diff options
-rw-r--r-- | device_tree.c | 14 | ||||
-rw-r--r-- | hw/pci-host/ppce500.c | 113 | ||||
-rw-r--r-- | hw/ppc/e500.c | 36 | ||||
-rw-r--r-- | hw/ppc/e500.h | 5 | ||||
-rw-r--r-- | hw/ppc/e500plat.c | 5 | ||||
-rw-r--r-- | hw/ppc/mpc8544ds.c | 11 | ||||
-rw-r--r-- | hw/ppc/ppc.c | 4 | ||||
-rw-r--r-- | hw/ppc/spapr.c | 62 | ||||
-rw-r--r-- | hw/ppc/spapr_iommu.c | 6 | ||||
-rw-r--r-- | include/hw/ppc/spapr.h | 1 | ||||
-rw-r--r-- | pc-bios/README | 2 | ||||
-rw-r--r-- | pc-bios/slof.bin | bin | 923896 -> 911704 bytes | |||
m--------- | roms/SLOF | 0 | ||||
-rw-r--r-- | target-ppc/cpu.h | 26 | ||||
-rw-r--r-- | target-ppc/fpu_helper.c | 85 | ||||
-rw-r--r-- | target-ppc/helper.h | 4 | ||||
-rw-r--r-- | target-ppc/kvm.c | 20 | ||||
-rw-r--r-- | target-ppc/mem_helper.c | 22 | ||||
-rw-r--r-- | target-ppc/translate.c | 271 | ||||
-rw-r--r-- | target-ppc/translate_init.c | 5 |
20 files changed, 537 insertions, 155 deletions
diff --git a/device_tree.c b/device_tree.c index df9eed9cbc..4cb1cd50aa 100644 --- a/device_tree.c +++ b/device_tree.c @@ -324,6 +324,7 @@ int qemu_fdt_setprop_sized_cells_from_array(void *fdt, uint64_t value; int cellnum, vnum, ncells; uint32_t hival; + int ret; propcells = g_new0(uint32_t, numvalues * 2); @@ -331,18 +332,23 @@ int qemu_fdt_setprop_sized_cells_from_array(void *fdt, for (vnum = 0; vnum < numvalues; vnum++) { ncells = values[vnum * 2]; if (ncells != 1 && ncells != 2) { - return -1; + ret = -1; + goto out; } value = values[vnum * 2 + 1]; hival = cpu_to_be32(value >> 32); if (ncells > 1) { propcells[cellnum++] = hival; } else if (hival != 0) { - return -1; + ret = -1; + goto out; } propcells[cellnum++] = cpu_to_be32(value); } - return qemu_fdt_setprop(fdt, node_path, property, propcells, - cellnum * sizeof(uint32_t)); + ret = qemu_fdt_setprop(fdt, node_path, property, propcells, + cellnum * sizeof(uint32_t)); +out: + g_free(propcells); + return ret; } diff --git a/hw/pci-host/ppce500.c b/hw/pci-host/ppce500.c index 1b4c0f0023..574f8b2efb 100644 --- a/hw/pci-host/ppce500.c +++ b/hw/pci-host/ppce500.c @@ -62,11 +62,19 @@ #define PPCE500_PCI_NR_POBS 5 #define PPCE500_PCI_NR_PIBS 3 +#define PIWAR_EN 0x80000000 /* Enable */ +#define PIWAR_PF 0x20000000 /* prefetch */ +#define PIWAR_TGI_LOCAL 0x00f00000 /* target - local memory */ +#define PIWAR_READ_SNOOP 0x00050000 +#define PIWAR_WRITE_SNOOP 0x00005000 +#define PIWAR_SZ_MASK 0x0000003f + struct pci_outbound { uint32_t potar; uint32_t potear; uint32_t powbar; uint32_t powar; + MemoryRegion mem; }; struct pci_inbound { @@ -74,6 +82,7 @@ struct pci_inbound { uint32_t piwbar; uint32_t piwbear; uint32_t piwar; + MemoryRegion mem; }; #define TYPE_PPC_E500_PCI_HOST_BRIDGE "e500-pcihost" @@ -91,10 +100,13 @@ struct PPCE500PCIState { uint32_t irq_num[PCI_NUM_PINS]; uint32_t first_slot; uint32_t first_pin_irq; + AddressSpace bm_as; + MemoryRegion bm; /* mmio maps */ MemoryRegion container; MemoryRegion iomem; MemoryRegion pio; + MemoryRegion busmem; }; #define TYPE_PPC_E500_PCI_BRIDGE "e500-host-bridge" @@ -181,6 +193,71 @@ static uint64_t pci_reg_read4(void *opaque, hwaddr addr, return value; } +/* DMA mapping */ +static void e500_update_piw(PPCE500PCIState *pci, int idx) +{ + uint64_t tar = ((uint64_t)pci->pib[idx].pitar) << 12; + uint64_t wbar = ((uint64_t)pci->pib[idx].piwbar) << 12; + uint64_t war = pci->pib[idx].piwar; + uint64_t size = 2ULL << (war & PIWAR_SZ_MASK); + MemoryRegion *address_space_mem = get_system_memory(); + MemoryRegion *mem = &pci->pib[idx].mem; + MemoryRegion *bm = &pci->bm; + char *name; + + if (memory_region_is_mapped(mem)) { + /* Before we modify anything, unmap and destroy the region */ + memory_region_del_subregion(bm, mem); + object_unparent(OBJECT(mem)); + } + + if (!(war & PIWAR_EN)) { + /* Not enabled, nothing to do */ + return; + } + + name = g_strdup_printf("PCI Inbound Window %d", idx); + memory_region_init_alias(mem, OBJECT(pci), name, address_space_mem, tar, + size); + memory_region_add_subregion_overlap(bm, wbar, mem, -1); + g_free(name); + + pci_debug("%s: Added window of size=%#lx from PCI=%#lx to CPU=%#lx\n", + __func__, size, wbar, tar); +} + +/* BAR mapping */ +static void e500_update_pow(PPCE500PCIState *pci, int idx) +{ + uint64_t tar = ((uint64_t)pci->pob[idx].potar) << 12; + uint64_t wbar = ((uint64_t)pci->pob[idx].powbar) << 12; + uint64_t war = pci->pob[idx].powar; + uint64_t size = 2ULL << (war & PIWAR_SZ_MASK); + MemoryRegion *mem = &pci->pob[idx].mem; + MemoryRegion *address_space_mem = get_system_memory(); + char *name; + + if (memory_region_is_mapped(mem)) { + /* Before we modify anything, unmap and destroy the region */ + memory_region_del_subregion(address_space_mem, mem); + object_unparent(OBJECT(mem)); + } + + if (!(war & PIWAR_EN)) { + /* Not enabled, nothing to do */ + return; + } + + name = g_strdup_printf("PCI Outbound Window %d", idx); + memory_region_init_alias(mem, OBJECT(pci), name, &pci->busmem, tar, + size); + memory_region_add_subregion(address_space_mem, wbar, mem); + g_free(name); + + pci_debug("%s: Added window of size=%#lx from CPU=%#lx to PCI=%#lx\n", + __func__, size, wbar, tar); +} + static void pci_reg_write4(void *opaque, hwaddr addr, uint64_t value, unsigned size) { @@ -199,18 +276,22 @@ static void pci_reg_write4(void *opaque, hwaddr addr, case PPCE500_PCI_OW3: case PPCE500_PCI_OW4: idx = (addr >> 5) & 0x7; - switch (addr & 0xC) { + switch (addr & 0x1F) { case PCI_POTAR: pci->pob[idx].potar = value; + e500_update_pow(pci, idx); break; case PCI_POTEAR: pci->pob[idx].potear = value; + e500_update_pow(pci, idx); break; case PCI_POWBAR: pci->pob[idx].powbar = value; + e500_update_pow(pci, idx); break; case PCI_POWAR: pci->pob[idx].powar = value; + e500_update_pow(pci, idx); break; default: break; @@ -221,18 +302,22 @@ static void pci_reg_write4(void *opaque, hwaddr addr, case PPCE500_PCI_IW2: case PPCE500_PCI_IW1: idx = ((addr >> 5) & 0x3) - 1; - switch (addr & 0xC) { + switch (addr & 0x1F) { case PCI_PITAR: pci->pib[idx].pitar = value; + e500_update_piw(pci, idx); break; case PCI_PIWBAR: pci->pib[idx].piwbar = value; + e500_update_piw(pci, idx); break; case PCI_PIWBEAR: pci->pib[idx].piwbear = value; + e500_update_piw(pci, idx); break; case PCI_PIWAR: pci->pib[idx].piwar = value; + e500_update_piw(pci, idx); break; default: break; @@ -349,13 +434,20 @@ static int e500_pcihost_bridge_initfn(PCIDevice *d) return 0; } +static AddressSpace *e500_pcihost_set_iommu(PCIBus *bus, void *opaque, + int devfn) +{ + PPCE500PCIState *s = opaque; + + return &s->bm_as; +} + static int e500_pcihost_initfn(SysBusDevice *dev) { PCIHostState *h; PPCE500PCIState *s; PCIBus *b; int i; - MemoryRegion *address_space_mem = get_system_memory(); h = PCI_HOST_BRIDGE(dev); s = PPC_E500_PCI_HOST_BRIDGE(dev); @@ -369,12 +461,22 @@ static int e500_pcihost_initfn(SysBusDevice *dev) } memory_region_init(&s->pio, OBJECT(s), "pci-pio", PCIE500_PCI_IOLEN); + memory_region_init(&s->busmem, OBJECT(s), "pci bus memory", UINT64_MAX); + + /* PIO lives at the bottom of our bus space */ + memory_region_add_subregion_overlap(&s->busmem, 0, &s->pio, -2); b = pci_register_bus(DEVICE(dev), NULL, mpc85xx_pci_set_irq, - mpc85xx_pci_map_irq, s, address_space_mem, - &s->pio, PCI_DEVFN(s->first_slot, 0), 4, TYPE_PCI_BUS); + mpc85xx_pci_map_irq, s, &s->busmem, &s->pio, + PCI_DEVFN(s->first_slot, 0), 4, TYPE_PCI_BUS); h->bus = b; + /* Set up PCI view of memory */ + memory_region_init(&s->bm, OBJECT(s), "bm-e500", UINT64_MAX); + memory_region_add_subregion(&s->bm, 0x0, &s->busmem); + address_space_init(&s->bm_as, &s->bm, "pci-bm"); + pci_setup_iommu(b, e500_pcihost_set_iommu, s); + pci_create_simple(b, 0, "e500-host-bridge"); memory_region_init(&s->container, OBJECT(h), "pci-container", PCIE500_ALL_SIZE); @@ -388,7 +490,6 @@ static int e500_pcihost_initfn(SysBusDevice *dev) memory_region_add_subregion(&s->container, PCIE500_CFGDATA, &h->data_mem); memory_region_add_subregion(&s->container, PCIE500_REG_BASE, &s->iomem); sysbus_init_mmio(dev, &s->container); - sysbus_init_mmio(dev, &s->pio); pci_bus_set_route_irq_fn(b, e500_route_intx_pin_to_irq); return 0; diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c index 2832fc0da4..7e17d180c6 100644 --- a/hw/ppc/e500.c +++ b/hw/ppc/e500.c @@ -51,21 +51,16 @@ #define RAM_SIZES_ALIGN (64UL << 20) /* TODO: parameterize */ -#define MPC8544_CCSRBAR_BASE 0xE0000000ULL #define MPC8544_CCSRBAR_SIZE 0x00100000ULL #define MPC8544_MPIC_REGS_OFFSET 0x40000ULL #define MPC8544_MSI_REGS_OFFSET 0x41600ULL #define MPC8544_SERIAL0_REGS_OFFSET 0x4500ULL #define MPC8544_SERIAL1_REGS_OFFSET 0x4600ULL #define MPC8544_PCI_REGS_OFFSET 0x8000ULL -#define MPC8544_PCI_REGS_BASE (MPC8544_CCSRBAR_BASE + \ - MPC8544_PCI_REGS_OFFSET) #define MPC8544_PCI_REGS_SIZE 0x1000ULL -#define MPC8544_PCI_IO 0xE1000000ULL #define MPC8544_UTIL_OFFSET 0xe0000ULL -#define MPC8544_SPIN_BASE 0xEF000000ULL #define MPC8XXX_GPIO_OFFSET 0x000FF000ULL -#define MPC8XXX_GPIO_IRQ 43 +#define MPC8XXX_GPIO_IRQ 47 struct boot_info { @@ -293,12 +288,12 @@ static int ppce500_load_device_tree(MachineState *machine, int len; uint32_t pci_ranges[14] = { - 0x2000000, 0x0, 0xc0000000, - 0x0, 0xc0000000, + 0x2000000, 0x0, params->pci_mmio_bus_base, + params->pci_mmio_base >> 32, params->pci_mmio_base, 0x0, 0x20000000, 0x1000000, 0x0, 0x0, - 0x0, 0xe1000000, + params->pci_pio_base >> 32, params->pci_pio_base, 0x0, 0x10000, }; QemuOpts *machine_opts = qemu_get_machine_opts(); @@ -389,7 +384,7 @@ static int ppce500_load_device_tree(MachineState *machine, CPUState *cpu; PowerPCCPU *pcpu; char cpu_name[128]; - uint64_t cpu_release_addr = MPC8544_SPIN_BASE + (i * 0x20); + uint64_t cpu_release_addr = params->spin_base + (i * 0x20); cpu = qemu_get_cpu(i); if (cpu == NULL) { @@ -426,7 +421,7 @@ static int ppce500_load_device_tree(MachineState *machine, qemu_fdt_add_subnode(fdt, "/aliases"); /* XXX These should go into their respective devices' code */ - snprintf(soc, sizeof(soc), "/soc@%llx", MPC8544_CCSRBAR_BASE); + snprintf(soc, sizeof(soc), "/soc@%"PRIx64, params->ccsrbar_base); qemu_fdt_add_subnode(fdt, soc); qemu_fdt_setprop_string(fdt, soc, "device_type", "soc"); qemu_fdt_setprop(fdt, soc, "compatible", compatible_sb, @@ -434,7 +429,7 @@ static int ppce500_load_device_tree(MachineState *machine, qemu_fdt_setprop_cell(fdt, soc, "#address-cells", 1); qemu_fdt_setprop_cell(fdt, soc, "#size-cells", 1); qemu_fdt_setprop_cells(fdt, soc, "ranges", 0x0, - MPC8544_CCSRBAR_BASE >> 32, MPC8544_CCSRBAR_BASE, + params->ccsrbar_base >> 32, params->ccsrbar_base, MPC8544_CCSRBAR_SIZE); /* XXX should contain a reasonable value */ qemu_fdt_setprop_cell(fdt, soc, "bus-frequency", 0); @@ -493,7 +488,8 @@ static int ppce500_load_device_tree(MachineState *machine, qemu_fdt_setprop_cell(fdt, msi, "phandle", msi_ph); qemu_fdt_setprop_cell(fdt, msi, "linux,phandle", msi_ph); - snprintf(pci, sizeof(pci), "/pci@%llx", MPC8544_PCI_REGS_BASE); + snprintf(pci, sizeof(pci), "/pci@%llx", + params->ccsrbar_base + MPC8544_PCI_REGS_OFFSET); qemu_fdt_add_subnode(fdt, pci); qemu_fdt_setprop_cell(fdt, pci, "cell-index", 0); qemu_fdt_setprop_string(fdt, pci, "compatible", "fsl,mpc8540-pci"); @@ -512,8 +508,10 @@ static int ppce500_load_device_tree(MachineState *machine, } qemu_fdt_setprop_cell(fdt, pci, "fsl,msi", msi_ph); qemu_fdt_setprop(fdt, pci, "ranges", pci_ranges, sizeof(pci_ranges)); - qemu_fdt_setprop_cells(fdt, pci, "reg", MPC8544_PCI_REGS_BASE >> 32, - MPC8544_PCI_REGS_BASE, 0, 0x1000); + qemu_fdt_setprop_cells(fdt, pci, "reg", + (params->ccsrbar_base + MPC8544_PCI_REGS_OFFSET) >> 32, + (params->ccsrbar_base + MPC8544_PCI_REGS_OFFSET), + 0, 0x1000); qemu_fdt_setprop_cell(fdt, pci, "clock-frequency", 66666666); qemu_fdt_setprop_cell(fdt, pci, "#interrupt-cells", 1); qemu_fdt_setprop_cell(fdt, pci, "#size-cells", 2); @@ -841,7 +839,7 @@ void ppce500_init(MachineState *machine, PPCE500Params *params) irqs[i][OPENPIC_OUTPUT_INT] = input[PPCE500_INPUT_INT]; irqs[i][OPENPIC_OUTPUT_CINT] = input[PPCE500_INPUT_CINT]; env->spr_cb[SPR_BOOKE_PIR].default_value = cs->cpu_index = i; - env->mpic_iack = MPC8544_CCSRBAR_BASE + + env->mpic_iack = params->ccsrbar_base + MPC8544_MPIC_REGS_OFFSET + 0xa0; ppc_booke_timers_init(cpu, 400000000, PPC_TIMER_E500); @@ -875,7 +873,7 @@ void ppce500_init(MachineState *machine, PPCE500Params *params) qdev_init_nofail(dev); ccsr = CCSR(dev); ccsr_addr_space = &ccsr->ccsr_space; - memory_region_add_subregion(address_space_mem, MPC8544_CCSRBAR_BASE, + memory_region_add_subregion(address_space_mem, params->ccsrbar_base, ccsr_addr_space); mpic = ppce500_init_mpic(params, ccsr_addr_space, irqs); @@ -917,8 +915,6 @@ void ppce500_init(MachineState *machine, PPCE500Params *params) if (!pci_bus) printf("couldn't create PCI controller!\n"); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, MPC8544_PCI_IO); - if (pci_bus) { /* Register network interfaces. */ for (i = 0; i < nb_nics; i++) { @@ -927,7 +923,7 @@ void ppce500_init(MachineState *machine, PPCE500Params *params) } /* Register spinning region */ - sysbus_create_simple("e500-spin", MPC8544_SPIN_BASE, NULL); + sysbus_create_simple("e500-spin", params->spin_base, NULL); if (cur_base < (32 * 1024 * 1024)) { /* u-boot occupies memory up to 32MB, so load blobs above */ diff --git a/hw/ppc/e500.h b/hw/ppc/e500.h index 9f61ab2b1c..ef224ea5e6 100644 --- a/hw/ppc/e500.h +++ b/hw/ppc/e500.h @@ -17,6 +17,11 @@ typedef struct PPCE500Params { hwaddr platform_bus_size; int platform_bus_first_irq; int platform_bus_num_irqs; + hwaddr ccsrbar_base; + hwaddr pci_pio_base; + hwaddr pci_mmio_base; + hwaddr pci_mmio_bus_base; + hwaddr spin_base; } PPCE500Params; void ppce500_init(MachineState *machine, PPCE500Params *params); diff --git a/hw/ppc/e500plat.c b/hw/ppc/e500plat.c index d50ae000ee..14b14eaa7d 100644 --- a/hw/ppc/e500plat.c +++ b/hw/ppc/e500plat.c @@ -41,6 +41,11 @@ static void e500plat_init(MachineState *machine) .platform_bus_size = (128ULL * 1024 * 1024), .platform_bus_first_irq = 5, .platform_bus_num_irqs = 10, + .ccsrbar_base = 0xFE0000000ULL, + .pci_pio_base = 0xFE1000000ULL, + .pci_mmio_base = 0xC00000000ULL, + .pci_mmio_bus_base = 0xE0000000ULL, + .spin_base = 0xFEF000000ULL, }; /* Older KVM versions don't support EPR which breaks guests when we announce diff --git a/hw/ppc/mpc8544ds.c b/hw/ppc/mpc8544ds.c index b99f74af75..3a3b141e43 100644 --- a/hw/ppc/mpc8544ds.c +++ b/hw/ppc/mpc8544ds.c @@ -15,6 +15,7 @@ #include "hw/boards.h" #include "sysemu/device_tree.h" #include "hw/ppc/openpic.h" +#include "qemu/error-report.h" static void mpc8544ds_fixup_devtree(PPCE500Params *params, void *fdt) { @@ -33,8 +34,18 @@ static void mpc8544ds_init(MachineState *machine) .pci_nr_slots = 2, .fixup_devtree = mpc8544ds_fixup_devtree, .mpic_version = OPENPIC_MODEL_FSL_MPIC_20, + .ccsrbar_base = 0xE0000000ULL, + .pci_mmio_base = 0xC0000000ULL, + .pci_mmio_bus_base = 0xC0000000ULL, + .pci_pio_base = 0xE1000000ULL, + .spin_base = 0xEF000000ULL, }; + if (machine->ram_size > 0xc0000000) { + error_report("The MPC8544DS board only supports up to 3GB of RAM"); + exit(1); + } + ppce500_init(machine, ¶ms); } diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c index bec82cd7a9..5ce565d5ec 100644 --- a/hw/ppc/ppc.c +++ b/hw/ppc/ppc.c @@ -844,7 +844,7 @@ static void timebase_pre_save(void *opaque) return; } - tb->time_of_the_day_ns = get_clock_realtime(); + tb->time_of_the_day_ns = qemu_clock_get_ns(QEMU_CLOCK_HOST); /* * tb_offset is only expected to be changed by migration so * there is no need to update it from KVM here @@ -873,7 +873,7 @@ static int timebase_post_load(void *opaque, int version_id) * We try to adjust timebase by downtime if host clocks are not * too much out of sync (1 second for now). */ - host_ns = get_clock_realtime(); + host_ns = qemu_clock_get_ns(QEMU_CLOCK_HOST); ns_diff = MAX(0, host_ns - tb_remote->time_of_the_day_ns); migration_duration_ns = MIN(NSEC_PER_SEC, ns_diff); migration_duration_tb = muldiv64(migration_duration_ns, freq, NSEC_PER_SEC); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 53c4116ed3..b560459e83 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -819,9 +819,16 @@ static void emulate_spapr_hypercall(PowerPCCPU *cpu) } } +#define HPTE(_table, _i) (void *)(((uint64_t *)(_table)) + ((_i) * 2)) +#define HPTE_VALID(_hpte) (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_VALID) +#define HPTE_DIRTY(_hpte) (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_HPTE_DIRTY) +#define CLEAN_HPTE(_hpte) ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY)) +#define DIRTY_HPTE(_hpte) ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY)) + static void spapr_reset_htab(sPAPREnvironment *spapr) { long shift; + int index; /* allocate hash page table. For now we always make this 16mb, * later we should probably make it scale to the size of guest @@ -833,6 +840,11 @@ static void spapr_reset_htab(sPAPREnvironment *spapr) /* Kernel handles htab, we don't need to allocate one */ spapr->htab_shift = shift; kvmppc_kern_htab = true; + + /* Tell readers to update their file descriptor */ + if (spapr->htab_fd >= 0) { + spapr->htab_fd_stale = true; + } } else { if (!spapr->htab) { /* Allocate an htab if we don't yet have one */ @@ -841,6 +853,10 @@ static void spapr_reset_htab(sPAPREnvironment *spapr) /* And clear it */ memset(spapr->htab, 0, HTAB_SIZE(spapr)); + + for (index = 0; index < HTAB_SIZE(spapr) / HASH_PTE_SIZE_64; index++) { + DIRTY_HPTE(HPTE(spapr->htab, index)); + } } /* Update the RMA size if necessary */ @@ -867,6 +883,28 @@ static int find_unknown_sysbus_device(SysBusDevice *sbdev, void *opaque) return 0; } +/* + * A guest reset will cause spapr->htab_fd to become stale if being used. + * Reopen the file descriptor to make sure the whole HTAB is properly read. + */ +static int spapr_check_htab_fd(sPAPREnvironment *spapr) +{ + int rc = 0; + + if (spapr->htab_fd_stale) { + close(spapr->htab_fd); + spapr->htab_fd = kvmppc_get_htab_fd(false); + if (spapr->htab_fd < 0) { + error_report("Unable to open fd for reading hash table from KVM: " + "%s", strerror(errno)); + rc = -1; + } + spapr->htab_fd_stale = false; + } + + return rc; +} + static void ppc_spapr_reset(void) { PowerPCCPU *first_ppc_cpu; @@ -986,11 +1024,6 @@ static const VMStateDescription vmstate_spapr = { }, }; -#define HPTE(_table, _i) (void *)(((uint64_t *)(_table)) + ((_i) * 2)) -#define HPTE_VALID(_hpte) (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_VALID) -#define HPTE_DIRTY(_hpte) (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_HPTE_DIRTY) -#define CLEAN_HPTE(_hpte) ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY)) - static int htab_save_setup(QEMUFile *f, void *opaque) { sPAPREnvironment *spapr = opaque; @@ -1005,6 +1038,7 @@ static int htab_save_setup(QEMUFile *f, void *opaque) assert(kvm_enabled()); spapr->htab_fd = kvmppc_get_htab_fd(false); + spapr->htab_fd_stale = false; if (spapr->htab_fd < 0) { fprintf(stderr, "Unable to open fd for reading hash table from KVM: %s\n", strerror(errno)); @@ -1037,7 +1071,7 @@ static void htab_save_first_pass(QEMUFile *f, sPAPREnvironment *spapr, /* Consume valid HPTEs */ chunkstart = index; - while ((index < htabslots) + while ((index < htabslots) && (index - chunkstart < USHRT_MAX) && HPTE_VALID(HPTE(spapr->htab, index))) { index++; CLEAN_HPTE(HPTE(spapr->htab, index)); @@ -1089,7 +1123,7 @@ static int htab_save_later_pass(QEMUFile *f, sPAPREnvironment *spapr, chunkstart = index; /* Consume valid dirty HPTEs */ - while ((index < htabslots) + while ((index < htabslots) && (index - chunkstart < USHRT_MAX) && HPTE_DIRTY(HPTE(spapr->htab, index)) && HPTE_VALID(HPTE(spapr->htab, index))) { CLEAN_HPTE(HPTE(spapr->htab, index)); @@ -1099,7 +1133,7 @@ static int htab_save_later_pass(QEMUFile *f, sPAPREnvironment *spapr, invalidstart = index; /* Consume invalid dirty HPTEs */ - while ((index < htabslots) + while ((index < htabslots) && (index - invalidstart < USHRT_MAX) && HPTE_DIRTY(HPTE(spapr->htab, index)) && !HPTE_VALID(HPTE(spapr->htab, index))) { CLEAN_HPTE(HPTE(spapr->htab, index)); @@ -1157,6 +1191,11 @@ static int htab_save_iterate(QEMUFile *f, void *opaque) if (!spapr->htab) { assert(kvm_enabled()); + rc = spapr_check_htab_fd(spapr); + if (rc < 0) { + return rc; + } + rc = kvmppc_save_htab(f, spapr->htab_fd, MAX_KVM_BUF_SIZE, MAX_ITERATION_NS); if (rc < 0) { @@ -1188,6 +1227,11 @@ static int htab_save_complete(QEMUFile *f, void *opaque) assert(kvm_enabled()); + rc = spapr_check_htab_fd(spapr); + if (rc < 0) { + return rc; + } + rc = kvmppc_save_htab(f, spapr->htab_fd, MAX_KVM_BUF_SIZE, -1); if (rc < 0) { return rc; @@ -1438,7 +1482,7 @@ static void ppc_spapr_init(MachineState *machine) } if (spapr->rtas_size > RTAS_MAX_SIZE) { hw_error("RTAS too big ! 0x%zx bytes (max is 0x%x)\n", - spapr->rtas_size, RTAS_MAX_SIZE); + (size_t)spapr->rtas_size, RTAS_MAX_SIZE); exit(1); } g_free(filename); diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index 6c91d8edd8..da474740c0 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -173,9 +173,9 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn, return tcet; } -static void spapr_tce_table_finalize(Object *obj) +static void spapr_tce_table_unrealize(DeviceState *dev, Error **errp) { - sPAPRTCETable *tcet = SPAPR_TCE_TABLE(obj); + sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev); QLIST_REMOVE(tcet, list); @@ -420,6 +420,7 @@ static void spapr_tce_table_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); dc->init = spapr_tce_table_realize; dc->reset = spapr_tce_reset; + dc->unrealize = spapr_tce_table_unrealize; QLIST_INIT(&spapr_tce_tables); @@ -435,7 +436,6 @@ static TypeInfo spapr_tce_table_info = { .parent = TYPE_DEVICE, .instance_size = sizeof(sPAPRTCETable), .class_init = spapr_tce_table_class_init, - .instance_finalize = spapr_tce_table_finalize, }; static void register_types(void) diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index 749daf4dd7..716bff43bf 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -37,6 +37,7 @@ typedef struct sPAPREnvironment { int htab_save_index; bool htab_first_pass; int htab_fd; + bool htab_fd_stale; } sPAPREnvironment; #define H_SUCCESS 0 diff --git a/pc-bios/README b/pc-bios/README index edfadd7d38..8a85e69d3b 100644 --- a/pc-bios/README +++ b/pc-bios/README @@ -17,7 +17,7 @@ - SLOF (Slimline Open Firmware) is a free IEEE 1275 Open Firmware implementation for certain IBM POWER hardware. The sources are at https://github.com/aik/SLOF, and the image currently in qemu is - built from git tag qemu-slof-20140630. + built from git tag qemu-slof-20141202. - sgabios (the Serial Graphics Adapter option ROM) provides a means for legacy x86 software to communicate with an attached serial console as diff --git a/pc-bios/slof.bin b/pc-bios/slof.bin Binary files differindex 69b0a5dbc3..031e3063a2 100644 --- a/pc-bios/slof.bin +++ b/pc-bios/slof.bin diff --git a/roms/SLOF b/roms/SLOF -Subproject f284ab3f03ae69a20e1ae966f6ddf76da33cbf7 +Subproject a70dbda2e21f6e438b3617c44ff180c3418dc30 diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h index f42589c478..c62097bb8a 100644 --- a/target-ppc/cpu.h +++ b/target-ppc/cpu.h @@ -559,6 +559,26 @@ struct ppc_slb_t { #define ESR_VLEMI (1 << (63 - 58)) /* VLE operation */ #define ESR_MIF (1 << (63 - 62)) /* Misaligned instruction (VLE) */ +/* Transaction EXception And Summary Register bits */ +#define TEXASR_FAILURE_PERSISTENT (63 - 7) +#define TEXASR_DISALLOWED (63 - 8) +#define TEXASR_NESTING_OVERFLOW (63 - 9) +#define TEXASR_FOOTPRINT_OVERFLOW (63 - 10) +#define TEXASR_SELF_INDUCED_CONFLICT (63 - 11) +#define TEXASR_NON_TRANSACTIONAL_CONFLICT (63 - 12) +#define TEXASR_TRANSACTION_CONFLICT (63 - 13) +#define TEXASR_TRANSLATION_INVALIDATION_CONFLICT (63 - 14) +#define TEXASR_IMPLEMENTATION_SPECIFIC (63 - 15) +#define TEXASR_INSTRUCTION_FETCH_CONFLICT (63 - 16) +#define TEXASR_ABORT (63 - 31) +#define TEXASR_SUSPENDED (63 - 32) +#define TEXASR_PRIVILEGE_HV (63 - 34) +#define TEXASR_PRIVILEGE_PR (63 - 35) +#define TEXASR_FAILURE_SUMMARY (63 - 36) +#define TEXASR_TFIAR_EXACT (63 - 37) +#define TEXASR_ROT (63 - 38) +#define TEXASR_TRANSACTION_LEVEL (63 - 52) /* 12 bits */ + enum { POWERPC_FLAG_NONE = 0x00000000, /* Flag for MSR bit 25 signification (VRE/SPE) */ @@ -585,6 +605,8 @@ enum { POWERPC_FLAG_CFAR = 0x00040000, /* Has VSX */ POWERPC_FLAG_VSX = 0x00080000, + /* Has Transaction Memory (ISA 2.07) */ + POWERPC_FLAG_TM = 0x00100000, }; /*****************************************************************************/ @@ -2011,6 +2033,8 @@ enum { PPC2_ISA207S = 0x0000000000008000ULL, /* Double precision floating point conversion for signed integer 64 */ PPC2_FP_CVT_S64 = 0x0000000000010000ULL, + /* Transactional Memory (ISA 2.07, Book II) */ + PPC2_TM = 0x0000000000020000ULL, #define PPC_TCG_INSNS2 (PPC2_BOOKE206 | PPC2_VSX | PPC2_PRCNTL | PPC2_DBRX | \ PPC2_ISA205 | PPC2_VSX207 | PPC2_PERM_ISA206 | \ @@ -2018,7 +2042,7 @@ enum { PPC2_FP_CVT_ISA206 | PPC2_FP_TST_ISA206 | \ PPC2_BCTAR_ISA207 | PPC2_LSQ_ISA207 | \ PPC2_ALTIVEC_207 | PPC2_ISA207S | PPC2_DFP | \ - PPC2_FP_CVT_S64) + PPC2_FP_CVT_S64 | PPC2_TM) }; /*****************************************************************************/ diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c index 7f74466f32..6cceffc556 100644 --- a/target-ppc/fpu_helper.c +++ b/target-ppc/fpu_helper.c @@ -19,6 +19,9 @@ #include "cpu.h" #include "exec/helper-proto.h" +#define float64_snan_to_qnan(x) ((x) | 0x0008000000000000ULL) +#define float32_snan_to_qnan(x) ((x) | 0x00400000) + /*****************************************************************************/ /* Floating point operations helpers */ uint64_t helper_float32_to_float64(CPUPPCState *env, uint32_t arg) @@ -60,59 +63,55 @@ static inline int ppc_float64_get_unbiased_exp(float64 f) return ((f >> 52) & 0x7FF) - 1023; } -uint32_t helper_compute_fprf(CPUPPCState *env, uint64_t arg, uint32_t set_fprf) +void helper_compute_fprf(CPUPPCState *env, uint64_t arg) { CPU_DoubleU farg; int isneg; - int ret; + int fprf; farg.ll = arg; isneg = float64_is_neg(farg.d); if (unlikely(float64_is_any_nan(farg.d))) { if (float64_is_signaling_nan(farg.d)) { /* Signaling NaN: flags are undefined */ - ret = 0x00; + fprf = 0x00; } else { /* Quiet NaN */ - ret = 0x11; + fprf = 0x11; } } else if (unlikely(float64_is_infinity(farg.d))) { /* +/- infinity */ if (isneg) { - ret = 0x09; + fprf = 0x09; } else { - ret = 0x05; + fprf = 0x05; } } else { if (float64_is_zero(farg.d)) { /* +/- zero */ if (isneg) { - ret = 0x12; + fprf = 0x12; } else { - ret = 0x02; + fprf = 0x02; } } else { if (isden(farg.d)) { /* Denormalized numbers */ - ret = 0x10; + fprf = 0x10; } else { /* Normalized numbers */ - ret = 0x00; + fprf = 0x00; } if (isneg) { - ret |= 0x08; + fprf |= 0x08; } else { - ret |= 0x04; + fprf |= 0x04; } } } - if (set_fprf) { - /* We update FPSCR_FPRF */ - env->fpscr &= ~(0x1F << FPSCR_FPRF); - env->fpscr |= ret << FPSCR_FPRF; - } - /* We just need fpcc to update Rc1 */ - return ret & 0xF; + /* We update FPSCR_FPRF */ + env->fpscr &= ~(0x1F << FPSCR_FPRF); + env->fpscr |= fprf << FPSCR_FPRF; } /* Floating-point invalid operations exception */ @@ -920,14 +919,16 @@ uint64_t helper_fsqrt(CPUPPCState *env, uint64_t arg) farg.ll = arg; - if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { - /* Square root of a negative nonzero number */ - farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1); - } else { + if (unlikely(float64_is_any_nan(farg.d))) { if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN square root */ + /* sNaN reciprocal square root */ fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1); + farg.ll = float64_snan_to_qnan(farg.ll); } + } else if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { + /* Square root of a negative nonzero number */ + farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1); + } else { farg.d = float64_sqrt(farg.d, &env->fp_status); } return farg.ll; @@ -974,17 +975,20 @@ uint64_t helper_frsqrte(CPUPPCState *env, uint64_t arg) farg.ll = arg; - if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { - /* Reciprocal square root of a negative nonzero number */ - farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1); - } else { + if (unlikely(float64_is_any_nan(farg.d))) { if (unlikely(float64_is_signaling_nan(farg.d))) { /* sNaN reciprocal square root */ fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1); + farg.ll = float64_snan_to_qnan(farg.ll); } + } else if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { + /* Reciprocal square root of a negative nonzero number */ + farg.ll = fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1); + } else { farg.d = float64_sqrt(farg.d, &env->fp_status); farg.d = float64_div(float64_one, farg.d, &env->fp_status); } + return farg.ll; } @@ -1845,7 +1849,7 @@ void helper_##name(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ putVSR(xT(opcode), &xt, env); \ @@ -1900,7 +1904,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ \ @@ -1954,7 +1958,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ \ @@ -1995,7 +1999,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ \ @@ -2044,7 +2048,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ \ @@ -2094,7 +2098,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ \ @@ -2294,7 +2298,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt_out.fld, sfprf); \ + helper_compute_fprf(env, xt_out.fld); \ } \ } \ putVSR(xT(opcode), &xt_out, env); \ @@ -2382,9 +2386,6 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ VSX_SCALAR_CMP(xscmpodp, 1) VSX_SCALAR_CMP(xscmpudp, 0) -#define float64_snan_to_qnan(x) ((x) | 0x0008000000000000ULL) -#define float32_snan_to_qnan(x) ((x) | 0x00400000) - /* VSX_MAX_MIN - VSX floating point maximum/minimum * name - instruction mnemonic * op - operation (max or min) @@ -2504,7 +2505,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ if (sfprf) { \ helper_compute_fprf(env, ttp##_to_float64(xt.tfld, \ - &env->fp_status), sfprf); \ + &env->fp_status)); \ } \ } \ \ @@ -2614,7 +2615,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ xt.tfld = helper_frsp(env, xt.tfld); \ } \ if (sfprf) { \ - helper_compute_fprf(env, xt.tfld, sfprf); \ + helper_compute_fprf(env, xt.tfld); \ } \ } \ \ @@ -2669,7 +2670,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ xt.fld = tp##_round_to_int(xb.fld, &env->fp_status); \ } \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld, sfprf); \ + helper_compute_fprf(env, xt.fld); \ } \ } \ \ @@ -2709,7 +2710,7 @@ uint64_t helper_xsrsp(CPUPPCState *env, uint64_t xb) uint64_t xt = helper_frsp(env, xb); - helper_compute_fprf(env, xt, 1); + helper_compute_fprf(env, xt); helper_float_check_status(env); return xt; } diff --git a/target-ppc/helper.h b/target-ppc/helper.h index 210fd97f6a..869be1509d 100644 --- a/target-ppc/helper.h +++ b/target-ppc/helper.h @@ -52,7 +52,7 @@ DEF_HELPER_FLAGS_2(brinc, TCG_CALL_NO_RWG_SE, tl, tl, tl) DEF_HELPER_1(float_check_status, void, env) DEF_HELPER_1(reset_fpstatus, void, env) -DEF_HELPER_3(compute_fprf, i32, env, i64, i32) +DEF_HELPER_2(compute_fprf, void, env, i64) DEF_HELPER_3(store_fpscr, void, env, i64, i32) DEF_HELPER_2(fpscr_clrbit, void, env, i32) DEF_HELPER_2(fpscr_setbit, void, env, i32) @@ -665,3 +665,5 @@ DEF_HELPER_4(dscri, void, env, fprp, fprp, i32) DEF_HELPER_4(dscriq, void, env, fprp, fprp, i32) DEF_HELPER_4(dscli, void, env, fprp, fprp, i32) DEF_HELPER_4(dscliq, void, env, fprp, fprp, i32) + +DEF_HELPER_1(tbegin, void, env) diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c index 6843fa0b98..911f91212a 100644 --- a/target-ppc/kvm.c +++ b/target-ppc/kvm.c @@ -2246,8 +2246,23 @@ int kvmppc_save_htab(QEMUFile *f, int fd, size_t bufsize, int64_t max_ns) strerror(errno)); return rc; } else if (rc) { - /* Kernel already retuns data in BE format for the file */ - qemu_put_buffer(f, buf, rc); + uint8_t *buffer = buf; + ssize_t n = rc; + while (n) { + struct kvm_get_htab_header *head = + (struct kvm_get_htab_header *) buffer; + size_t chunksize = sizeof(*head) + + HASH_PTE_SIZE_64 * head->n_valid; + + qemu_put_be32(f, head->index); + qemu_put_be16(f, head->n_valid); + qemu_put_be16(f, head->n_invalid); + qemu_put_buffer(f, (void *)(head + 1), + HASH_PTE_SIZE_64 * head->n_valid); + + buffer += chunksize; + n -= chunksize; + } } } while ((rc != 0) && ((max_ns < 0) @@ -2264,7 +2279,6 @@ int kvmppc_load_htab_chunk(QEMUFile *f, int fd, uint32_t index, ssize_t rc; buf = alloca(chunksize); - /* This is KVM on ppc, so this is all big-endian */ buf->index = index; buf->n_valid = n_valid; buf->n_invalid = n_invalid; diff --git a/target-ppc/mem_helper.c b/target-ppc/mem_helper.c index 50344b81cf..6d37dae7b0 100644 --- a/target-ppc/mem_helper.c +++ b/target-ppc/mem_helper.c @@ -269,3 +269,25 @@ STVE(stvewx, cpu_stl_data, bswap32, u32) #undef HI_IDX #undef LO_IDX + +void helper_tbegin(CPUPPCState *env) +{ + /* As a degenerate implementation, always fail tbegin. The reason + * given is "Nesting overflow". The "persistent" bit is set, + * providing a hint to the error handler to not retry. The TFIAR + * captures the address of the failure, which is this tbegin + * instruction. Instruction execution will continue with the + * next instruction in memory, which is precisely what we want. + */ + + env->spr[SPR_TEXASR] = + (1ULL << TEXASR_FAILURE_PERSISTENT) | + (1ULL << TEXASR_NESTING_OVERFLOW) | + (msr_hv << TEXASR_PRIVILEGE_HV) | + (msr_pr << TEXASR_PRIVILEGE_PR) | + (1ULL << TEXASR_FAILURE_SUMMARY) | + (1ULL << TEXASR_TFIAR_EXACT); + env->spr[SPR_TFIAR] = env->nip | (msr_hv << 1) | msr_pr; + env->spr[SPR_TFHAR] = env->nip + 4; + env->crf[0] = 0xB; /* 0b1010 = transaction failure */ +} diff --git a/target-ppc/translate.c b/target-ppc/translate.c index 2e32e8d8b8..7c801f36e3 100644 --- a/target-ppc/translate.c +++ b/target-ppc/translate.c @@ -203,6 +203,7 @@ struct DisasContext { int altivec_enabled; int vsx_enabled; int spe_enabled; + int tm_enabled; ppc_spr_t *spr_cb; /* Needed to check rights for mfspr/mtspr */ int singlestep_enabled; uint64_t insns_flags; @@ -250,26 +251,10 @@ static inline void gen_reset_fpstatus(void) gen_helper_reset_fpstatus(cpu_env); } -static inline void gen_compute_fprf(TCGv_i64 arg, int set_fprf, int set_rc) +static inline void gen_compute_fprf(TCGv_i64 arg) { - TCGv_i32 t0 = tcg_temp_new_i32(); - - if (set_fprf != 0) { - /* This case might be optimized later */ - tcg_gen_movi_i32(t0, 1); - gen_helper_compute_fprf(t0, cpu_env, arg, t0); - if (unlikely(set_rc)) { - tcg_gen_mov_i32(cpu_crf[1], t0); - } - gen_helper_float_check_status(cpu_env); - } else if (unlikely(set_rc)) { - /* We always need to compute fpcc */ - tcg_gen_movi_i32(t0, 0); - gen_helper_compute_fprf(t0, cpu_env, arg, t0); - tcg_gen_mov_i32(cpu_crf[1], t0); - } - - tcg_temp_free_i32(t0); + gen_helper_compute_fprf(cpu_env, arg); + gen_helper_float_check_status(cpu_env); } static inline void gen_set_access_type(DisasContext *ctx, int access_type) @@ -346,11 +331,13 @@ static inline void gen_stop_exception(DisasContext *ctx) ctx->exception = POWERPC_EXCP_STOP; } +#ifndef CONFIG_USER_ONLY /* No need to update nip here, as execution flow will change */ static inline void gen_sync_exception(DisasContext *ctx) { ctx->exception = POWERPC_EXCP_SYNC; } +#endif #define GEN_HANDLER(name, opc1, opc2, opc3, inval, type) \ GEN_OPCODE(name, opc1, opc2, opc3, inval, type, PPC_NONE) @@ -452,7 +439,10 @@ EXTRACT_HELPER(ME, 1, 5); EXTRACT_HELPER(TO, 21, 5); EXTRACT_HELPER(CRM, 12, 8); + +#ifndef CONFIG_USER_ONLY EXTRACT_HELPER(SR, 16, 4); +#endif /* mtfsf/mtfsfi */ EXTRACT_HELPER(FPBF, 23, 3); @@ -2077,6 +2067,21 @@ static void gen_srd(DisasContext *ctx) } #endif +#if defined(TARGET_PPC64) +static void gen_set_cr1_from_fpscr(DisasContext *ctx) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + tcg_gen_trunc_tl_i32(tmp, cpu_fpscr); + tcg_gen_shri_i32(cpu_crf[1], tmp, 28); + tcg_temp_free_i32(tmp); +} +#else +static void gen_set_cr1_from_fpscr(DisasContext *ctx) +{ + tcg_gen_shri_tl(cpu_crf[1], cpu_fpscr, 28); +} +#endif + /*** Floating-Point arithmetic ***/ #define _GEN_FLOAT_ACB(name, op, op1, op2, isfloat, set_fprf, type) \ static void gen_f##name(DisasContext *ctx) \ @@ -2095,8 +2100,12 @@ static void gen_f##name(DisasContext *ctx) \ gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rD(ctx->opcode)]); \ } \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], set_fprf, \ - Rc(ctx->opcode) != 0); \ + if (set_fprf) { \ + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + } \ + if (unlikely(Rc(ctx->opcode) != 0)) { \ + gen_set_cr1_from_fpscr(ctx); \ + } \ } #define GEN_FLOAT_ACB(name, op2, set_fprf, type) \ @@ -2120,8 +2129,12 @@ static void gen_f##name(DisasContext *ctx) \ gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rD(ctx->opcode)]); \ } \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], \ - set_fprf, Rc(ctx->opcode) != 0); \ + if (set_fprf) { \ + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + } \ + if (unlikely(Rc(ctx->opcode) != 0)) { \ + gen_set_cr1_from_fpscr(ctx); \ + } \ } #define GEN_FLOAT_AB(name, op2, inval, set_fprf, type) \ _GEN_FLOAT_AB(name, name, 0x3F, op2, inval, 0, set_fprf, type); \ @@ -2144,8 +2157,12 @@ static void gen_f##name(DisasContext *ctx) \ gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rD(ctx->opcode)]); \ } \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], \ - set_fprf, Rc(ctx->opcode) != 0); \ + if (set_fprf) { \ + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + } \ + if (unlikely(Rc(ctx->opcode) != 0)) { \ + gen_set_cr1_from_fpscr(ctx); \ + } \ } #define GEN_FLOAT_AC(name, op2, inval, set_fprf, type) \ _GEN_FLOAT_AC(name, name, 0x3F, op2, inval, 0, set_fprf, type); \ @@ -2163,8 +2180,12 @@ static void gen_f##name(DisasContext *ctx) \ gen_reset_fpstatus(); \ gen_helper_f##name(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rB(ctx->opcode)]); \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], \ - set_fprf, Rc(ctx->opcode) != 0); \ + if (set_fprf) { \ + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + } \ + if (unlikely(Rc(ctx->opcode) != 0)) { \ + gen_set_cr1_from_fpscr(ctx); \ + } \ } #define GEN_FLOAT_BS(name, op1, op2, set_fprf, type) \ @@ -2179,8 +2200,12 @@ static void gen_f##name(DisasContext *ctx) \ gen_reset_fpstatus(); \ gen_helper_f##name(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rB(ctx->opcode)]); \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], \ - set_fprf, Rc(ctx->opcode) != 0); \ + if (set_fprf) { \ + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + } \ + if (unlikely(Rc(ctx->opcode) != 0)) { \ + gen_set_cr1_from_fpscr(ctx); \ + } \ } /* fadd - fadds */ @@ -2213,7 +2238,10 @@ static void gen_frsqrtes(DisasContext *ctx) cpu_fpr[rB(ctx->opcode)]); gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, cpu_fpr[rD(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 1, Rc(ctx->opcode) != 0); + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); + if (unlikely(Rc(ctx->opcode) != 0)) { + gen_set_cr1_from_fpscr(ctx); + } } /* fsel */ @@ -2234,7 +2262,10 @@ static void gen_fsqrt(DisasContext *ctx) gen_reset_fpstatus(); gen_helper_fsqrt(cpu_fpr[rD(ctx->opcode)], cpu_env, cpu_fpr[rB(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 1, Rc(ctx->opcode) != 0); + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); + if (unlikely(Rc(ctx->opcode) != 0)) { + gen_set_cr1_from_fpscr(ctx); + } } static void gen_fsqrts(DisasContext *ctx) @@ -2250,7 +2281,10 @@ static void gen_fsqrts(DisasContext *ctx) cpu_fpr[rB(ctx->opcode)]); gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, cpu_fpr[rD(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 1, Rc(ctx->opcode) != 0); + gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); + if (unlikely(Rc(ctx->opcode) != 0)) { + gen_set_cr1_from_fpscr(ctx); + } } /*** Floating-Point multiply-and-add ***/ @@ -2370,7 +2404,9 @@ static void gen_fabs(DisasContext *ctx) } tcg_gen_andi_i64(cpu_fpr[rD(ctx->opcode)], cpu_fpr[rB(ctx->opcode)], ~(1ULL << 63)); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 0, Rc(ctx->opcode) != 0); + if (unlikely(Rc(ctx->opcode))) { + gen_set_cr1_from_fpscr(ctx); + } } /* fmr - fmr. */ @@ -2382,7 +2418,9 @@ static void gen_fmr(DisasContext *ctx) return; } tcg_gen_mov_i64(cpu_fpr[rD(ctx->opcode)], cpu_fpr[rB(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 0, Rc(ctx->opcode) != 0); + if (unlikely(Rc(ctx->opcode))) { + gen_set_cr1_from_fpscr(ctx); + } } /* fnabs */ @@ -2395,7 +2433,9 @@ static void gen_fnabs(DisasContext *ctx) } tcg_gen_ori_i64(cpu_fpr[rD(ctx->opcode)], cpu_fpr[rB(ctx->opcode)], 1ULL << 63); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 0, Rc(ctx->opcode) != 0); + if (unlikely(Rc(ctx->opcode))) { + gen_set_cr1_from_fpscr(ctx); + } } /* fneg */ @@ -2408,7 +2448,9 @@ static void gen_fneg(DisasContext *ctx) } tcg_gen_xori_i64(cpu_fpr[rD(ctx->opcode)], cpu_fpr[rB(ctx->opcode)], 1ULL << 63); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 0, Rc(ctx->opcode) != 0); + if (unlikely(Rc(ctx->opcode))) { + gen_set_cr1_from_fpscr(ctx); + } } /* fcpsgn: PowerPC 2.05 specification */ @@ -2421,7 +2463,9 @@ static void gen_fcpsgn(DisasContext *ctx) } tcg_gen_deposit_i64(cpu_fpr[rD(ctx->opcode)], cpu_fpr[rA(ctx->opcode)], cpu_fpr[rB(ctx->opcode)], 0, 63); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 0, Rc(ctx->opcode) != 0); + if (unlikely(Rc(ctx->opcode))) { + gen_set_cr1_from_fpscr(ctx); + } } static void gen_fmrgew(DisasContext *ctx) @@ -2479,7 +2523,9 @@ static void gen_mffs(DisasContext *ctx) } gen_reset_fpstatus(); tcg_gen_extu_tl_i64(cpu_fpr[rD(ctx->opcode)], cpu_fpscr); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)], 0, Rc(ctx->opcode) != 0); + if (unlikely(Rc(ctx->opcode))) { + gen_set_cr1_from_fpscr(ctx); + } } /* mtfsb0 */ @@ -6743,7 +6789,7 @@ static void gen_st##name(DisasContext *ctx) \ tcg_temp_free(EA); \ } -#define GEN_VR_LVE(name, opc2, opc3) \ +#define GEN_VR_LVE(name, opc2, opc3, size) \ static void gen_lve##name(DisasContext *ctx) \ { \ TCGv EA; \ @@ -6755,13 +6801,16 @@ static void gen_lve##name(DisasContext *ctx) \ gen_set_access_type(ctx, ACCESS_INT); \ EA = tcg_temp_new(); \ gen_addr_reg_index(ctx, EA); \ + if (size > 1) { \ + tcg_gen_andi_tl(EA, EA, ~(size - 1)); \ + } \ rs = gen_avr_ptr(rS(ctx->opcode)); \ gen_helper_lve##name(cpu_env, rs, EA); \ tcg_temp_free(EA); \ tcg_temp_free_ptr(rs); \ } -#define GEN_VR_STVE(name, opc2, opc3) \ +#define GEN_VR_STVE(name, opc2, opc3, size) \ static void gen_stve##name(DisasContext *ctx) \ { \ TCGv EA; \ @@ -6773,6 +6822,9 @@ static void gen_stve##name(DisasContext *ctx) \ gen_set_access_type(ctx, ACCESS_INT); \ EA = tcg_temp_new(); \ gen_addr_reg_index(ctx, EA); \ + if (size > 1) { \ + tcg_gen_andi_tl(EA, EA, ~(size - 1)); \ + } \ rs = gen_avr_ptr(rS(ctx->opcode)); \ gen_helper_stve##name(cpu_env, rs, EA); \ tcg_temp_free(EA); \ @@ -6783,17 +6835,17 @@ GEN_VR_LDX(lvx, 0x07, 0x03); /* As we don't emulate the cache, lvxl is stricly equivalent to lvx */ GEN_VR_LDX(lvxl, 0x07, 0x0B); -GEN_VR_LVE(bx, 0x07, 0x00); -GEN_VR_LVE(hx, 0x07, 0x01); -GEN_VR_LVE(wx, 0x07, 0x02); +GEN_VR_LVE(bx, 0x07, 0x00, 1); +GEN_VR_LVE(hx, 0x07, 0x01, 2); +GEN_VR_LVE(wx, 0x07, 0x02, 4); GEN_VR_STX(svx, 0x07, 0x07); /* As we don't emulate the cache, stvxl is stricly equivalent to stvx */ GEN_VR_STX(svxl, 0x07, 0x0F); -GEN_VR_STVE(bx, 0x07, 0x04); -GEN_VR_STVE(hx, 0x07, 0x05); -GEN_VR_STVE(wx, 0x07, 0x06); +GEN_VR_STVE(bx, 0x07, 0x04, 1); +GEN_VR_STVE(hx, 0x07, 0x05, 2); +GEN_VR_STVE(wx, 0x07, 0x06, 4); static void gen_lvsl(DisasContext *ctx) { @@ -8205,21 +8257,6 @@ static inline TCGv_ptr gen_fprp_ptr(int reg) return r; } -#if defined(TARGET_PPC64) -static void gen_set_cr1_from_fpscr(DisasContext *ctx) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_trunc_tl_i32(tmp, cpu_fpscr); - tcg_gen_shri_i32(cpu_crf[1], tmp, 28); - tcg_temp_free_i32(tmp); -} -#else -static void gen_set_cr1_from_fpscr(DisasContext *ctx) -{ - tcg_gen_shri_tl(cpu_crf[1], cpu_fpscr, 28); -} -#endif - #define GEN_DFP_T_A_B_Rc(name) \ static void gen_##name(DisasContext *ctx) \ { \ @@ -9642,6 +9679,88 @@ GEN_SPE(efdctsiz, speundef, 0x1D, 0x0B, 0x00180000, 0xFFFFFFFF, PPC_SPE_DOUBLE GEN_SPE(efdtstgt, efdtstlt, 0x1E, 0x0B, 0x00600000, 0x00600000, PPC_SPE_DOUBLE); // GEN_SPE(efdtsteq, speundef, 0x1F, 0x0B, 0x00600000, 0xFFFFFFFF, PPC_SPE_DOUBLE); // +static void gen_tbegin(DisasContext *ctx) +{ + if (unlikely(!ctx->tm_enabled)) { + gen_exception_err(ctx, POWERPC_EXCP_FU, FSCR_IC_TM); + return; + } + gen_helper_tbegin(cpu_env); +} + +#define GEN_TM_NOOP(name) \ +static inline void gen_##name(DisasContext *ctx) \ +{ \ + if (unlikely(!ctx->tm_enabled)) { \ + gen_exception_err(ctx, POWERPC_EXCP_FU, FSCR_IC_TM); \ + return; \ + } \ + /* Because tbegin always fails in QEMU, these user \ + * space instructions all have a simple implementation: \ + * \ + * CR[0] = 0b0 || MSR[TS] || 0b0 \ + * = 0b0 || 0b00 || 0b0 \ + */ \ + tcg_gen_movi_i32(cpu_crf[0], 0); \ +} + +GEN_TM_NOOP(tend); +GEN_TM_NOOP(tabort); +GEN_TM_NOOP(tabortwc); +GEN_TM_NOOP(tabortwci); +GEN_TM_NOOP(tabortdc); +GEN_TM_NOOP(tabortdci); +GEN_TM_NOOP(tsr); + +static void gen_tcheck(DisasContext *ctx) +{ + if (unlikely(!ctx->tm_enabled)) { + gen_exception_err(ctx, POWERPC_EXCP_FU, FSCR_IC_TM); + return; + } + /* Because tbegin always fails, the tcheck implementation + * is simple: + * + * CR[CRF] = TDOOMED || MSR[TS] || 0b0 + * = 0b1 || 0b00 || 0b0 + */ + tcg_gen_movi_i32(cpu_crf[crfD(ctx->opcode)], 0x8); +} + +#if defined(CONFIG_USER_ONLY) +#define GEN_TM_PRIV_NOOP(name) \ +static inline void gen_##name(DisasContext *ctx) \ +{ \ + gen_inval_exception(ctx, POWERPC_EXCP_PRIV_OPC); \ +} + +#else + +#define GEN_TM_PRIV_NOOP(name) \ +static inline void gen_##name(DisasContext *ctx) \ +{ \ + if (unlikely(ctx->pr)) { \ + gen_inval_exception(ctx, POWERPC_EXCP_PRIV_OPC); \ + return; \ + } \ + if (unlikely(!ctx->tm_enabled)) { \ + gen_exception_err(ctx, POWERPC_EXCP_FU, FSCR_IC_TM); \ + return; \ + } \ + /* Because tbegin always fails, the implementation is \ + * simple: \ + * \ + * CR[0] = 0b0 || MSR[TS] || 0b0 \ + * = 0b0 || 0b00 | 0b0 \ + */ \ + tcg_gen_movi_i32(cpu_crf[0], 0); \ +} + +#endif + +GEN_TM_PRIV_NOOP(treclaim); +GEN_TM_PRIV_NOOP(trechkpt); + static opcode_t opcodes[] = { GEN_HANDLER(invalid, 0x00, 0x00, 0x00, 0xFFFFFFFF, PPC_NONE), GEN_HANDLER(cmp, 0x1F, 0x00, 0x00, 0x00400000, PPC_INTEGER), @@ -11054,6 +11173,29 @@ GEN_SPEOP_LDST(evstwhe, 0x18, 2), GEN_SPEOP_LDST(evstwho, 0x1A, 2), GEN_SPEOP_LDST(evstwwe, 0x1C, 2), GEN_SPEOP_LDST(evstwwo, 0x1E, 2), + +GEN_HANDLER2_E(tbegin, "tbegin", 0x1F, 0x0E, 0x14, 0x01DFF800, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tend, "tend", 0x1F, 0x0E, 0x15, 0x01FFF800, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tabort, "tabort", 0x1F, 0x0E, 0x1C, 0x03E0F800, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tabortwc, "tabortwc", 0x1F, 0x0E, 0x18, 0x00000000, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tabortwci, "tabortwci", 0x1F, 0x0E, 0x1A, 0x00000000, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tabortdc, "tabortdc", 0x1F, 0x0E, 0x19, 0x00000000, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tabortdci, "tabortdci", 0x1F, 0x0E, 0x1B, 0x00000000, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tsr, "tsr", 0x1F, 0x0E, 0x17, 0x03DFF800, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(tcheck, "tcheck", 0x1F, 0x0E, 0x16, 0x007FF800, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(treclaim, "treclaim", 0x1F, 0x0E, 0x1D, 0x03E0F800, \ + PPC_NONE, PPC2_TM), +GEN_HANDLER2_E(trechkpt, "trechkpt", 0x1F, 0x0E, 0x1F, 0x03FFF800, \ + PPC_NONE, PPC2_TM), }; #include "helper_regs.h" @@ -11311,6 +11453,13 @@ static inline void gen_intermediate_code_internal(PowerPCCPU *cpu, } else { ctx.vsx_enabled = 0; } +#if defined(TARGET_PPC64) + if ((env->flags & POWERPC_FLAG_TM) && msr_tm) { + ctx.tm_enabled = msr_tm; + } else { + ctx.tm_enabled = 0; + } +#endif if ((env->flags & POWERPC_FLAG_SE) && msr_se) ctx.singlestep_enabled = CPU_SINGLE_STEP; else diff --git a/target-ppc/translate_init.c b/target-ppc/translate_init.c index f0a29992df..df1a62c4c6 100644 --- a/target-ppc/translate_init.c +++ b/target-ppc/translate_init.c @@ -8214,7 +8214,8 @@ POWERPC_FAMILY(POWER8)(ObjectClass *oc, void *data) PPC2_ATOMIC_ISA206 | PPC2_FP_CVT_ISA206 | PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207 | PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 | - PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64; + PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | + PPC2_TM; pcc->msr_mask = (1ull << MSR_SF) | (1ull << MSR_TM) | (1ull << MSR_VR) | @@ -8242,7 +8243,7 @@ POWERPC_FAMILY(POWER8)(ObjectClass *oc, void *data) pcc->flags = POWERPC_FLAG_VRE | POWERPC_FLAG_SE | POWERPC_FLAG_BE | POWERPC_FLAG_PMM | POWERPC_FLAG_BUS_CLK | POWERPC_FLAG_CFAR | - POWERPC_FLAG_VSX; + POWERPC_FLAG_VSX | POWERPC_FLAG_TM; pcc->l1_dcache_size = 0x8000; pcc->l1_icache_size = 0x8000; pcc->interrupts_big_endian = ppc_cpu_interrupts_big_endian_lpcr; |