watchdog/meson.build +++ b/hw/watchdog/meson.build @@ -6,3 +6,4 @@ softmmu_ss.add(when: 'CONFIG_WDT_DIAG288', if_true: files('wdt_diag288.c')) softmmu_ss.add(when: 'CONFIG_ASPEED_SOC', if_true: files('wdt_aspeed.c')) softmmu_ss.add(when: 'CONFIG_WDT_IMX2', if_true: files('wdt_imx2.c')) softmmu_ss.add(when: 'CONFIG_WDT_SBSA', if_true: files('sbsa_gwdt.c')) +specific_ss.add(when: 'CONFIG_PSERIES', if_true: files('spapr_watchdog.c')) diff --git a/hw/watchdog/spapr_watchdog.c b/hw/watchdog/spapr_watchdog.c new file mode 100644 index 0000000..55ff1f0 --- /dev/null +++ b/hw/watchdog/spapr_watchdog.c @@ -0,0 +1,274 @@ +/* + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "target/ppc/cpu.h" +#include "migration/vmstate.h" +#include "trace.h" + +#include "hw/ppc/spapr.h" + +#define FIELD_BE(reg, field, start, len) \ + FIELD(reg, field, 64 - (start + len), len) + +/* + * Bits 47: "leaveOtherWatchdogsRunningOnTimeout", specified on + * the "Start watchdog" operation, + * 0 - stop out-standing watchdogs on timeout, + * 1 - leave outstanding watchdogs running on timeout + */ +FIELD_BE(PSERIES_WDTF, LEAVE_OTHER, 47, 1) + +/* Bits 48-55: "operation" */ +FIELD_BE(PSERIES_WDTF, OP, 48, 8) +#define PSERIES_WDTF_OP_START 0x1 +#define PSERIES_WDTF_OP_STOP 0x2 +#define PSERIES_WDTF_OP_QUERY 0x3 +#define PSERIES_WDTF_OP_QUERY_LPM 0x4 + +/* Bits 56-63: "timeoutAction" */ +FIELD_BE(PSERIES_WDTF, ACTION, 56, 8) +#define PSERIES_WDTF_ACTION_HARD_POWER_OFF 0x1 +#define PSERIES_WDTF_ACTION_HARD_RESTART 0x2 +#define PSERIES_WDTF_ACTION_DUMP_RESTART 0x3 + +FIELD_BE(PSERIES_WDTF, RESERVED, 0, 47) + +/* Special watchdogNumber for the "stop all watchdogs" operation */ +#define PSERIES_WDT_STOP_ALL ((uint64_t)~0) + +/* + * For the "Query watchdog capabilities" operation, a uint64 structure + * defined as: + * Bits 0-15: The minimum supported timeout in milliseconds + * Bits 16-31: The number of watchdogs supported + * Bits 32-63: Reserved + */ +FIELD_BE(PSERIES_WDTQ, MIN_TIMEOUT, 0, 16) +FIELD_BE(PSERIES_WDTQ, NUM, 16, 16) + +/* + * For the "Query watchdog LPM requirement" operation: + * 1 = The given "watchdogNumber" must be stopped prior to suspending + * 2 = The given "watchdogNumber" does not have to be stopped prior to + * suspending + */ +#define PSERIES_WDTQL_STOPPED 1 +#define PSERIES_WDTQL_QUERY_NOT_STOPPED 2 + +#define WDT_MIN_TIMEOUT 1 /* 1ms */ + +static target_ulong watchdog_stop(unsigned watchdogNumber, SpaprWatchdog *w) +{ + target_ulong ret = H_NOOP; + + if (timer_pending(&w->timer)) { + timer_del(&w->timer); + ret = H_SUCCESS; + } + trace_spapr_watchdog_stop(watchdogNumber, ret); + + return ret; +} + +static target_ulong watchdog_stop_all(SpaprMachineState *spapr) +{ + target_ulong ret = H_NOOP; + int i; + + for (i = 1; i <= ARRAY_SIZE(spapr->wds); ++i) { + target_ulong r = watchdog_stop(i, &spapr->wds[i - 1]); + + if (r != H_NOOP && r != H_SUCCESS) { + ret = r; + } + } + + return ret; +} + +static void watchdog_expired(void *pw) +{ + SpaprWatchdog *w = pw; + CPUState *cs; + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + unsigned num = w - spapr->wds; + + g_assert(num < ARRAY_SIZE(spapr->wds)); + trace_spapr_watchdog_expired(num, w->action); + switch (w->action) { + case PSERIES_WDTF_ACTION_HARD_POWER_OFF: + qemu_system_vmstop_request(RUN_STATE_SHUTDOWN); + break; + case PSERIES_WDTF_ACTION_HARD_RESTART: + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); + break; + case PSERIES_WDTF_ACTION_DUMP_RESTART: + CPU_FOREACH(cs) { + async_run_on_cpu(cs, spapr_do_system_reset_on_cpu, RUN_ON_CPU_NULL); + } + break; + } + if (!w->leave_others) { + watchdog_stop_all(spapr); + } +} + +static target_ulong h_watchdog(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + target_ulong ret = H_SUCCESS; + target_ulong flags = args[0]; + target_ulong watchdogNumber = args[1]; /* 1-Based per PAPR */ + target_ulong timeoutInMs = args[2]; + unsigned operation = FIELD_EX64(flags, PSERIES_WDTF, OP); + unsigned timeoutAction = FIELD_EX64(flags, PSERIES_WDTF, ACTION); + SpaprWatchdog *w; + + if (FIELD_EX64(flags, PSERIES_WDTF, RESERVED)) { + return H_PARAMETER; + } + + switch (operation) { + case PSERIES_WDTF_OP_START: + if (watchdogNumber > ARRAY_SIZE(spapr->wds)) { + return H_P2; + } + if (timeoutInMs <= WDT_MIN_TIMEOUT) { + return H_P3; + } + + w = &spapr->wds[watchdogNumber - 1]; + switch (timeoutAction) { + case PSERIES_WDTF_ACTION_HARD_POWER_OFF: + case PSERIES_WDTF_ACTION_HARD_RESTART: + case PSERIES_WDTF_ACTION_DUMP_RESTART: + w->action = timeoutAction; + break; + default: + return H_PARAMETER; + } + w->leave_others = FIELD_EX64(flags, PSERIES_WDTF, LEAVE_OTHER); + timer_mod(&w->timer, + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + timeoutInMs); + trace_spapr_watchdog_start(flags, watchdogNumber, timeoutInMs); + break; + case PSERIES_WDTF_OP_STOP: + if (watchdogNumber == PSERIES_WDT_STOP_ALL) { + ret = watchdog_stop_all(spapr); + } else if (watchdogNumber <= ARRAY_SIZE(spapr->wds)) { + ret = watchdog_stop(watchdogNumber, + &spapr->wds[watchdogNumber - 1]); + } else { + return H_P2; + } + break; + case PSERIES_WDTF_OP_QUERY: + args[0] = FIELD_DP64(0, PSERIES_WDTQ, MIN_TIMEOUT, WDT_MIN_TIMEOUT); + args[0] = FIELD_DP64(args[0], PSERIES_WDTQ, NUM, + ARRAY_SIZE(spapr->wds)); + trace_spapr_watchdog_query(args[0]); + break; + case PSERIES_WDTF_OP_QUERY_LPM: + if (watchdogNumber > ARRAY_SIZE(spapr->wds)) { + return H_P2; + } + args[0] = PSERIES_WDTQL_QUERY_NOT_STOPPED; + trace_spapr_watchdog_query_lpm(args[0]); + break; + default: + return H_PARAMETER; + } + + return ret; +} + +void spapr_watchdog_init(SpaprMachineState *spapr) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spapr->wds); ++i) { + char name[16]; + SpaprWatchdog *w = &spapr->wds[i]; + + snprintf(name, sizeof(name) - 1, "wdt%d", i + 1); + object_initialize_child_with_props(OBJECT(spapr), name, w, + sizeof(SpaprWatchdog), + TYPE_SPAPR_WDT, + &error_fatal, NULL); + qdev_realize(DEVICE(w), NULL, &error_fatal); + } +} + +static bool watchdog_needed(void *opaque) +{ + SpaprWatchdog *w = opaque; + + return timer_pending(&w->timer); +} + +static const VMStateDescription vmstate_wdt = { + .name = "spapr_watchdog", + .version_id = 1, + .minimum_version_id = 1, + .needed = watchdog_needed, + .fields = (VMStateField[]) { + VMSTATE_TIMER(timer, SpaprWatchdog), + VMSTATE_UINT8(action, SpaprWatchdog), + VMSTATE_UINT8(leave_others, SpaprWatchdog), + VMSTATE_END_OF_LIST() + } +}; + +static void spapr_wdt_realize(DeviceState *dev, Error **errp) +{ + SpaprWatchdog *w = SPAPR_WDT(dev); + Object *o = OBJECT(dev); + + timer_init_ms(&w->timer, QEMU_CLOCK_VIRTUAL, watchdog_expired, w); + + object_property_add_uint64_ptr(o, "expire", + (uint64_t *)&w->timer.expire_time, + OBJ_PROP_FLAG_READ); + object_property_add_uint8_ptr(o, "action", &w->action, OBJ_PROP_FLAG_READ); + object_property_add_uint8_ptr(o, "leaveOtherWatchdogsRunningOnTimeout", + &w->leave_others, OBJ_PROP_FLAG_READ); +} + +static void spapr_wdt_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = spapr_wdt_realize; + dc->vmsd = &vmstate_wdt; + dc->user_creatable = false; +} + +static const TypeInfo spapr_wdt_info = { + .name = TYPE_SPAPR_WDT, + .parent = TYPE_DEVICE, + .instance_size = sizeof(SpaprWatchdog), + .class_init = spapr_wdt_class_init, +}; + +static void spapr_watchdog_register_types(void) +{ + spapr_register_hypercall(H_WATCHDOG, h_watchdog); + type_register_static(&spapr_wdt_info); +} + +type_init(spapr_watchdog_register_types) diff --git a/hw/watchdog/trace-events b/hw/watchdog/trace-events index e7523e2..89ccbcf 100644 --- a/hw/watchdog/trace-events +++ b/hw/watchdog/trace-events @@ -9,3 +9,10 @@ cmsdk_apb_watchdog_lock(uint32_t lock) "CMSDK APB watchdog: lock %" PRIu32 # wdt-aspeed.c aspeed_wdt_read(uint64_t addr, uint32_t size) "@0x%" PRIx64 " size=%d" aspeed_wdt_write(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size=%d value=0x%"PRIx64 + +# spapr_watchdog.c +spapr_watchdog_start(uint64_t flags, uint64_t num, uint64_t timeout) "Flags 0x%" PRIx64 " num=%" PRId64 " %" PRIu64 "ms" +spapr_watchdog_stop(uint64_t num, uint64_t ret) "num=%" PRIu64 " ret=%" PRId64 +spapr_watchdog_query(uint64_t caps) "caps=0x%" PRIx64 +spapr_watchdog_query_lpm(uint64_t caps) "caps=0x%" PRIx64 +spapr_watchdog_expired(uint64_t num, unsigned action) "num=%" PRIu64 " action=%u" diff --git a/include/hw/pci-host/pnv_phb3_regs.h b/include/hw/pci-host/pnv_phb3_regs.h index a174ef1..38f8ce9 100644 --- a/include/hw/pci-host/pnv_phb3_regs.h +++ b/include/hw/pci-host/pnv_phb3_regs.h @@ -13,22 +13,6 @@ #include "qemu/host-utils.h" /* - * 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); -} - -/* * PBCQ XSCOM registers */ diff --git a/include/hw/ppc/pnv.h b/include/hw/ppc/pnv.h index 86cb7d7..b991194 100644 --- a/include/hw/ppc/pnv.h +++ b/include/hw/ppc/pnv.h @@ -189,7 +189,8 @@ DECLARE_INSTANCE_CHECKER(PnvChip, PNV_CHIP_POWER10, TYPE_PNV_CHIP_POWER10) PowerPCCPU *pnv_chip_find_cpu(PnvChip *chip, uint32_t pir); -void pnv_phb_attach_root_port(PCIHostState *pci, const char *name); +void pnv_phb_attach_root_port(PCIHostState *pci, const char *name, + int index, int chip_id); #define TYPE_PNV_MACHINE MACHINE_TYPE_NAME("powernv") typedef struct PnvMachineClass PnvMachineClass; diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index 072dda2..530d739 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -164,6 +164,21 @@ struct SpaprMachineClass { SpaprIrq *irq; }; +#define WDT_MAX_WATCHDOGS 4 /* Maximum number of watchdog devices */ + +#define TYPE_SPAPR_WDT "spapr-wdt" +OBJECT_DECLARE_SIMPLE_TYPE(SpaprWatchdog, SPAPR_WDT) + +typedef struct SpaprWatchdog { + /*< private >*/ + DeviceState parent_obj; + /*< public >*/ + + QEMUTimer timer; + uint8_t action; /* One of PSERIES_WDTF_ACTION_xxx */ + uint8_t leave_others; /* leaveOtherWatchdogsRunningOnTimeout */ +} SpaprWatchdog; + /** * SpaprMachineState: */ @@ -264,6 +279,8 @@ struct SpaprMachineState { uint32_t FORM2_assoc_array[NUMA_NODES_MAX_NUM][FORM2_NUMA_ASSOC_SIZE]; Error *fwnmi_migration_blocker; + + SpaprWatchdog wds[WDT_MAX_WATCHDOGS]; }; #define H_SUCCESS 0 @@ -344,6 +361,7 @@ struct SpaprMachineState { #define H_P7 -60 #define H_P8 -61 #define H_P9 -62 +#define H_NOOP -63 #define H_UNSUPPORTED -67 #define H_OVERLAP -68 #define H_UNSUPPORTED_FLAG -256 @@ -564,8 +582,9 @@ struct SpaprMachineState { #define H_SCM_HEALTH 0x400 #define H_RPT_INVALIDATE 0x448 #define H_SCM_FLUSH 0x44C +#define H_WATCHDOG 0x45C -#define MAX_HCALL_OPCODE H_SCM_FLUSH +#define MAX_HCALL_OPCODE H_WATCHDOG /* The hcalls above are standardized in PAPR and implemented by pHyp * as well. @@ -902,6 +921,7 @@ struct SpaprTceTable { bool bypass; bool need_vfio; bool skipping_replay; + bool def_win; int fd; MemoryRegion root; IOMMUMemoryRegion iommu; @@ -1027,6 +1047,7 @@ extern const VMStateDescription vmstate_spapr_cap_large_decr; extern const VMStateDescription vmstate_spapr_cap_ccf_assist; extern const VMStateDescription vmstate_spapr_cap_fwnmi; extern const VMStateDescription vmstate_spapr_cap_rpt_invalidate; +extern const VMStateDescription vmstate_spapr_wdt; static inline uint8_t spapr_get_cap(SpaprMachineState *spapr, int cap) { @@ -1063,4 +1084,7 @@ target_ulong spapr_vof_client_architecture_support(MachineState *ms, target_ulong ovec_addr); void spapr_vof_client_dt_finalize(SpaprMachineState *spapr, void *fdt); +/* H_WATCHDOG */ +void spapr_watchdog_init(SpaprMachineState *spapr); + #endif /* HW_SPAPR_H */ diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c index 976be5e..912b037 100644 --- a/target/ppc/cpu-models.c +++ b/target/ppc/cpu-models.c @@ -385,19 +385,19 @@ POWERPC_DEF_SVR("mpc8548e_v21", "MPC8548E v2.1", CPU_POWERPC_MPC8548E_v21, POWERPC_SVR_8548E_v21, e500v2) POWERPC_DEF_SVR("mpc8555_v10", "MPC8555 v1.0", - CPU_POWERPC_MPC8555_v10, POWERPC_SVR_8555_v10, e500v2) + CPU_POWERPC_MPC8555_v10, POWERPC_SVR_8555_v10, e500v1) POWERPC_DEF_SVR("mpc8555_v11", "MPC8555 v1.1", - CPU_POWERPC_MPC8555_v11, POWERPC_SVR_8555_v11, e500v2) + CPU_POWERPC_MPC8555_v11, POWERPC_SVR_8555_v11, e500v1) POWERPC_DEF_SVR("mpc8555e_v10", "MPC8555E v1.0", - CPU_POWERPC_MPC8555E_v10, POWERPC_SVR_8555E_v10, e500v2) + CPU_POWERPC_MPC8555E_v10, POWERPC_SVR_8555E_v10, e500v1) POWERPC_DEF_SVR("mpc8555e_v11", "MPC8555E v1.1", - CPU_POWERPC_MPC8555E_v11, POWERPC_SVR_8555E_v11, e500v2) + CPU_POWERPC_MPC8555E_v11, POWERPC_SVR_8555E_v11, e500v1) POWERPC_DEF_SVR("mpc8560_v10", "MPC8560 v1.0", - CPU_POWERPC_MPC8560_v10, POWERPC_SVR_8560_v10, e500v2) + CPU_POWERPC_MPC8560_v10, POWERPC_SVR_8560_v10, e500v1) POWERPC_DEF_SVR("mpc8560_v20", "MPC8560 v2.0", - CPU_POWERPC_MPC8560_v20, POWERPC_SVR_8560_v20, e500v2) + CPU_POWERPC_MPC8560_v20, POWERPC_SVR_8560_v20, e500v1) POWERPC_DEF_SVR("mpc8560_v21", "MPC8560 v2.1", - CPU_POWERPC_MPC8560_v21, POWERPC_SVR_8560_v21, e500v2) + CPU_POWERPC_MPC8560_v21, POWERPC_SVR_8560_v21, e500v1) POWERPC_DEF_SVR("mpc8567", "MPC8567", CPU_POWERPC_MPC8567, POWERPC_SVR_8567, e500v2) POWERPC_DEF_SVR("mpc8567e", "MPC8567E", @@ -879,7 +879,6 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { { "755", "755_v2.8" }, { "goldfinger", "755_v2.8" }, { "7400", "7400_v2.9" }, - { "max", "7400_v2.9" }, { "g4", "7400_v2.9" }, { "7410", "7410_v1.4" }, { "nitro", "7410_v1.4" }, @@ -918,6 +917,6 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { #endif { "ppc32", "604" }, { "ppc", "604" }, - { "default", "604" }, + { NULL, NULL } }; diff --git a/target/ppc/cpu-models.h b/target/ppc/cpu-models.h index 76775a7..1326493 100644 --- a/target/ppc/cpu-models.h +++ b/target/ppc/cpu-models.h @@ -184,13 +184,13 @@ enum { #define CPU_POWERPC_MPC8548E_v11 CPU_POWERPC_e500v2_v11 #define CPU_POWERPC_MPC8548E_v20 CPU_POWERPC_e500v2_v20 #define CPU_POWERPC_MPC8548E_v21 CPU_POWERPC_e500v2_v21 -#define CPU_POWERPC_MPC8555_v10 CPU_POWERPC_e500v2_v10 -#define CPU_POWERPC_MPC8555_v11 CPU_POWERPC_e500v2_v11 -#define CPU_POWERPC_MPC8555E_v10 CPU_POWERPC_e500v2_v10 -#define CPU_POWERPC_MPC8555E_v11 CPU_POWERPC_e500v2_v11 -#define CPU_POWERPC_MPC8560_v10 CPU_POWERPC_e500v2_v10 -#define CPU_POWERPC_MPC8560_v20 CPU_POWERPC_e500v2_v20 -#define CPU_POWERPC_MPC8560_v21 CPU_POWERPC_e500v2_v21 +#define CPU_POWERPC_MPC8555_v10 CPU_POWERPC_e500v1_v20 +#define CPU_POWERPC_MPC8555_v11 CPU_POWERPC_e500v1_v20 +#define CPU_POWERPC_MPC8555E_v10 CPU_POWERPC_e500v1_v20 +#define CPU_POWERPC_MPC8555E_v11 CPU_POWERPC_e500v1_v20 +#define CPU_POWERPC_MPC8560_v10 CPU_POWERPC_e500v1_v10 +#define CPU_POWERPC_MPC8560_v20 CPU_POWERPC_e500v1_v20 +#define CPU_POWERPC_MPC8560_v21 CPU_POWERPC_e500v1_v20 #define CPU_POWERPC_MPC8567 CPU_POWERPC_e500v2_v22 #define CPU_POWERPC_MPC8567E CPU_POWERPC_e500v2_v22 #define CPU_POWERPC_MPC8568 CPU_POWERPC_e500v2_v22 diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 6d78078..7aaff9d 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -47,6 +47,18 @@ PPC_BIT32(bs)) #define PPC_BITMASK8(bs, be) ((PPC_BIT8(bs) - PPC_BIT8(be)) | PPC_BIT8(bs)) +/* + * QEMU version of the GETFIELD/SETFIELD macros from skiboot + * + * It might be better to use the existing extract64() and + * deposit64() but this means that all the register definitions will + * change and become incompatible with the ones found in skiboot. + */ +#define MASK_TO_LSH(m) (__builtin_ffsll(m) - 1) +#define GETFIELD(m, v) (((v) & (m)) >> MASK_TO_LSH(m)) +#define SETFIELD(m, v, val) \ + (((v) & ~(m)) | ((((typeof(v))(val)) << MASK_TO_LSH(m)) & (m))) + /*****************************************************************************/ /* Exception vectors definitions */ enum { @@ -694,42 +706,42 @@ enum { /*****************************************************************************/ /* Floating point status and control register */ -#define FPSCR_DRN2 34 /* Decimal Floating-Point rounding control */ -#define FPSCR_DRN1 33 /* Decimal Floating-Point rounding control */ -#define FPSCR_DRN0 32 /* Decimal Floating-Point rounding control */ -#define FPSCR_FX 31 /* Floating-point exception summary */ -#define FPSCR_FEX 30 /* Floating-point enabled exception summary */ -#define FPSCR_VX 29 /* Floating-point invalid operation exception summ. */ -#define FPSCR_OX 28 /* Floating-point overflow exception */ -#define FPSCR_UX 27 /* Floating-point underflow exception */ -#define FPSCR_ZX 26 /* Floating-point zero divide exception */ -#define FPSCR_XX 25 /* Floating-point inexact exception */ -#define FPSCR_VXSNAN 24 /* Floating-point invalid operation exception (sNan) */ -#define FPSCR_VXISI 23 /* Floating-point invalid operation exception (inf) */ -#define FPSCR_VXIDI 22 /* Floating-point invalid operation exception (inf) */ -#define FPSCR_VXZDZ 21 /* Floating-point invalid operation exception (zero) */ -#define FPSCR_VXIMZ 20 /* Floating-point invalid operation exception (inf) */ -#define FPSCR_VXVC 19 /* Floating-point invalid operation exception (comp) */ -#define FPSCR_FR 18 /* Floating-point fraction rounded */ -#define FPSCR_FI 17 /* Floating-point fraction inexact */ -#define FPSCR_C 16 /* Floating-point result class descriptor */ -#define FPSCR_FL 15 /* Floating-point less than or negative */ -#define FPSCR_FG 14 /* Floating-point greater than or negative */ -#define FPSCR_FE 13 /* Floating-point equal or zero */ -#define FPSCR_FU 12 /* Floating-point unordered or NaN */ -#define FPSCR_FPCC 12 /* Floating-point condition code */ -#define FPSCR_FPRF 12 /* Floating-point result flags */ -#define FPSCR_VXSOFT 10 /* Floating-point invalid operation exception (soft) */ -#define FPSCR_VXSQRT 9 /* Floating-point invalid operation exception (sqrt) */ -#define FPSCR_VXCVI 8 /* Floating-point invalid operation exception (int) */ -#define FPSCR_VE 7 /* Floating-point invalid operation exception enable */ -#define FPSCR_OE 6 /* Floating-point overflow exception enable */ -#define FPSCR_UE 5 /* Floating-point underflow exception enable */ -#define FPSCR_ZE 4 /* Floating-point zero divide exception enable */ -#define FPSCR_XE 3 /* Floating-point inexact exception enable */ -#define FPSCR_NI 2 /* Floating-point non-IEEE mode */ -#define FPSCR_RN1 1 -#define FPSCR_RN0 0 /* Floating-point rounding control */ +#define FPSCR_DRN2 PPC_BIT_NR(29) /* Decimal Floating-Point rounding ctrl. */ +#define FPSCR_DRN1 PPC_BIT_NR(30) /* Decimal Floating-Point rounding ctrl. */ +#define FPSCR_DRN0 PPC_BIT_NR(31) /* Decimal Floating-Point rounding ctrl. */ +#define FPSCR_FX PPC_BIT_NR(32) /* Floating-point exception summary */ +#define FPSCR_FEX PPC_BIT_NR(33) /* Floating-point enabled exception summ.*/ +#define FPSCR_VX PPC_BIT_NR(34) /* Floating-point invalid op. excp. summ.*/ +#define FPSCR_OX PPC_BIT_NR(35) /* Floating-point overflow exception */ +#define FPSCR_UX PPC_BIT_NR(36) /* Floating-point underflow exception */ +#define FPSCR_ZX PPC_BIT_NR(37) /* Floating-point zero divide exception */ +#define FPSCR_XX PPC_BIT_NR(38) /* Floating-point inexact exception */ +#define FPSCR_VXSNAN PPC_BIT_NR(39) /* Floating-point invalid op. excp (sNan)*/ +#define FPSCR_VXISI PPC_BIT_NR(40) /* Floating-point invalid op. excp (inf) */ +#define FPSCR_VXIDI PPC_BIT_NR(41) /* Floating-point invalid op. excp (inf) */ +#define FPSCR_VXZDZ PPC_BIT_NR(42) /* Floating-point invalid op. excp (zero)*/ +#define FPSCR_VXIMZ PPC_BIT_NR(43) /* Floating-point invalid op. excp (inf) */ +#define FPSCR_VXVC PPC_BIT_NR(44) /* Floating-point invalid op. excp (comp)*/ +#define FPSCR_FR PPC_BIT_NR(45) /* Floating-point fraction rounded */ +#define FPSCR_FI PPC_BIT_NR(46) /* Floating-point fraction inexact */ +#define FPSCR_C PPC_BIT_NR(47) /* Floating-point result class descriptor*/ +#define FPSCR_FL PPC_BIT_NR(48) /* Floating-point less than or negative */ +#define FPSCR_FG PPC_BIT_NR(49) /* Floating-point greater than or neg. */ +#define FPSCR_FE PPC_BIT_NR(50) /* Floating-point equal or zero */ +#define FPSCR_FU PPC_BIT_NR(51) /* Floating-point unordered or NaN */ +#define FPSCR_FPCC PPC_BIT_NR(51) /* Floating-point condition code */ +#define FPSCR_FPRF PPC_BIT_NR(51) /* Floating-point result flags */ +#define FPSCR_VXSOFT PPC_BIT_NR(53) /* Floating-point invalid op. excp (soft)*/ +#define FPSCR_VXSQRT PPC_BIT_NR(54) /* Floating-point invalid op. excp (sqrt)*/ +#define FPSCR_VXCVI PPC_BIT_NR(55) /* Floating-point invalid op. excp (int) */ +#define FPSCR_VE PPC_BIT_NR(56) /* Floating-point invalid op. excp enable*/ +#define FPSCR_OE PPC_BIT_NR(57) /* Floating-point overflow excp. enable */ +#define FPSCR_UE PPC_BIT_NR(58) /* Floating-point underflow excp. enable */ +#define FPSCR_ZE PPC_BIT_NR(59) /* Floating-point zero divide excp enable*/ +#define FPSCR_XE PPC_BIT_NR(60) /* Floating-point inexact excp. enable */ +#define FPSCR_NI PPC_BIT_NR(61) /* Floating-point non-IEEE mode */ +#define FPSCR_RN1 PPC_BIT_NR(62) +#define FPSCR_RN0 PPC_BIT_NR(63) /* Floating-point rounding control */ /* Invalid operation exception summary */ #define FPSCR_IX ((1 << FPSCR_VXSNAN) | (1 << FPSCR_VXISI) | \ (1 << FPSCR_VXIDI) | (1 << FPSCR_VXZDZ) | \ @@ -2277,6 +2289,8 @@ enum { PPC2_ISA310 = 0x0000000000100000ULL, /* lwsync instruction */ PPC2_MEM_LWSYNC = 0x0000000000200000ULL, + /* ISA 2.06 BCD assist instructions */ + PPC2_BCDA_ISA206 = 0x0000000000400000ULL, #define PPC_TCG_INSNS2 (PPC2_BOOKE206 | PPC2_VSX | PPC2_PRCNTL | PPC2_DBRX | \ PPC2_ISA205 | PPC2_VSX207 | PPC2_PERM_ISA206 | \ @@ -2285,7 +2299,8 @@ enum { PPC2_BCTAR_ISA207 | PPC2_LSQ_ISA207 | \ PPC2_ALTIVEC_207 | PPC2_ISA207S | PPC2_DFP | \ PPC2_FP_CVT_S64 | PPC2_TM | PPC2_PM_ISA206 | \ - PPC2_ISA300 | PPC2_ISA310 | PPC2_MEM_LWSYNC) + PPC2_ISA300 | PPC2_ISA310 | PPC2_MEM_LWSYNC | \ + PPC2_BCDA_ISA206) }; /*****************************************************************************/ diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index c16cb8d..86ad284 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -47,6 +47,10 @@ #include "spr_common.h" #include "power8-pmu.h" +#ifndef CONFIG_USER_ONLY +#include "hw/boards.h" +#endif + /* #define PPC_DEBUG_SPR */ /* #define USE_APPLE_GDB */ @@ -5985,7 +5989,7 @@ POWERPC_FAMILY(POWER7)(ObjectClass *oc, void *data) PPC2_PERM_ISA206 | PPC2_DIVE_ISA206 | PPC2_ATOMIC_ISA206 | PPC2_FP_CVT_ISA206 | PPC2_FP_TST_ISA206 | PPC2_FP_CVT_S64 | - PPC2_PM_ISA206 | PPC2_MEM_LWSYNC; + PPC2_PM_ISA206 | PPC2_MEM_LWSYNC | PPC2_BCDA_ISA206; pcc->msr_mask = (1ull << MSR_SF) | (1ull << MSR_VR) | (1ull << MSR_VSX) | @@ -6159,7 +6163,8 @@ POWERPC_FAMILY(POWER8)(ObjectClass *oc, void *data) PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207 | PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 | PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | - PPC2_TM | PPC2_PM_ISA206 | PPC2_MEM_LWSYNC; + PPC2_TM | PPC2_PM_ISA206 | PPC2_MEM_LWSYNC | + PPC2_BCDA_ISA206; pcc->msr_mask = (1ull << MSR_SF) | (1ull << MSR_HV) | (1ull << MSR_TM) | @@ -6379,7 +6384,8 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data) PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207 | PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 | PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | - PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL | PPC2_MEM_LWSYNC; + PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL | PPC2_MEM_LWSYNC | + PPC2_BCDA_ISA206; pcc->msr_mask = (1ull << MSR_SF) | (1ull << MSR_HV) | (1ull << MSR_TM) | @@ -6597,7 +6603,7 @@ POWERPC_FAMILY(POWER10)(ObjectClass *oc, void *data) PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 | PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL | PPC2_ISA310 | - PPC2_MEM_LWSYNC; + PPC2_MEM_LWSYNC | PPC2_BCDA_ISA206; pcc->msr_mask = (1ull << MSR_SF) | (1ull << MSR_HV) | (1ull << MSR_TM) | @@ -6963,6 +6969,21 @@ static ObjectClass *ppc_cpu_class_by_name(const char *name) } } + /* + * All ppc CPUs represent hardware that exists in the real world, i.e.: we + * do not have a "max" CPU with all possible emulated features enabled. + * Return the default CPU type for the machine because that has greater + * chance of being useful as the "max" CPU. + */ +#if !defined(CONFIG_USER_ONLY) + if (strcmp(name, "max") == 0) { + MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); + if (mc) { + return object_class_by_name(mc->default_cpu_type); + } + } +#endif + cpu_model = g_ascii_strdown(name, -1); p = ppc_cpu_lookup_alias(cpu_model); if (p) { diff --git a/target/ppc/dfp_helper.c b/target/ppc/dfp_helper.c index 0d01ac3..5ba74b2 100644 --- a/target/ppc/dfp_helper.c +++ b/target/ppc/dfp_helper.c @@ -1391,3 +1391,68 @@ DFP_HELPER_SHIFT(DSCLI, 64, 1) DFP_HELPER_SHIFT(DSCLIQ, 128, 1) DFP_HELPER_SHIFT(DSCRI, 64, 0) DFP_HELPER_SHIFT(DSCRIQ, 128, 0) + +target_ulong helper_CDTBCD(target_ulong s) +{ + uint64_t res = 0; + uint32_t dec32, declets; + uint8_t bcd[6]; + int i, w, sh; + decNumber a; + + for (w = 1; w >= 0; w--) { + res <<= 32; + declets = extract64(s, 32 * w, 20); + if (declets) { + /* decimal32 with zero exponent and word "w" declets */ + dec32 = (0x225ULL << 20) | declets; + decimal32ToNumber((decimal32 *)&dec32, &a); + decNumberGetBCD(&a, bcd); + for (i = 0; i < a.digits; i++) { + sh = 4 * (a.digits - 1 - i); + res |= (uint64_t)bcd[i] << sh; + } + } + } + + return res; +} + +target_ulong helper_CBCDTD(target_ulong s) +{ + uint64_t res = 0; + uint32_t dec32; + uint8_t bcd[6]; + int w, i, offs; + decNumber a; + decContext context; + + decContextDefault(&context, DEC_INIT_DECIMAL32); + + for (w = 1; w >= 0; w--) { + res <<= 32; + decNumberZero(&a); + /* Extract each BCD field of word "w" */ + for (i = 5; i >= 0; i--) { + offs = 4 * (5 - i) + 32 * w; + bcd[i] = extract64(s, offs, 4); + if (bcd[i] > 9) { + /* + * If the field value is greater than 9, the results are + * undefined. We could use a fixed value like 0 or 9, but + * an and with 9 seems to better match the hardware behavior. + */ + bcd[i] &= 9; + } + } + + /* Create a decNumber with the BCD values and convert to decimal32 */ + decNumberSetBCD(&a, bcd, 6); + decimal32FromNumber((decimal32 *)&dec32, &a, &context); + + /* Extract the two declets from the decimal32 value */ + res |= dec32 & 0xfffff; + } + + return res; +} diff --git a/target/ppc/helper.h b/target/ppc/helper.h index d627cfe..ed0641a 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -54,6 +54,8 @@ DEF_HELPER_3(sraw, tl, env, tl, tl) DEF_HELPER_FLAGS_2(CFUGED, TCG_CALL_NO_RWG_SE, i64, i64, i64) DEF_HELPER_FLAGS_2(PDEPD, TCG_CALL_NO_RWG_SE, i64, i64, i64) DEF_HELPER_FLAGS_2(PEXTD, TCG_CALL_NO_RWG_SE, i64, i64, i64) +DEF_HELPER_FLAGS_1(CDTBCD, TCG_CALL_NO_RWG_SE, tl, tl) +DEF_HELPER_FLAGS_1(CBCDTD, TCG_CALL_NO_RWG_SE, tl, tl) #if defined(TARGET_PPC64) DEF_HELPER_FLAGS_2(cmpeqb, TCG_CALL_NO_RWG_SE, i32, tl, tl) DEF_HELPER_FLAGS_1(popcntw, TCG_CALL_NO_RWG_SE, tl, tl) @@ -204,14 +206,14 @@ DEF_HELPER_FLAGS_5(vadduws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32) DEF_HELPER_FLAGS_5(vsububs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32) DEF_HELPER_FLAGS_5(vsubuhs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32) DEF_HELPER_FLAGS_5(vsubuws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32) -DEF_HELPER_FLAGS_3(vadduqm, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_4(vaddecuq, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) -DEF_HELPER_FLAGS_4(vaddeuqm, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) -DEF_HELPER_FLAGS_3(vaddcuq, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vsubuqm, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_4(vsubecuq, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) -DEF_HELPER_FLAGS_4(vsubeuqm, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) -DEF_HELPER_FLAGS_3(vsubcuq, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VADDUQM, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_4(VADDECUQ, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) +DEF_HELPER_FLAGS_4(VADDEUQM, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) +DEF_HELPER_FLAGS_3(VADDCUQ, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VSUBUQM, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_4(VSUBECUQ, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) +DEF_HELPER_FLAGS_4(VSUBEUQM, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) +DEF_HELPER_FLAGS_3(VSUBCUQ, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_4(vsldoi, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) DEF_HELPER_FLAGS_3(vextractub, TCG_CALL_NO_RWG, void, avr, avr, i32) DEF_HELPER_FLAGS_3(vextractuh, TCG_CALL_NO_RWG, void, avr, avr, i32) @@ -318,7 +320,7 @@ DEF_HELPER_FLAGS_3(vbpermq, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_3(vpmsumb, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_3(vpmsumh, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_3(vpmsumw, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vpmsumd, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VPMSUMD, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_2(vextublx, TCG_CALL_NO_RWG, tl, tl, avr) DEF_HELPER_FLAGS_2(vextuhlx, TCG_CALL_NO_RWG, tl, tl, avr) DEF_HELPER_FLAGS_2(vextuwlx, TCG_CALL_NO_RWG, tl, tl, avr) diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode index 6ea48d5..f7653ef 100644 --- a/target/ppc/insn32.decode +++ b/target/ppc/insn32.decode @@ -21,11 +21,11 @@ @A ...... frt:5 fra:5 frb:5 frc:5 ..... rc:1 &A &D rt ra si:int64_t -@D ...... rt:5 ra:5 si:s16 &D +@D ...... rt:5 ra:5 si:s16 &D &D_bf bf l:bool ra imm -@D_bfs ...... bf:3 - l:1 ra:5 imm:s16 &D_bf -@D_bfu ...... bf:3 - l:1 ra:5 imm:16 &D_bf +@D_bfs ...... bf:3 . l:1 ra:5 imm:s16 &D_bf +@D_bfu ...... bf:3 . l:1 ra:5 imm:16 &D_bf %dq_si 4:s12 !function=times_16 %dq_rtp 22:4 !function=times_2 @@ -38,7 +38,7 @@ @DQ_TSXP ...... ..... ra:5 ............ .... &D si=%dq_si rt=%rt_tsxp %ds_si 2:s14 !function=times_4 -@DS ...... rt:5 ra:5 .............. .. &D si=%ds_si +@DS ...... rt:5 ra:5 .............. .. &D si=%ds_si %ds_rtp 22:4 !function=times_2 @DS_rtp ...... ....0 ra:5 .............. .. &D rt=%ds_rtp si=%ds_si @@ -49,10 +49,10 @@ &DX rt d %dx_d 6:s10 16:5 0:1 -@DX ...... rt:5 ..... .......... ..... . &DX d=%dx_d +@DX ...... rt:5 ..... .......... ..... . &DX d=%dx_d &VA vrt vra vrb rc -@VA ...... vrt:5 vra:5 vrb:5 rc:5 ...... &VA +@VA ...... vrt:5 vra:5 vrb:5 rc:5 ...... &VA &VC vrt vra vrb rc:bool @VC ...... vrt:5 vra:5 vrb:5 rc:1 .......... &VC @@ -61,7 +61,7 @@ @VN ...... vrt:5 vra:5 vrb:5 .. sh:3 ...... &VN &VX vrt vra vrb -@VX ...... vrt:5 vra:5 vrb:5 .......... . &VX +@VX ...... vrt:5 vra:5 vrb:5 .......... . &VX &VX_bf bf vra vrb @VX_bf ...... bf:3 .. vra:5 vrb:5 ........... &VX_bf @@ -76,17 +76,20 @@ @VX_tb_rc ...... vrt:5 ..... vrb:5 rc:1 .......... &VX_tb_rc &VX_uim4 vrt uim vrb -@VX_uim4 ...... vrt:5 . uim:4 vrb:5 ........... &VX_uim4 +@VX_uim4 ...... vrt:5 . uim:4 vrb:5 ........... &VX_uim4 &VX_tb vrt vrb -@VX_tb ...... vrt:5 ..... vrb:5 ........... &VX_tb +@VX_tb ...... vrt:5 ..... vrb:5 ........... &VX_tb &X rt ra rb -@X ...... rt:5 ra:5 rb:5 .......... . &X +@X ...... rt:5 ra:5 rb:5 .......... . &X &X_rc rt ra rb rc:bool @X_rc ...... rt:5 ra:5 rb:5 .......... rc:1 &X_rc +&X_sa rs ra +@X_sa ...... rs:5 ra:5 ..... .......... . &X_sa + %x_frtp 22:4 !function=times_2 %x_frap 17:4 !function=times_2 %x_frbp 12:4 !function=times_2 @@ -94,9 +97,15 @@ @X_tp_a_bp_rc ...... ....0 ra:5 ....0 .......... rc:1 &X_rc rt=%x_frtp rb=%x_frbp +&X_t rt +@X_t ...... rt:5 ..... ..... .......... . &X_t + &X_tb rt rb @X_tb ...... rt:5 ..... rb:5 .......... . &X_tb +&X_t_rc rt rc:bool +@X_t_rc ...... rt:5 ..... ..... .......... rc:1 &X_t_rc + &X_tb_rc rt rb rc:bool @X_tb_rc ...... rt:5 ..... rb:5 .......... rc:1 &X_tb_rc @@ -107,7 +116,7 @@ @X_t_bp_rc ...... rt:5 ..... ....0 .......... rc:1 &X_tb_rc rb=%x_frbp &X_bi rt bi -@X_bi ...... rt:5 bi:5 ----- .......... - &X_bi +@X_bi ...... rt:5 bi:5 ..... .......... . &X_bi &X_bf bf ra rb @X_bf ...... bf:3 .. ra:5 rb:5 .......... . &X_bf @@ -122,7 +131,13 @@ @X_bf_uim_bp ...... bf:3 . uim:6 ....0 .......... . &X_bf_uim rb=%x_frbp &X_bfl bf l:bool ra rb -@X_bfl ...... bf:3 - l:1 ra:5 rb:5 ..........- &X_bfl +@X_bfl ...... bf:3 . l:1 ra:5 rb:5 .......... . &X_bfl + +&X_imm2 rt imm +@X_imm2 ...... rt:5 ..... ... imm:2 .......... . &X_imm2 + +&X_imm3 rt imm +@X_imm3 ...... rt:5 ..... .. imm:3 .......... . &X_imm3 %x_xt 0:1 21:5 &X_imm5 xt imm:uint8_t vrb @@ -299,6 +314,12 @@ CNTTZDM 011111 ..... ..... ..... 1000111011 - @X PDEPD 011111 ..... ..... ..... 0010011100 - @X PEXTD 011111 ..... ..... ..... 0010111100 - @X +## BCD Assist + +ADDG6S 011111 ..... ..... ..... - 001001010 - @X +CDTBCD 011111 ..... ..... ----- 0100011010 - @X_sa +CBCDTD 011111 ..... ..... ----- 0100111010 - @X_sa + ### Float-Point Load Instructions LFS 110000 ..... ..... ................ @D @@ -334,6 +355,16 @@ SETBCR 011111 ..... ..... ----- 0110100000 - @X_bi SETNBC 011111 ..... ..... ----- 0111000000 - @X_bi SETNBCR 011111 ..... ..... ----- 0111100000 - @X_bi +### Move To/From FPSCR + +MFFS 111111 ..... 00000 ----- 1001000111 . @X_t_rc +MFFSCE 111111 ..... 00001 ----- 1001000111 - @X_t +MFFSCRN 111111 ..... 10110 ..... 1001000111 - @X_tb +MFFSCDRN 111111 ..... 10100 ..... 1001000111 - @X_tb +MFFSCRNI 111111 ..... 10111 ---.. 1001000111 - @X_imm2 +MFFSCDRNI 111111 ..... 10101 --... 1001000111 - @X_imm3 +MFFSL 111111 ..... 11000 ----- 1001000111 - @X_t + ### Decimal Floating-Point Arithmetic Instructions DADD 111011 ..... ..... ..... 0000000010 . @X_rc @@ -426,6 +457,10 @@ DSCLIQ 111111 ..... ..... ...... 001000010 . @Z22_tap_sh_rc DSCRI 111011 ..... ..... ...... 001100010 . @Z22_ta_sh_rc DSCRIQ 111111 ..... ..... ...... 001100010 . @Z22_tap_sh_rc +## Vector Exclusive-OR-based Instructions + +VPMSUMD 000100 ..... ..... ..... 10011001000 @VX + ## Vector Integer Instructions VCMPEQUB 000100 ..... ..... ..... . 0000000110 @VC @@ -546,6 +581,18 @@ VRLQNM 000100 ..... ..... ..... 00101000101 @VX ## Vector Integer Arithmetic Instructions +VADDCUQ 000100 ..... ..... ..... 00101000000 @VX +VADDUQM 000100 ..... ..... ..... 00100000000 @VX + +VADDEUQM 000100 ..... ..... ..... ..... 111100 @VA +VADDECUQ 000100 ..... ..... ..... ..... 111101 @VA + +VSUBCUQ 000100 ..... ..... ..... 10101000000 @VX +VSUBUQM 000100 ..... ..... ..... 10100000000 @VX + +VSUBECUQ 000100 ..... ..... ..... ..... 111111 @VA +VSUBEUQM 000100 ..... ..... ..... ..... 111110 @VA + VEXTSB2W 000100 ..... 10000 ..... 11000000010 @VX_tb VEXTSH2W 000100 ..... 10001 ..... 11000000010 @VX_tb VEXTSB2D 000100 ..... 11000 ..... 11000000010 @VX_tb diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index 3ae03f7..d905f07 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -1484,52 +1484,24 @@ PMSUM(vpmsumb, u8, u16, uint16_t) PMSUM(vpmsumh, u16, u32, uint32_t) PMSUM(vpmsumw, u32, u64, uint64_t) -void helper_vpmsumd(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) +void helper_VPMSUMD(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) { - -#ifdef CONFIG_INT128 - int i, j; - __uint128_t prod[2]; - - VECTOR_FOR_INORDER_I(i, u64) { - prod[i] = 0; - for (j = 0; j < 64; j++) { - if (a->u64[i] & (1ull << j)) { - prod[i] ^= (((__uint128_t)b->u64[i]) << j); - } - } - } - - r->u128 = prod[0] ^ prod[1]; - -#else int i, j; - ppc_avr_t prod[2]; - - VECTOR_FOR_INORDER_I(i, u64) { - prod[i].VsrD(1) = prod[i].VsrD(0) = 0; - for (j = 0; j < 64; j++) { - if (a->u64[i] & (1ull << j)) { - ppc_avr_t bshift; - if (j == 0) { - bshift.VsrD(0) = 0; - bshift.VsrD(1) = b->u64[i]; - } else { - bshift.VsrD(0) = b->u64[i] >> (64 - j); - bshift.VsrD(1) = b->u64[i] << j; - } - prod[i].VsrD(1) ^= bshift.VsrD(1); - prod[i].VsrD(0) ^= bshift.VsrD(0); + Int128 tmp, prod[2] = {int128_zero(), int128_zero()}; + + for (j = 0; j < 64; j++) { + for (i = 0; i < ARRAY_SIZE(r->u64); i++) { + if (a->VsrD(i) & (1ull << j)) { + tmp = int128_make64(b->VsrD(i)); + tmp = int128_lshift(tmp, j); + prod[i] = int128_xor(prod[i], tmp); } } } - r->VsrD(1) = prod[0].VsrD(1) ^ prod[1].VsrD(1); - r->VsrD(0) = prod[0].VsrD(0) ^ prod[1].VsrD(0); -#endif + r->s128 = int128_xor(prod[0], prod[1]); } - #if HOST_BIG_ENDIAN #define PKBIG 1 #else @@ -2204,189 +2176,66 @@ VGENERIC_DO(popcntd, u64) #undef VGENERIC_DO -#if HOST_BIG_ENDIAN -#define QW_ONE { .u64 = { 0, 1 } } -#else -#define QW_ONE { .u64 = { 1, 0 } } -#endif - -#ifndef CONFIG_INT128 - -static inline void avr_qw_not(ppc_avr_t *t, ppc_avr_t a) -{ - t->u64[0] = ~a.u64[0]; - t->u64[1] = ~a.u64[1]; -} - -static int avr_qw_cmpu(ppc_avr_t a, ppc_avr_t b) -{ - if (a.VsrD(0) < b.VsrD(0)) { - return -1; - } else if (a.VsrD(0) > b.VsrD(0)) { - return 1; - } else if (a.VsrD(1) < b.VsrD(1)) { - return -1; - } else if (a.VsrD(1) > b.VsrD(1)) { - return 1; - } else { - return 0; - } -} - -static void avr_qw_add(ppc_avr_t *t, ppc_avr_t a, ppc_avr_t b) -{ - t->VsrD(1) = a.VsrD(1) + b.VsrD(1); - t->VsrD(0) = a.VsrD(0) + b.VsrD(0) + - (~a.VsrD(1) < b.VsrD(1)); -} - -static int avr_qw_addc(ppc_avr_t *t, ppc_avr_t a, ppc_avr_t b) -{ - ppc_avr_t not_a; - t->VsrD(1) = a.VsrD(1) + b.VsrD(1); - t->VsrD(0) = a.VsrD(0) + b.VsrD(0) + - (~a.VsrD(1) < b.VsrD(1)); - avr_qw_not(¬_a, a); - return avr_qw_cmpu(not_a, b) < 0; -} - -#endif - -void helper_vadduqm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) +void helper_VADDUQM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) { -#ifdef CONFIG_INT128 - r->u128 = a->u128 + b->u128; -#else - avr_qw_add(r, *a, *b); -#endif + r->s128 = int128_add(a->s128, b->s128); } -void helper_vaddeuqm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) +void helper_VADDEUQM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { -#ifdef CONFIG_INT128 - r->u128 = a->u128 + b->u128 + (c->u128 & 1); -#else - - if (c->VsrD(1) & 1) { - ppc_avr_t tmp; - - tmp.VsrD(0) = 0; - tmp.VsrD(1) = c->VsrD(1) & 1; - avr_qw_add(&tmp, *a, tmp); - avr_qw_add(r, tmp, *b); - } else { - avr_qw_add(r, *a, *b); - } -#endif + r->s128 = int128_add(int128_add(a->s128, b->s128), + int128_make64(int128_getlo(c->s128) & 1)); } -void helper_vaddcuq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) +void helper_VADDCUQ(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) { -#ifdef CONFIG_INT128 - r->u128 = (~a->u128 < b->u128); -#else - ppc_avr_t not_a; - - avr_qw_not(¬_a, *a); - + r->VsrD(1) = int128_ult(int128_not(a->s128), b->s128); r->VsrD(0) = 0; - r->VsrD(1) = (avr_qw_cmpu(not_a, *b) < 0); -#endif } -void helper_vaddecuq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) +void helper_VADDECUQ(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { -#ifdef CONFIG_INT128 - int carry_out = (~a->u128 < b->u128); - if (!carry_out && (c->u128 & 1)) { - carry_out = ((a->u128 + b->u128 + 1) == 0) && - ((a->u128 != 0) || (b->u128 != 0)); - } - r->u128 = carry_out; -#else - - int carry_in = c->VsrD(1) & 1; - int carry_out = 0; - ppc_avr_t tmp; - - carry_out = avr_qw_addc(&tmp, *a, *b); + bool carry_out = int128_ult(int128_not(a->s128), b->s128), + carry_in = int128_getlo(c->s128) & 1; if (!carry_out && carry_in) { - ppc_avr_t one = QW_ONE; - carry_out = avr_qw_addc(&tmp, tmp, one); + carry_out = (int128_nz(a->s128) || int128_nz(b->s128)) && + int128_eq(int128_add(a->s128, b->s128), int128_makes64(-1)); } + r->VsrD(0) = 0; r->VsrD(1) = carry_out; -#endif } -void helper_vsubuqm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) +void helper_VSUBUQM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) { -#ifdef CONFIG_INT128 - r->u128 = a->u128 - b->u128; -#else - ppc_avr_t tmp; - ppc_avr_t one = QW_ONE; - - avr_qw_not(&tmp, *b); - avr_qw_add(&tmp, *a, tmp); - avr_qw_add(r, tmp, one); -#endif + r->s128 = int128_sub(a->s128, b->s128); } -void helper_vsubeuqm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) +void helper_VSUBEUQM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { -#ifdef CONFIG_INT128 - r->u128 = a->u128 + ~b->u128 + (c->u128 & 1); -#else - ppc_avr_t tmp, sum; - - avr_qw_not(&tmp, *b); - avr_qw_add(&sum, *a, tmp); - - tmp.VsrD(0) = 0; - tmp.VsrD(1) = c->VsrD(1) & 1; - avr_qw_add(r, sum, tmp); -#endif + r->s128 = int128_add(int128_add(a->s128, int128_not(b->s128)), + int128_make64(int128_getlo(c->s128) & 1)); } -void helper_vsubcuq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) +void helper_VSUBCUQ(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) { -#ifdef CONFIG_INT128 - r->u128 = (~a->u128 < ~b->u128) || - (a->u128 + ~b->u128 == (__uint128_t)-1); -#else - int carry = (avr_qw_cmpu(*a, *b) > 0); - if (!carry) { - ppc_avr_t tmp; - avr_qw_not(&tmp, *b); - avr_qw_add(&tmp, *a, tmp); - carry = ((tmp.VsrSD(0) == -1ull) && (tmp.VsrSD(1) == -1ull)); - } + Int128 tmp = int128_not(b->s128); + + r->VsrD(1) = int128_ult(int128_not(a->s128), tmp) || + int128_eq(int128_add(a->s128, tmp), int128_makes64(-1)); r->VsrD(0) = 0; - r->VsrD(1) = carry; -#endif } -void helper_vsubecuq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) +void helper_VSUBECUQ(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { -#ifdef CONFIG_INT128 - r->u128 = - (~a->u128 < ~b->u128) || - ((c->u128 & 1) && (a->u128 + ~b->u128 == (__uint128_t)-1)); -#else - int carry_in = c->VsrD(1) & 1; - int carry_out = (avr_qw_cmpu(*a, *b) > 0); - if (!carry_out && carry_in) { - ppc_avr_t tmp; - avr_qw_not(&tmp, *b); - avr_qw_add(&tmp, *a, tmp); - carry_out = ((tmp.VsrD(0) == -1ull) && (tmp.VsrD(1) == -1ull)); - } + Int128 tmp = int128_not(b->s128); + bool carry_out = int128_ult(int128_not(a->s128), tmp), + carry_in = int128_getlo(c->s128) & 1; + r->VsrD(1) = carry_out || (carry_in && int128_eq(int128_add(a->s128, tmp), + int128_makes64(-1))); r->VsrD(0) = 0; - r->VsrD(1) = carry_out; -#endif } #define BCD_PLUS_PREF_1 0xC diff --git a/target/ppc/internal.h b/target/ppc/internal.h index 2add128..467f304 100644 --- a/target/ppc/internal.h +++ b/target/ppc/internal.h @@ -159,9 +159,6 @@ EXTRACT_HELPER(FPL, 25, 1); EXTRACT_HELPER(FPFLM, 17, 8); EXTRACT_HELPER(FPW, 16, 1); -/* mffscrni */ -EXTRACT_HELPER(RM, 11, 2); - /* addpcis */ EXTRACT_HELPER_SPLIT_3(DX, 10, 6, 6, 5, 16, 1, 1, 0, 0) #if defined(TARGET_PPC64) diff --git a/target/ppc/translate/fixedpoint-impl.c.inc b/target/ppc/translate/fixedpoint-impl.c.inc index 1aab32b..cb0097b 100644 --- a/target/ppc/translate/fixedpoint-impl.c.inc +++ b/target/ppc/translate/fixedpoint-impl.c.inc @@ -492,3 +492,54 @@ static bool trans_PEXTD(DisasContext *ctx, arg_X *a) #endif return true; } + +static bool trans_ADDG6S(DisasContext *ctx, arg_X *a) +{ + const uint64_t carry_bits = 0x1111111111111111ULL; + TCGv t0, t1, carry, zero = tcg_constant_tl(0); + + REQUIRE_INSNS_FLAGS2(ctx, BCDA_ISA206); + + t0 = tcg_temp_new(); + t1 = tcg_const_tl(0); + carry = tcg_const_tl(0); + + for (int i = 0; i < 16; i++) { + tcg_gen_shri_tl(t0, cpu_gpr[a->ra], i * 4); + tcg_gen_andi_tl(t0, t0, 0xf); + tcg_gen_add_tl(t1, t1, t0); + + tcg_gen_shri_tl(t0, cpu_gpr[a->rb], i * 4); + tcg_gen_andi_tl(t0, t0, 0xf); + tcg_gen_add_tl(t1, t1, t0); + + tcg_gen_andi_tl(t1, t1, 0x10); + tcg_gen_setcond_tl(TCG_COND_NE, t1, t1, zero); + + tcg_gen_shli_tl(t0, t1, i * 4); + tcg_gen_or_tl(carry, carry, t0); + } + + tcg_gen_xori_tl(carry, carry, (target_long)carry_bits); + tcg_gen_muli_tl(cpu_gpr[a->rt], carry, 6); + + tcg_temp_free(t0); + tcg_temp_free(t1); + tcg_temp_free(carry); + + return true; +} + +static bool trans_CDTBCD(DisasContext *ctx, arg_X_sa *a) +{ + REQUIRE_INSNS_FLAGS2(ctx, BCDA_ISA206); + gen_helper_CDTBCD(cpu_gpr[a->ra], cpu_gpr[a->rs]); + return true; +} + +static bool trans_CBCDTD(DisasContext *ctx, arg_X_sa *a) +{ + REQUIRE_INSNS_FLAGS2(ctx, BCDA_ISA206); + gen_helper_CBCDTD(cpu_gpr[a->ra], cpu_gpr[a->rs]); + return true; +} diff --git a/target/ppc/translate/fp-impl.c.inc b/target/ppc/translate/fp-impl.c.inc index f9b58b8..319513d 100644 --- a/target/ppc/translate/fp-impl.c.inc +++ b/target/ppc/translate/fp-impl.c.inc @@ -615,141 +615,162 @@ static void gen_mcrfs(DisasContext *ctx) tcg_temp_free_i64(tnew_fpscr); } -/* mffs */ -static void gen_mffs(DisasContext *ctx) +static TCGv_i64 place_from_fpscr(int rt, uint64_t mask) { - TCGv_i64 t0; - if (unlikely(!ctx->fpu_enabled)) { - gen_exception(ctx, POWERPC_EXCP_FPU); - return; - } - t0 = tcg_temp_new_i64(); + TCGv_i64 fpscr = tcg_temp_new_i64(); + TCGv_i64 fpscr_masked = tcg_temp_new_i64(); + + tcg_gen_extu_tl_i64(fpscr, cpu_fpscr); + tcg_gen_andi_i64(fpscr_masked, fpscr, mask); + set_fpr(rt, fpscr_masked); + + tcg_temp_free_i64(fpscr_masked); + + return fpscr; +} + +static void store_fpscr_masked(TCGv_i64 fpscr, uint64_t clear_mask, + TCGv_i64 set_mask, uint32_t store_mask) +{ + TCGv_i64 fpscr_masked = tcg_temp_new_i64(); + TCGv_i32 st_mask = tcg_constant_i32(store_mask); + + tcg_gen_andi_i64(fpscr_masked, fpscr, ~clear_mask); + tcg_gen_or_i64(fpscr_masked, fpscr_masked, set_mask); + gen_helper_store_fpscr(cpu_env, fpscr_masked, st_mask); + + tcg_temp_free_i64(fpscr_masked); +} + +static bool trans_MFFS(DisasContext *ctx, arg_X_t_rc *a) +{ + TCGv_i64 fpscr; + + REQUIRE_FPU(ctx); + gen_reset_fpstatus(); - tcg_gen_extu_tl_i64(t0, cpu_fpscr); - set_fpr(rD(ctx->opcode), t0); - if (unlikely(Rc(ctx->opcode))) { + fpscr = place_from_fpscr(a->rt, UINT64_MAX); + if (a->rc) { gen_set_cr1_from_fpscr(ctx); } - tcg_temp_free_i64(t0); + + tcg_temp_free_i64(fpscr); + + return true; } -/* mffsl */ -static void gen_mffsl(DisasContext *ctx) +static bool trans_MFFSCE(DisasContext *ctx, arg_X_t *a) { - TCGv_i64 t0; + TCGv_i64 fpscr; - if (unlikely(!(ctx->insns_flags2 & PPC2_ISA300))) { - return gen_mffs(ctx); - } + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_FPU(ctx); - if (unlikely(!ctx->fpu_enabled)) { - gen_exception(ctx, POWERPC_EXCP_FPU); - return; - } - t0 = tcg_temp_new_i64(); gen_reset_fpstatus(); - tcg_gen_extu_tl_i64(t0, cpu_fpscr); - /* Mask everything except mode, status, and enables. */ - tcg_gen_andi_i64(t0, t0, FP_DRN | FP_STATUS | FP_ENABLES | FP_RN); - set_fpr(rD(ctx->opcode), t0); - tcg_temp_free_i64(t0); + fpscr = place_from_fpscr(a->rt, UINT64_MAX); + store_fpscr_masked(fpscr, FP_ENABLES, tcg_constant_i64(0), 0x0003); + + tcg_temp_free_i64(fpscr); + + return true; } -/* mffsce */ -static void gen_mffsce(DisasContext *ctx) +static bool trans_MFFSCRN(DisasContext *ctx, arg_X_tb *a) { - TCGv_i64 t0; - TCGv_i32 mask; - - if (unlikely(!(ctx->insns_flags2 & PPC2_ISA300))) { - return gen_mffs(ctx); - } + TCGv_i64 t1, fpscr; - if (unlikely(!ctx->fpu_enabled)) { - gen_exception(ctx, POWERPC_EXCP_FPU); - return; - } + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_FPU(ctx); - t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + get_fpr(t1, a->rb); + tcg_gen_andi_i64(t1, t1, FP_RN); gen_reset_fpstatus(); - tcg_gen_extu_tl_i64(t0, cpu_fpscr); - set_fpr(rD(ctx->opcode), t0); + fpscr = place_from_fpscr(a->rt, FP_DRN | FP_ENABLES | FP_NI | FP_RN); + store_fpscr_masked(fpscr, FP_RN, t1, 0x0001); - /* Clear exception enable bits in the FPSCR. */ - tcg_gen_andi_i64(t0, t0, ~FP_ENABLES); - mask = tcg_const_i32(0x0003); - gen_helper_store_fpscr(cpu_env, t0, mask); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(fpscr); - tcg_temp_free_i32(mask); - tcg_temp_free_i64(t0); + return true; } -static void gen_helper_mffscrn(DisasContext *ctx, TCGv_i64 t1) +static bool trans_MFFSCDRN(DisasContext *ctx, arg_X_tb *a) { - TCGv_i64 t0 = tcg_temp_new_i64(); - TCGv_i32 mask = tcg_const_i32(0x0001); + TCGv_i64 t1, fpscr; - gen_reset_fpstatus(); - tcg_gen_extu_tl_i64(t0, cpu_fpscr); - tcg_gen_andi_i64(t0, t0, FP_DRN | FP_ENABLES | FP_RN); - set_fpr(rD(ctx->opcode), t0); + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_FPU(ctx); - /* Mask FPSCR value to clear RN. */ - tcg_gen_andi_i64(t0, t0, ~FP_RN); + t1 = tcg_temp_new_i64(); + get_fpr(t1, a->rb); + tcg_gen_andi_i64(t1, t1, FP_DRN); - /* Merge RN into FPSCR value. */ - tcg_gen_or_i64(t0, t0, t1); + gen_reset_fpstatus(); + fpscr = place_from_fpscr(a->rt, FP_DRN | FP_ENABLES | FP_NI | FP_RN); + store_fpscr_masked(fpscr, FP_DRN, t1, 0x0100); - gen_helper_store_fpscr(cpu_env, t0, mask); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(fpscr); - tcg_temp_free_i32(mask); - tcg_temp_free_i64(t0); + return true; } -/* mffscrn */ -static void gen_mffscrn(DisasContext *ctx) +static bool trans_MFFSCRNI(DisasContext *ctx, arg_X_imm2 *a) { - TCGv_i64 t1; - - if (unlikely(!(ctx->insns_flags2 & PPC2_ISA300))) { - return gen_mffs(ctx); - } + TCGv_i64 t1, fpscr; - if (unlikely(!ctx->fpu_enabled)) { - gen_exception(ctx, POWERPC_EXCP_FPU); - return; - } + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_FPU(ctx); t1 = tcg_temp_new_i64(); - get_fpr(t1, rB(ctx->opcode)); - /* Mask FRB to get just RN. */ - tcg_gen_andi_i64(t1, t1, FP_RN); + tcg_gen_movi_i64(t1, a->imm); - gen_helper_mffscrn(ctx, t1); + gen_reset_fpstatus(); + fpscr = place_from_fpscr(a->rt, FP_DRN | FP_ENABLES | FP_NI | FP_RN); + store_fpscr_masked(fpscr, FP_RN, t1, 0x0001); tcg_temp_free_i64(t1); + tcg_temp_free_i64(fpscr); + + return true; } -/* mffscrni */ -static void gen_mffscrni(DisasContext *ctx) +static bool trans_MFFSCDRNI(DisasContext *ctx, arg_X_imm3 *a) { - TCGv_i64 t1; + TCGv_i64 t1, fpscr; - if (unlikely(!(ctx->insns_flags2 & PPC2_ISA300))) { - return gen_mffs(ctx); - } - - if (unlikely(!ctx->fpu_enabled)) { - gen_exception(ctx, POWERPC_EXCP_FPU); - return; - } + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_FPU(ctx); - t1 = tcg_const_i64((uint64_t)RM(ctx->opcode)); + t1 = tcg_temp_new_i64(); + tcg_gen_movi_i64(t1, (uint64_t)a->imm << FPSCR_DRN0); - gen_helper_mffscrn(ctx, t1); + gen_reset_fpstatus(); + fpscr = place_from_fpscr(a->rt, FP_DRN | FP_ENABLES | FP_NI | FP_RN); + store_fpscr_masked(fpscr, FP_DRN, t1, 0x0100); tcg_temp_free_i64(t1); + tcg_temp_free_i64(fpscr); + + return true; +} + +static bool trans_MFFSL(DisasContext *ctx, arg_X_t *a) +{ + TCGv_i64 fpscr; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_FPU(ctx); + + gen_reset_fpstatus(); + fpscr = place_from_fpscr(a->rt, + FP_DRN | FP_STATUS | FP_ENABLES | FP_NI | FP_RN); + + tcg_temp_free_i64(fpscr); + + return true; } /* mtfsb0 */ diff --git a/target/ppc/translate/fp-ops.c.inc b/target/ppc/translate/fp-ops.c.inc index 0538ab2..1b65f5a 100644 --- a/target/ppc/translate/fp-ops.c.inc +++ b/target/ppc/translate/fp-ops.c.inc @@ -74,15 +74,6 @@ GEN_HANDLER_E(fcpsgn, 0x3F, 0x08, 0x00, 0x00000000, PPC_NONE, PPC2_ISA205), GEN_HANDLER_E(fmrgew, 0x3F, 0x06, 0x1E, 0x00000001, PPC_NONE, PPC2_VSX207), GEN_HANDLER_E(fmrgow, 0x3F, 0x06, 0x1A, 0x00000001, PPC_NONE, PPC2_VSX207), GEN_HANDLER(mcrfs, 0x3F, 0x00, 0x02, 0x0063F801, PPC_FLOAT), -GEN_HANDLER_E_2(mffs, 0x3F, 0x07, 0x12, 0x00, 0x00000000, PPC_FLOAT, PPC_NONE), -GEN_HANDLER_E_2(mffsce, 0x3F, 0x07, 0x12, 0x01, 0x00000000, PPC_FLOAT, - PPC2_ISA300), -GEN_HANDLER_E_2(mffsl, 0x3F, 0x07, 0x12, 0x18, 0x00000000, PPC_FLOAT, - PPC2_ISA300), -GEN_HANDLER_E_2(mffscrn, 0x3F, 0x07, 0x12, 0x16, 0x00000000, PPC_FLOAT, - PPC_NONE), -GEN_HANDLER_E_2(mffscrni, 0x3F, 0x07, 0x12, 0x17, 0x00000000, PPC_FLOAT, - PPC_NONE), GEN_HANDLER(mtfsb0, 0x3F, 0x06, 0x02, 0x001FF800, PPC_FLOAT), GEN_HANDLER(mtfsb1, 0x3F, 0x06, 0x01, 0x001FF800, PPC_FLOAT), GEN_HANDLER(mtfsf, 0x3F, 0x07, 0x16, 0x00000000, PPC_FLOAT), diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc index 0b563be..e644ad3 100644 --- a/target/ppc/translate/vmx-impl.c.inc +++ b/target/ppc/translate/vmx-impl.c.inc @@ -1234,18 +1234,6 @@ GEN_VXFORM_SAT(vsubuws, MO_32, sub, ussub, 0, 26); GEN_VXFORM_SAT(vsubsbs, MO_8, sub, sssub, 0, 28); GEN_VXFORM_SAT(vsubshs, MO_16, sub, sssub, 0, 29); GEN_VXFORM_SAT(vsubsws, MO_32, sub, sssub, 0, 30); -GEN_VXFORM(vadduqm, 0, 4); -GEN_VXFORM(vaddcuq, 0, 5); -GEN_VXFORM3(vaddeuqm, 30, 0); -GEN_VXFORM3(vaddecuq, 30, 0); -GEN_VXFORM_DUAL(vaddeuqm, PPC_NONE, PPC2_ALTIVEC_207, \ - vaddecuq, PPC_NONE, PPC2_ALTIVEC_207) -GEN_VXFORM(vsubuqm, 0, 20); -GEN_VXFORM(vsubcuq, 0, 21); -GEN_VXFORM3(vsubeuqm, 31, 0); -GEN_VXFORM3(vsubecuq, 31, 0); -GEN_VXFORM_DUAL(vsubeuqm, PPC_NONE, PPC2_ALTIVEC_207, \ - vsubecuq, PPC_NONE, PPC2_ALTIVEC_207) GEN_VXFORM_TRANS(vsl, 2, 7); GEN_VXFORM_TRANS(vsr, 2, 11); GEN_VXFORM_ENV(vpkuhum, 7, 0); @@ -2572,6 +2560,12 @@ static bool do_va_helper(DisasContext *ctx, arg_VA *a, return true; } +TRANS_FLAGS2(ALTIVEC_207, VADDECUQ, do_va_helper, gen_helper_VADDECUQ) +TRANS_FLAGS2(ALTIVEC_207, VADDEUQM, do_va_helper, gen_helper_VADDEUQM) + +TRANS_FLAGS2(ALTIVEC_207, VSUBEUQM, do_va_helper, gen_helper_VSUBEUQM) +TRANS_FLAGS2(ALTIVEC_207, VSUBECUQ, do_va_helper, gen_helper_VSUBECUQ) + TRANS_FLAGS(ALTIVEC, VPERM, do_va_helper, gen_helper_VPERM) TRANS_FLAGS2(ISA300, VPERMR, do_va_helper, gen_helper_VPERMR) @@ -2717,7 +2711,6 @@ GEN_VXFORM_TRANS(vgbbd, 6, 20); GEN_VXFORM(vpmsumb, 4, 16) GEN_VXFORM(vpmsumh, 4, 17) GEN_VXFORM(vpmsumw, 4, 18) -GEN_VXFORM(vpmsumd, 4, 19) #define GEN_BCD(op) \ static void gen_##op(DisasContext *ctx) \ @@ -2862,11 +2855,6 @@ GEN_VXFORM_DUAL(vsubuwm, PPC_ALTIVEC, PPC_NONE, \ bcdus, PPC_NONE, PPC2_ISA300) GEN_VXFORM_DUAL(vsubsbs, PPC_ALTIVEC, PPC_NONE, \ bcdtrunc, PPC_NONE, PPC2_ISA300) -GEN_VXFORM_DUAL(vsubuqm, PPC2_ALTIVEC_207, PPC_NONE, \ - bcdtrunc, PPC_NONE, PPC2_ISA300) -GEN_VXFORM_DUAL(vsubcuq, PPC2_ALTIVEC_207, PPC_NONE, \ - bcdutrunc, PPC_NONE, PPC2_ISA300) - static void gen_vsbox(DisasContext *ctx) { @@ -3101,6 +3089,14 @@ static bool do_vx_helper(DisasContext *ctx, arg_VX *a, return true; } +TRANS_FLAGS2(ALTIVEC_207, VADDCUQ, do_vx_helper, gen_helper_VADDCUQ) +TRANS_FLAGS2(ALTIVEC_207, VADDUQM, do_vx_helper, gen_helper_VADDUQM) + +TRANS_FLAGS2(ALTIVEC_207, VPMSUMD, do_vx_helper, gen_helper_VPMSUMD) + +TRANS_FLAGS2(ALTIVEC_207, VSUBCUQ, do_vx_helper, gen_helper_VSUBCUQ) +TRANS_FLAGS2(ALTIVEC_207, VSUBUQM, do_vx_helper, gen_helper_VSUBUQM) + static bool do_vx_vmuleo(DisasContext *ctx, arg_VX *a, bool even, void (*gen_mul)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64)) { diff --git a/target/ppc/translate/vmx-ops.c.inc b/target/ppc/translate/vmx-ops.c.inc index d7cc578..a3a0fd0 100644 --- a/target/ppc/translate/vmx-ops.c.inc +++ b/target/ppc/translate/vmx-ops.c.inc @@ -126,12 +126,8 @@ GEN_VXFORM(vsubuws, 0, 26), GEN_VXFORM_DUAL(vsubsbs, bcdtrunc, 0, 28, PPC_ALTIVEC, PPC2_ISA300), GEN_VXFORM(vsubshs, 0, 29), GEN_VXFORM_DUAL(vsubsws, xpnd04_2, 0, 30, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_207(vadduqm, 0, 4), -GEN_VXFORM_207(vaddcuq, 0, 5), -GEN_VXFORM_DUAL(vaddeuqm, vaddecuq, 30, 0xFF, PPC_NONE, PPC2_ALTIVEC_207), -GEN_VXFORM_DUAL(vsubuqm, bcdtrunc, 0, 20, PPC2_ALTIVEC_207, PPC2_ISA300), -GEN_VXFORM_DUAL(vsubcuq, bcdutrunc, 0, 21, PPC2_ALTIVEC_207, PPC2_ISA300), -GEN_VXFORM_DUAL(vsubeuqm, vsubecuq, 31, 0xFF, PPC_NONE, PPC2_ALTIVEC_207), +GEN_VXFORM_300(bcdtrunc, 0, 20), +GEN_VXFORM_300(bcdutrunc, 0, 21), GEN_VXFORM(vsl, 2, 7), GEN_VXFORM(vsr, 2, 11), GEN_VXFORM(vpkuhum, 7, 0), @@ -237,7 +233,6 @@ GEN_VXFORM_207(vgbbd, 6, 20), GEN_VXFORM_207(vpmsumb, 4, 16), GEN_VXFORM_207(vpmsumh, 4, 17), GEN_VXFORM_207(vpmsumw, 4, 18), -GEN_VXFORM_207(vpmsumd, 4, 19), GEN_VXFORM_207(vsbox, 4, 23), diff --git a/tests/tcg/ppc64/Makefile.target b/tests/tcg/ppc64/Makefile.target index babd209..331fae6 100644 --- a/tests/tcg/ppc64/Makefile.target +++ b/tests/tcg/ppc64/Makefile.target @@ -11,6 +11,7 @@ endif $(PPC64_TESTS): CFLAGS += -mpower8-vector PPC64_TESTS += mtfsf +PPC64_TESTS += mffsce ifneq ($(CROSS_CC_HAS_POWER10),) PPC64_TESTS += byte_reverse sha512-vector diff --git a/tests/tcg/ppc64le/Makefile.target b/tests/tcg/ppc64le/Makefile.target index 5b0eb5e..6ca3003 100644 --- a/tests/tcg/ppc64le/Makefile.target +++ b/tests/tcg/ppc64le/Makefile.target @@ -24,6 +24,7 @@ run-sha512-vector: QEMU_OPTS+=-cpu POWER10 run-plugin-sha512-vector-with-%: QEMU_OPTS+=-cpu POWER10 PPC64LE_TESTS += mtfsf +PPC64LE_TESTS += mffsce PPC64LE_TESTS += signal_save_restore_xer PPC64LE_TESTS += xxspltw diff --git a/tests/tcg/ppc64le/mffsce.c b/tests/tcg/ppc64le/mffsce.c new file mode 100644 index 0000000..20d882c --- /dev/null +++ b/tests/tcg/ppc64le/mffsce.c @@ -0,0 +1,37 @@ +#include <stdlib.h> +#include <stdint.h> +#include <assert.h> + +#define MTFSF(FLM, FRB) asm volatile ("mtfsf %0, %1" :: "i" (FLM), "f" (FRB)) +#define MFFS(FRT) asm("mffs %0" : "=f" (FRT)) +#define MFFSCE(FRT) asm("mffsce %0" : "=f" (FRT)) + +#define PPC_BIT_NR(nr) (63 - (nr)) + +#define FP_VE (1ull << PPC_BIT_NR(56)) +#define FP_UE (1ull << PPC_BIT_NR(58)) +#define FP_ZE (1ull << PPC_BIT_NR(59)) +#define FP_XE (1ull << PPC_BIT_NR(60)) +#define FP_NI (1ull << PPC_BIT_NR(61)) +#define FP_RN1 (1ull << PPC_BIT_NR(63)) + +int main(void) +{ + uint64_t frt, fpscr; + uint64_t test_value = FP_VE | FP_UE | FP_ZE | + FP_XE | FP_NI | FP_RN1; + MTFSF(0b11111111, test_value); /* set test value to cpu fpscr */ + MFFSCE(frt); + MFFS(fpscr); /* read the value that mffsce stored to cpu fpscr */ + + /* the returned value should be as the cpu fpscr was before */ + assert((frt & 0xff) == test_value); + + /* + * the cpu fpscr last 3 bits should be unchanged + * and enable bits should be unset + */ + assert((fpscr & 0xff) == (test_value & 0x7)); + + return 0; +} |