diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2022-03-02 12:38:46 +0000 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2022-03-02 12:38:46 +0000 |
commit | 64ada298b98a51eb2512607f6e6180cb330c47b1 (patch) | |
tree | 18bd53f57fa2bf127485a0c15c33021ab024cdf1 | |
parent | 44efeb90b2d06635fd4052fa080b2a2ea480501f (diff) | |
parent | 169518430562b454a1531610d2711c6b920929f6 (diff) |
Merge remote-tracking branch 'remotes/legoater/tags/pull-ppc-20220302' into staging
ppc-7.0 queue
* ppc/pnv fixes
* PMU EBB support
* target/ppc: PowerISA Vector/VSX instruction batch
* ppc/pnv: Extension of the powernv10 machine with XIVE2 ans PHB5 models
* spapr allocation cleanups
# gpg: Signature made Wed 02 Mar 2022 11:00:42 GMT
# gpg: using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@kaod.org>" [undefined]
# 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: A0F6 6548 F048 95EB FE6B 0B60 51A3 43C7 CFFB ECA1
* remotes/legoater/tags/pull-ppc-20220302: (87 commits)
hw/ppc/spapr_vio.c: use g_autofree in spapr_dt_vdevice()
hw/ppc/spapr_rtas.c: use g_autofree in rtas_ibm_get_system_parameter()
spapr_pci_nvlink2.c: use g_autofree in spapr_phb_nvgpu_ram_populate_dt()
hw/ppc/spapr_numa.c: simplify spapr_numa_write_assoc_lookup_arrays()
hw/ppc/spapr_drc.c: use g_autofree in spapr_drc_by_index()
hw/ppc/spapr_drc.c: use g_autofree in spapr_dr_connector_new()
hw/ppc/spapr_drc.c: use g_autofree in drc_unrealize()
hw/ppc/spapr_drc.c: use g_autofree in drc_realize()
hw/ppc/spapr_drc.c: use g_auto in spapr_dt_drc()
hw/ppc/spapr_caps.c: use g_autofree in spapr_caps_add_properties()
hw/ppc/spapr_caps.c: use g_autofree in spapr_cap_get_string()
hw/ppc/spapr_caps.c: use g_autofree in spapr_cap_set_string()
hw/ppc/spapr.c: fail early if no firmware found in machine_init()
hw/ppc/spapr.c: use g_autofree in spapr_dt_chosen()
pnv/xive2: Add support for 8bits thread id
pnv/xive2: Add support for automatic save&restore
xive2: Add a get_config() handler for the router configuration
pnv/xive2: Add support XIVE2 P9-compat mode (or Gen1)
ppc/pnv: add XIVE Gen2 TIMA support
pnv/xive2: Introduce new capability bits
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
51 files changed, 7737 insertions, 948 deletions
diff --git a/hw/intc/meson.build b/hw/intc/meson.build index 7466024402..d953197413 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -42,7 +42,7 @@ specific_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_intc.c')) specific_ss.add(when: 'CONFIG_OMPIC', if_true: files('ompic.c')) specific_ss.add(when: ['CONFIG_KVM', 'CONFIG_OPENPIC'], if_true: files('openpic_kvm.c')) -specific_ss.add(when: 'CONFIG_POWERNV', if_true: files('xics_pnv.c', 'pnv_xive.c')) +specific_ss.add(when: 'CONFIG_POWERNV', if_true: files('xics_pnv.c', 'pnv_xive.c', 'pnv_xive2.c')) specific_ss.add(when: 'CONFIG_PPC_UIC', if_true: files('ppc-uic.c')) specific_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_ic.c', 'bcm2836_control.c')) specific_ss.add(when: 'CONFIG_RX_ICU', if_true: files('rx_icu.c')) @@ -52,7 +52,7 @@ specific_ss.add(when: 'CONFIG_SH_INTC', if_true: files('sh_intc.c')) specific_ss.add(when: 'CONFIG_RISCV_ACLINT', if_true: files('riscv_aclint.c')) specific_ss.add(when: 'CONFIG_RISCV_APLIC', if_true: files('riscv_aplic.c')) specific_ss.add(when: 'CONFIG_SIFIVE_PLIC', if_true: files('sifive_plic.c')) -specific_ss.add(when: 'CONFIG_XICS', if_true: files('xics.c')) +specific_ss.add(when: 'CONFIG_XICS', if_true: files('xics.c', 'xive2.c')) specific_ss.add(when: ['CONFIG_KVM', 'CONFIG_XICS'], if_true: files('xics_kvm.c')) specific_ss.add(when: 'CONFIG_PSERIES', if_true: files('xics_spapr.c', 'spapr_xive.c')) diff --git a/hw/intc/pnv_xive.c b/hw/intc/pnv_xive.c index 621b20a03f..1ce1d7b07d 100644 --- a/hw/intc/pnv_xive.c +++ b/hw/intc/pnv_xive.c @@ -403,6 +403,34 @@ static int pnv_xive_get_eas(XiveRouter *xrtr, uint8_t blk, uint32_t idx, return pnv_xive_vst_read(xive, VST_TSEL_IVT, blk, idx, eas); } +static int pnv_xive_get_pq(XiveRouter *xrtr, uint8_t blk, uint32_t idx, + uint8_t *pq) +{ + PnvXive *xive = PNV_XIVE(xrtr); + + if (pnv_xive_block_id(xive) != blk) { + xive_error(xive, "VST: EAS %x is remote !?", XIVE_EAS(blk, idx)); + return -1; + } + + *pq = xive_source_esb_get(&xive->ipi_source, idx); + return 0; +} + +static int pnv_xive_set_pq(XiveRouter *xrtr, uint8_t blk, uint32_t idx, + uint8_t *pq) +{ + PnvXive *xive = PNV_XIVE(xrtr); + + if (pnv_xive_block_id(xive) != blk) { + xive_error(xive, "VST: EAS %x is remote !?", XIVE_EAS(blk, idx)); + return -1; + } + + *pq = xive_source_esb_set(&xive->ipi_source, idx, *pq); + return 0; +} + /* * One bit per thread id. The first register PC_THREAD_EN_REG0 covers * the first cores 0-15 (normal) of the chip or 0-7 (fused). The @@ -499,12 +527,12 @@ static PnvXive *pnv_xive_tm_get_xive(PowerPCCPU *cpu) * event notification to the Router. This is required on a multichip * system. */ -static void pnv_xive_notify(XiveNotifier *xn, uint32_t srcno) +static void pnv_xive_notify(XiveNotifier *xn, uint32_t srcno, bool pq_checked) { PnvXive *xive = PNV_XIVE(xn); uint8_t blk = pnv_xive_block_id(xive); - xive_router_notify(xn, XIVE_EAS(blk, srcno)); + xive_router_notify(xn, XIVE_EAS(blk, srcno), pq_checked); } /* @@ -1351,7 +1379,8 @@ static void pnv_xive_ic_hw_trigger(PnvXive *xive, hwaddr addr, uint64_t val) blk = XIVE_EAS_BLOCK(val); idx = XIVE_EAS_INDEX(val); - xive_router_notify(XIVE_NOTIFIER(xive), XIVE_EAS(blk, idx)); + xive_router_notify(XIVE_NOTIFIER(xive), XIVE_EAS(blk, idx), + !!(val & XIVE_TRIGGER_PQ)); } static void pnv_xive_ic_notify_write(void *opaque, hwaddr addr, uint64_t val, @@ -1971,6 +2000,8 @@ static void pnv_xive_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, pnv_xive_properties); xrc->get_eas = pnv_xive_get_eas; + xrc->get_pq = pnv_xive_get_pq; + xrc->set_pq = pnv_xive_set_pq; xrc->get_end = pnv_xive_get_end; xrc->write_end = pnv_xive_write_end; xrc->get_nvt = pnv_xive_get_nvt; diff --git a/hw/intc/pnv_xive2.c b/hw/intc/pnv_xive2.c new file mode 100644 index 0000000000..87303b4064 --- /dev/null +++ b/hw/intc/pnv_xive2.c @@ -0,0 +1,2128 @@ +/* + * QEMU PowerPC XIVE2 interrupt controller model (POWER10) + * + * Copyright (c) 2019-2022, IBM Corporation. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qapi/error.h" +#include "target/ppc/cpu.h" +#include "sysemu/cpus.h" +#include "sysemu/dma.h" +#include "monitor/monitor.h" +#include "hw/ppc/fdt.h" +#include "hw/ppc/pnv.h" +#include "hw/ppc/pnv_core.h" +#include "hw/ppc/pnv_xscom.h" +#include "hw/ppc/xive2.h" +#include "hw/ppc/pnv_xive.h" +#include "hw/ppc/xive_regs.h" +#include "hw/ppc/xive2_regs.h" +#include "hw/ppc/ppc.h" +#include "hw/qdev-properties.h" +#include "sysemu/reset.h" + +#include <libfdt.h> + +#include "pnv_xive2_regs.h" + +#undef XIVE2_DEBUG + +/* + * Virtual structures table (VST) + */ +#define SBE_PER_BYTE 4 + +typedef struct XiveVstInfo { + const char *name; + uint32_t size; + uint32_t max_blocks; +} XiveVstInfo; + +static const XiveVstInfo vst_infos[] = { + + [VST_EAS] = { "EAT", sizeof(Xive2Eas), 16 }, + [VST_ESB] = { "ESB", 1, 16 }, + [VST_END] = { "ENDT", sizeof(Xive2End), 16 }, + + [VST_NVP] = { "NVPT", sizeof(Xive2Nvp), 16 }, + [VST_NVG] = { "NVGT", sizeof(Xive2Nvgc), 16 }, + [VST_NVC] = { "NVCT", sizeof(Xive2Nvgc), 16 }, + + [VST_IC] = { "IC", 1 /* ? */ , 16 }, /* Topology # */ + [VST_SYNC] = { "SYNC", 1 /* ? */ , 16 }, /* Topology # */ + + /* + * This table contains the backing store pages for the interrupt + * fifos of the VC sub-engine in case of overflow. + * + * 0 - IPI, + * 1 - HWD, + * 2 - NxC, + * 3 - INT, + * 4 - OS-Queue, + * 5 - Pool-Queue, + * 6 - Hard-Queue + */ + [VST_ERQ] = { "ERQ", 1, VC_QUEUE_COUNT }, +}; + +#define xive2_error(xive, fmt, ...) \ + qemu_log_mask(LOG_GUEST_ERROR, "XIVE[%x] - " fmt "\n", \ + (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) +{ + uint8_t blk = xive->chip->chip_id; + uint64_t cfg_val = xive->cq_regs[CQ_XIVE_CFG >> 3]; + + if (cfg_val & CQ_XIVE_CFG_HYP_HARD_BLKID_OVERRIDE) { + blk = GETFIELD(CQ_XIVE_CFG_HYP_HARD_BLOCK_ID, cfg_val); + } + + return blk; +} + +/* + * Remote access to controllers. HW uses MMIOs. For now, a simple scan + * of the chips is good enough. + * + * TODO: Block scope support + */ +static PnvXive2 *pnv_xive2_get_remote(uint8_t blk) +{ + PnvMachineState *pnv = PNV_MACHINE(qdev_get_machine()); + int i; + + for (i = 0; i < pnv->num_chips; i++) { + Pnv10Chip *chip10 = PNV10_CHIP(pnv->chips[i]); + PnvXive2 *xive = &chip10->xive; + + if (pnv_xive2_block_id(xive) == blk) { + return xive; + } + } + return NULL; +} + +/* + * VST accessors for ESB, EAT, ENDT, NVP + * + * Indirect VST tables are arrays of VSDs pointing to a page (of same + * size). Each page is a direct VST table. + */ + +#define XIVE_VSD_SIZE 8 + +/* Indirect page size can be 4K, 64K, 2M, 16M. */ +static uint64_t pnv_xive2_vst_page_size_allowed(uint32_t page_shift) +{ + return page_shift == 12 || page_shift == 16 || + page_shift == 21 || page_shift == 24; +} + +static uint64_t pnv_xive2_vst_addr_direct(PnvXive2 *xive, uint32_t type, + uint64_t vsd, uint32_t idx) +{ + const XiveVstInfo *info = &vst_infos[type]; + uint64_t vst_addr = vsd & VSD_ADDRESS_MASK; + uint64_t vst_tsize = 1ull << (GETFIELD(VSD_TSIZE, vsd) + 12); + uint32_t idx_max; + + idx_max = vst_tsize / info->size - 1; + if (idx > idx_max) { +#ifdef XIVE2_DEBUG + xive2_error(xive, "VST: %s entry %x out of range [ 0 .. %x ] !?", + info->name, idx, idx_max); +#endif + return 0; + } + + return vst_addr + idx * info->size; +} + +static uint64_t pnv_xive2_vst_addr_indirect(PnvXive2 *xive, uint32_t type, + uint64_t vsd, uint32_t idx) +{ + const XiveVstInfo *info = &vst_infos[type]; + uint64_t vsd_addr; + uint32_t vsd_idx; + uint32_t page_shift; + uint32_t vst_per_page; + + /* Get the page size of the indirect table. */ + vsd_addr = vsd & VSD_ADDRESS_MASK; + ldq_be_dma(&address_space_memory, vsd_addr, &vsd, MEMTXATTRS_UNSPECIFIED); + + if (!(vsd & VSD_ADDRESS_MASK)) { + xive2_error(xive, "VST: invalid %s entry %x !?", info->name, idx); + return 0; + } + + page_shift = GETFIELD(VSD_TSIZE, vsd) + 12; + + if (!pnv_xive2_vst_page_size_allowed(page_shift)) { + xive2_error(xive, "VST: invalid %s page shift %d", info->name, + page_shift); + return 0; + } + + vst_per_page = (1ull << page_shift) / info->size; + vsd_idx = idx / vst_per_page; + + /* Load the VSD we are looking for, if not already done */ + if (vsd_idx) { + vsd_addr = vsd_addr + vsd_idx * XIVE_VSD_SIZE; + ldq_be_dma(&address_space_memory, vsd_addr, &vsd, + MEMTXATTRS_UNSPECIFIED); + + if (!(vsd & VSD_ADDRESS_MASK)) { + xive2_error(xive, "VST: invalid %s entry %x !?", info->name, idx); + return 0; + } + + /* + * Check that the pages have a consistent size across the + * indirect table + */ + if (page_shift != GETFIELD(VSD_TSIZE, vsd) + 12) { + xive2_error(xive, "VST: %s entry %x indirect page size differ !?", + info->name, idx); + return 0; + } + } + + return pnv_xive2_vst_addr_direct(xive, type, vsd, (idx % vst_per_page)); +} + +static uint64_t pnv_xive2_vst_addr(PnvXive2 *xive, uint32_t type, uint8_t blk, + uint32_t idx) +{ + const XiveVstInfo *info = &vst_infos[type]; + uint64_t vsd; + + if (blk >= info->max_blocks) { + xive2_error(xive, "VST: invalid block id %d for VST %s %d !?", + blk, info->name, idx); + return 0; + } + + vsd = xive->vsds[type][blk]; + + /* Remote VST access */ + if (GETFIELD(VSD_MODE, vsd) == VSD_MODE_FORWARD) { + xive = pnv_xive2_get_remote(blk); + + return xive ? pnv_xive2_vst_addr(xive, type, blk, idx) : 0; + } + + if (VSD_INDIRECT & vsd) { + return pnv_xive2_vst_addr_indirect(xive, type, vsd, idx); + } + + return pnv_xive2_vst_addr_direct(xive, type, vsd, idx); +} + +static int pnv_xive2_vst_read(PnvXive2 *xive, uint32_t type, uint8_t blk, + uint32_t idx, void *data) +{ + const XiveVstInfo *info = &vst_infos[type]; + uint64_t addr = pnv_xive2_vst_addr(xive, type, blk, idx); + + if (!addr) { + return -1; + } + + cpu_physical_memory_read(addr, data, info->size); + return 0; +} + +#define XIVE_VST_WORD_ALL -1 + +static int pnv_xive2_vst_write(PnvXive2 *xive, uint32_t type, uint8_t blk, + uint32_t idx, void *data, uint32_t word_number) +{ + const XiveVstInfo *info = &vst_infos[type]; + uint64_t addr = pnv_xive2_vst_addr(xive, type, blk, idx); + + if (!addr) { + return -1; + } + + if (word_number == XIVE_VST_WORD_ALL) { + cpu_physical_memory_write(addr, data, info->size); + } else { + cpu_physical_memory_write(addr + word_number * 4, + data + word_number * 4, 4); + } + return 0; +} + +static int pnv_xive2_get_pq(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + uint8_t *pq) +{ + PnvXive2 *xive = PNV_XIVE2(xrtr); + + if (pnv_xive2_block_id(xive) != blk) { + xive2_error(xive, "VST: EAS %x is remote !?", XIVE_EAS(blk, idx)); + return -1; + } + + *pq = xive_source_esb_get(&xive->ipi_source, idx); + return 0; +} + +static int pnv_xive2_set_pq(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + uint8_t *pq) +{ + PnvXive2 *xive = PNV_XIVE2(xrtr); + + if (pnv_xive2_block_id(xive) != blk) { + xive2_error(xive, "VST: EAS %x is remote !?", XIVE_EAS(blk, idx)); + return -1; + } + + *pq = xive_source_esb_set(&xive->ipi_source, idx, *pq); + return 0; +} + +static int pnv_xive2_get_end(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + Xive2End *end) +{ + return pnv_xive2_vst_read(PNV_XIVE2(xrtr), VST_END, blk, idx, end); +} + +static int pnv_xive2_write_end(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + Xive2End *end, uint8_t word_number) +{ + return pnv_xive2_vst_write(PNV_XIVE2(xrtr), VST_END, blk, idx, end, + word_number); +} + +static int pnv_xive2_end_update(PnvXive2 *xive) +{ + uint8_t blk = GETFIELD(VC_ENDC_WATCH_BLOCK_ID, + xive->vc_regs[(VC_ENDC_WATCH0_SPEC >> 3)]); + uint32_t idx = GETFIELD(VC_ENDC_WATCH_INDEX, + xive->vc_regs[(VC_ENDC_WATCH0_SPEC >> 3)]); + int i; + uint64_t endc_watch[4]; + + for (i = 0; i < ARRAY_SIZE(endc_watch); i++) { + endc_watch[i] = + cpu_to_be64(xive->vc_regs[(VC_ENDC_WATCH0_DATA0 >> 3) + i]); + } + + return pnv_xive2_vst_write(xive, VST_END, blk, idx, endc_watch, + XIVE_VST_WORD_ALL); +} + +static void pnv_xive2_end_cache_load(PnvXive2 *xive) +{ + uint8_t blk = GETFIELD(VC_ENDC_WATCH_BLOCK_ID, + xive->vc_regs[(VC_ENDC_WATCH0_SPEC >> 3)]); + uint32_t idx = GETFIELD(VC_ENDC_WATCH_INDEX, + xive->vc_regs[(VC_ENDC_WATCH0_SPEC >> 3)]); + uint64_t endc_watch[4] = { 0 }; + int i; + + if (pnv_xive2_vst_read(xive, VST_END, blk, idx, endc_watch)) { + xive2_error(xive, "VST: no END entry %x/%x !?", blk, idx); + } + + for (i = 0; i < ARRAY_SIZE(endc_watch); i++) { + xive->vc_regs[(VC_ENDC_WATCH0_DATA0 >> 3) + i] = + be64_to_cpu(endc_watch[i]); + } +} + +static int pnv_xive2_get_nvp(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + Xive2Nvp *nvp) +{ + return pnv_xive2_vst_read(PNV_XIVE2(xrtr), VST_NVP, blk, idx, nvp); +} + +static int pnv_xive2_write_nvp(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + Xive2Nvp *nvp, uint8_t word_number) +{ + return pnv_xive2_vst_write(PNV_XIVE2(xrtr), VST_NVP, blk, idx, nvp, + word_number); +} + +static int pnv_xive2_nvp_update(PnvXive2 *xive) +{ + uint8_t blk = GETFIELD(PC_NXC_WATCH_BLOCK_ID, + xive->pc_regs[(PC_NXC_WATCH0_SPEC >> 3)]); + uint32_t idx = GETFIELD(PC_NXC_WATCH_INDEX, + xive->pc_regs[(PC_NXC_WATCH0_SPEC >> 3)]); + int i; + uint64_t nxc_watch[4]; + + for (i = 0; i < ARRAY_SIZE(nxc_watch); i++) { + nxc_watch[i] = + cpu_to_be64(xive->pc_regs[(PC_NXC_WATCH0_DATA0 >> 3) + i]); + } + + return pnv_xive2_vst_write(xive, VST_NVP, blk, idx, nxc_watch, + XIVE_VST_WORD_ALL); +} + +static void pnv_xive2_nvp_cache_load(PnvXive2 *xive) +{ + uint8_t blk = GETFIELD(PC_NXC_WATCH_BLOCK_ID, + xive->pc_regs[(PC_NXC_WATCH0_SPEC >> 3)]); + uint32_t idx = GETFIELD(PC_NXC_WATCH_INDEX, + xive->pc_regs[(PC_NXC_WATCH0_SPEC >> 3)]); + uint64_t nxc_watch[4] = { 0 }; + int i; + + if (pnv_xive2_vst_read(xive, VST_NVP, blk, idx, nxc_watch)) { + xive2_error(xive, "VST: no NVP entry %x/%x !?", blk, idx); + } + + for (i = 0; i < ARRAY_SIZE(nxc_watch); i++) { + xive->pc_regs[(PC_NXC_WATCH0_DATA0 >> 3) + i] = + be64_to_cpu(nxc_watch[i]); + } +} + +static int pnv_xive2_get_eas(Xive2Router *xrtr, uint8_t blk, uint32_t idx, + Xive2Eas *eas) +{ + PnvXive2 *xive = PNV_XIVE2(xrtr); + + if (pnv_xive2_block_id(xive) != blk) { + xive2_error(xive, "VST: EAS %x is remote !?", XIVE_EAS(blk, idx)); + return -1; + } + + return pnv_xive2_vst_read(xive, VST_EAS, blk, idx, eas); +} + +static uint32_t pnv_xive2_get_config(Xive2Router *xrtr) +{ + PnvXive2 *xive = PNV_XIVE2(xrtr); + uint32_t cfg = 0; + + if (xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS) { + cfg |= XIVE2_GEN1_TIMA_OS; + } + + if (xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_EN_VP_SAVE_RESTORE) { + cfg |= XIVE2_VP_SAVE_RESTORE; + } + + if (GETFIELD(CQ_XIVE_CFG_HYP_HARD_RANGE, + xive->cq_regs[CQ_XIVE_CFG >> 3]) == CQ_XIVE_CFG_THREADID_8BITS) { + cfg |= XIVE2_THREADID_8BITS; + } + + return cfg; +} + +static bool pnv_xive2_is_cpu_enabled(PnvXive2 *xive, PowerPCCPU *cpu) +{ + int pir = ppc_cpu_pir(cpu); + uint32_t fc = PNV10_PIR2FUSEDCORE(pir); + uint64_t reg = fc < 8 ? TCTXT_EN0 : TCTXT_EN1; + uint32_t bit = pir & 0x3f; + + return xive->tctxt_regs[reg >> 3] & PPC_BIT(bit); +} + +static int pnv_xive2_match_nvt(XivePresenter *xptr, uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool cam_ignore, uint8_t priority, + uint32_t logic_serv, XiveTCTXMatch *match) +{ + PnvXive2 *xive = PNV_XIVE2(xptr); + PnvChip *chip = xive->chip; + int count = 0; + int i, j; + bool gen1_tima_os = + xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS; + + for (i = 0; i < chip->nr_cores; i++) { + PnvCore *pc = chip->cores[i]; + CPUCore *cc = CPU_CORE(pc); + + for (j = 0; j < cc->nr_threads; j++) { + PowerPCCPU *cpu = pc->threads[j]; + XiveTCTX *tctx; + int ring; + + if (!pnv_xive2_is_cpu_enabled(xive, cpu)) { + continue; + } + + tctx = XIVE_TCTX(pnv_cpu_state(cpu)->intc); + + if (gen1_tima_os) { + ring = xive_presenter_tctx_match(xptr, tctx, format, nvt_blk, + nvt_idx, cam_ignore, + logic_serv); + } else { + ring = xive2_presenter_tctx_match(xptr, tctx, format, nvt_blk, + nvt_idx, cam_ignore, + logic_serv); + } + + /* + * Save the context and follow on to catch duplicates, + * that we don't support yet. + */ + if (ring != -1) { + if (match->tctx) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: already found a " + "thread context NVT %x/%x\n", + nvt_blk, nvt_idx); + return false; + } + + match->ring = ring; + match->tctx = tctx; + count++; + } + } + } + + return count; +} + +static uint8_t pnv_xive2_get_block_id(Xive2Router *xrtr) +{ + return pnv_xive2_block_id(PNV_XIVE2(xrtr)); +} + +/* + * The TIMA MMIO space is shared among the chips and to identify the + * chip from which the access is being done, we extract the chip id + * from the PIR. + */ +static PnvXive2 *pnv_xive2_tm_get_xive(PowerPCCPU *cpu) +{ + int pir = ppc_cpu_pir(cpu); + XivePresenter *xptr = XIVE_TCTX(pnv_cpu_state(cpu)->intc)->xptr; + PnvXive2 *xive = PNV_XIVE2(xptr); + + if (!pnv_xive2_is_cpu_enabled(xive, cpu)) { + xive2_error(xive, "IC: CPU %x is not enabled", pir); + } + return xive; +} + +/* + * The internal sources of the interrupt controller have no knowledge + * of the XIVE2 chip on which they reside. Encode the block id in the + * source interrupt number before forwarding the source event + * notification to the Router. This is required on a multichip system. + */ +static void pnv_xive2_notify(XiveNotifier *xn, uint32_t srcno, bool pq_checked) +{ + PnvXive2 *xive = PNV_XIVE2(xn); + uint8_t blk = pnv_xive2_block_id(xive); + + xive2_router_notify(xn, XIVE_EAS(blk, srcno), pq_checked); +} + +/* + * Set Translation Tables + * + * TODO add support for multiple sets + */ +static int pnv_xive2_stt_set_data(PnvXive2 *xive, uint64_t val) +{ + uint8_t tsel = GETFIELD(CQ_TAR_SELECT, xive->cq_regs[CQ_TAR >> 3]); + uint8_t entry = GETFIELD(CQ_TAR_ENTRY_SELECT, + xive->cq_regs[CQ_TAR >> 3]); + + switch (tsel) { + case CQ_TAR_NVPG: + case CQ_TAR_ESB: + case CQ_TAR_END: + xive->tables[tsel][entry] = val; + break; + default: + xive2_error(xive, "IC: unsupported table %d", tsel); + return -1; + } + + if (xive->cq_regs[CQ_TAR >> 3] & CQ_TAR_AUTOINC) { + xive->cq_regs[CQ_TAR >> 3] = SETFIELD(CQ_TAR_ENTRY_SELECT, + xive->cq_regs[CQ_TAR >> 3], ++entry); + } + + return 0; +} +/* + * Virtual Structure Tables (VST) configuration + */ +static void pnv_xive2_vst_set_exclusive(PnvXive2 *xive, uint8_t type, + uint8_t blk, uint64_t vsd) +{ + Xive2EndSource *end_xsrc = &xive->end_source; + XiveSource *xsrc = &xive->ipi_source; + const XiveVstInfo *info = &vst_infos[type]; + uint32_t page_shift = GETFIELD(VSD_TSIZE, vsd) + 12; + uint64_t vst_tsize = 1ull << page_shift; + uint64_t vst_addr = vsd & VSD_ADDRESS_MASK; + + /* Basic checks */ + + if (VSD_INDIRECT & vsd) { + if (!pnv_xive2_vst_page_size_allowed(page_shift)) { + xive2_error(xive, "VST: invalid %s page shift %d", info->name, + page_shift); + return; + } + } + + if (!QEMU_IS_ALIGNED(vst_addr, 1ull << page_shift)) { + xive2_error(xive, "VST: %s table address 0x%"PRIx64 + " is not aligned with page shift %d", + info->name, vst_addr, page_shift); + return; + } + + /* Record the table configuration (in SRAM on HW) */ + xive->vsds[type][blk] = vsd; + + /* Now tune the models with the configuration provided by the FW */ + + switch (type) { + case VST_ESB: + /* + * Backing store pages for the source PQ bits. The model does + * not use these PQ bits backed in RAM because the XiveSource + * model has its own. + * + * If the table is direct, we can compute the number of PQ + * entries provisioned by FW (such as skiboot) and resize the + * ESB window accordingly. + */ + if (!(VSD_INDIRECT & vsd)) { + memory_region_set_size(&xsrc->esb_mmio, vst_tsize * SBE_PER_BYTE + * (1ull << xsrc->esb_shift)); + } + + memory_region_add_subregion(&xive->esb_mmio, 0, &xsrc->esb_mmio); + break; + + case VST_EAS: /* Nothing to be done */ + break; + + case VST_END: + /* + * Backing store pages for the END. + */ + if (!(VSD_INDIRECT & vsd)) { + memory_region_set_size(&end_xsrc->esb_mmio, (vst_tsize / info->size) + * (1ull << end_xsrc->esb_shift)); + } + memory_region_add_subregion(&xive->end_mmio, 0, &end_xsrc->esb_mmio); + break; + + case VST_NVP: /* Not modeled */ + case VST_NVG: /* Not modeled */ + case VST_NVC: /* Not modeled */ + case VST_IC: /* Not modeled */ + case VST_SYNC: /* Not modeled */ + case VST_ERQ: /* Not modeled */ + break; + + default: + g_assert_not_reached(); + } +} + +/* + * Both PC and VC sub-engines are configured as each use the Virtual + * Structure Tables + */ +static void pnv_xive2_vst_set_data(PnvXive2 *xive, uint64_t vsd) +{ + uint8_t mode = GETFIELD(VSD_MODE, vsd); + uint8_t type = GETFIELD(VC_VSD_TABLE_SELECT, + xive->vc_regs[VC_VSD_TABLE_ADDR >> 3]); + uint8_t blk = GETFIELD(VC_VSD_TABLE_ADDRESS, + xive->vc_regs[VC_VSD_TABLE_ADDR >> 3]); + uint64_t vst_addr = vsd & VSD_ADDRESS_MASK; + + if (type > VST_ERQ) { + xive2_error(xive, "VST: invalid table type %d", type); + return; + } + + if (blk >= vst_infos[type].max_blocks) { + xive2_error(xive, "VST: invalid block id %d for" + " %s table", blk, vst_infos[type].name); + return; + } + + if (!vst_addr) { + xive2_error(xive, "VST: invalid %s table address", + vst_infos[type].name); + return; + } + + switch (mode) { + case VSD_MODE_FORWARD: + xive->vsds[type][blk] = vsd; + break; + + case VSD_MODE_EXCLUSIVE: + pnv_xive2_vst_set_exclusive(xive, type, blk, vsd); + break; + + default: + xive2_error(xive, "VST: unsupported table mode %d", mode); + return; + } +} + +/* + * MMIO handlers + */ + + +/* + * IC BAR layout + * + * Page 0: Internal CQ register accesses (reads & writes) + * Page 1: Internal PC register accesses (reads & writes) + * Page 2: Internal VC register accesses (reads & writes) + * Page 3: Internal TCTXT (TIMA) reg accesses (read & writes) + * Page 4: Notify Port page (writes only, w/data), + * Page 5: Reserved + * Page 6: Sync Poll page (writes only, dataless) + * Page 7: Sync Inject page (writes only, dataless) + * Page 8: LSI Trigger page (writes only, dataless) + * Page 9: LSI SB Management page (reads & writes dataless) + * Pages 10-255: Reserved + * Pages 256-383: Direct mapped Thread Context Area (reads & writes) + * covering the 128 threads in P10. + * Pages 384-511: Reserved + */ +typedef struct PnvXive2Region { + const char *name; + uint32_t pgoff; + uint32_t pgsize; + const MemoryRegionOps *ops; +} PnvXive2Region; + +static const MemoryRegionOps pnv_xive2_ic_cq_ops; +static const MemoryRegionOps pnv_xive2_ic_pc_ops; +static const MemoryRegionOps pnv_xive2_ic_vc_ops; +static const MemoryRegionOps pnv_xive2_ic_tctxt_ops; +static const MemoryRegionOps pnv_xive2_ic_notify_ops; +static const MemoryRegionOps pnv_xive2_ic_sync_ops; +static const MemoryRegionOps pnv_xive2_ic_lsi_ops; +static const MemoryRegionOps pnv_xive2_ic_tm_indirect_ops; + +/* 512 pages. 4K: 2M range, 64K: 32M range */ +static const PnvXive2Region pnv_xive2_ic_regions[] = { + { "xive-ic-cq", 0, 1, &pnv_xive2_ic_cq_ops }, + { "xive-ic-vc", 1, 1, &pnv_xive2_ic_vc_ops }, + { "xive-ic-pc", 2, 1, &pnv_xive2_ic_pc_ops }, + { "xive-ic-tctxt", 3, 1, &pnv_xive2_ic_tctxt_ops }, + { "xive-ic-notify", 4, 1, &pnv_xive2_ic_notify_ops }, + /* page 5 reserved */ + { "xive-ic-sync", 6, 2, &pnv_xive2_ic_sync_ops }, + { "xive-ic-lsi", 8, 2, &pnv_xive2_ic_lsi_ops }, + /* pages 10-255 reserved */ + { "xive-ic-tm-indirect", 256, 128, &pnv_xive2_ic_tm_indirect_ops }, + /* pages 384-511 reserved */ +}; + +/* + * CQ operations + */ + +static uint64_t pnv_xive2_ic_cq_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t reg = offset >> 3; + uint64_t val = 0; + + switch (offset) { + case CQ_XIVE_CAP: /* Set at reset */ + case CQ_XIVE_CFG: + val = xive->cq_regs[reg]; + break; + case CQ_MSGSND: /* TODO check the #cores of the machine */ + val = 0xffffffff00000000; + break; + case CQ_CFG_PB_GEN: + val = CQ_CFG_PB_GEN_PB_INIT; /* TODO: fix CQ_CFG_PB_GEN default value */ + break; + default: + xive2_error(xive, "CQ: invalid read @%"HWADDR_PRIx, offset); + } + + return val; +} + +static uint64_t pnv_xive2_bar_size(uint64_t val) +{ + return 1ull << (GETFIELD(CQ_BAR_RANGE, val) + 24); +} + +static void pnv_xive2_ic_cq_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + MemoryRegion *sysmem = get_system_memory(); + uint32_t reg = offset >> 3; + int i; + + switch (offset) { + case CQ_XIVE_CFG: + case CQ_RST_CTL: /* TODO: reset all BARs */ + break; + + case CQ_IC_BAR: + xive->ic_shift = val & CQ_IC_BAR_64K ? 16 : 12; + if (!(val & CQ_IC_BAR_VALID)) { + xive->ic_base = 0; + if (xive->cq_regs[reg] & CQ_IC_BAR_VALID) { + for (i = 0; i < ARRAY_SIZE(xive->ic_mmios); i++) { + memory_region_del_subregion(&xive->ic_mmio, + &xive->ic_mmios[i]); + } + memory_region_del_subregion(sysmem, &xive->ic_mmio); + } + } else { + xive->ic_base = val & ~(CQ_IC_BAR_VALID | CQ_IC_BAR_64K); + if (!(xive->cq_regs[reg] & CQ_IC_BAR_VALID)) { + for (i = 0; i < ARRAY_SIZE(xive->ic_mmios); i++) { + memory_region_add_subregion(&xive->ic_mmio, + pnv_xive2_ic_regions[i].pgoff << xive->ic_shift, + &xive->ic_mmios[i]); + } + memory_region_add_subregion(sysmem, xive->ic_base, + &xive->ic_mmio); + } + } + break; + + case CQ_TM_BAR: + xive->tm_shift = val & CQ_TM_BAR_64K ? 16 : 12; + if (!(val & CQ_TM_BAR_VALID)) { + xive->tm_base = 0; + if (xive->cq_regs[reg] & CQ_TM_BAR_VALID) { + memory_region_del_subregion(sysmem, &xive->tm_mmio); + } + } else { + xive->tm_base = val & ~(CQ_TM_BAR_VALID | CQ_TM_BAR_64K); + if (!(xive->cq_regs[reg] & CQ_TM_BAR_VALID)) { + memory_region_add_subregion(sysmem, xive->tm_base, + &xive->tm_mmio); + } + } + break; + + case CQ_ESB_BAR: + xive->esb_shift = val & CQ_BAR_64K ? 16 : 12; + if (!(val & CQ_BAR_VALID)) { + xive->esb_base = 0; + if (xive->cq_regs[reg] & CQ_BAR_VALID) { + memory_region_del_subregion(sysmem, &xive->esb_mmio); + } + } else { + xive->esb_base = val & CQ_BAR_ADDR; + if (!(xive->cq_regs[reg] & CQ_BAR_VALID)) { + memory_region_set_size(&xive->esb_mmio, + pnv_xive2_bar_size(val)); + memory_region_add_subregion(sysmem, xive->esb_base, + &xive->esb_mmio); + } + } + break; + + case CQ_END_BAR: + xive->end_shift = val & CQ_BAR_64K ? 16 : 12; + if (!(val & CQ_BAR_VALID)) { + xive->end_base = 0; + if (xive->cq_regs[reg] & CQ_BAR_VALID) { + memory_region_del_subregion(sysmem, &xive->end_mmio); + } + } else { + xive->end_base = val & CQ_BAR_ADDR; + if (!(xive->cq_regs[reg] & CQ_BAR_VALID)) { + memory_region_set_size(&xive->end_mmio, + pnv_xive2_bar_size(val)); + memory_region_add_subregion(sysmem, xive->end_base, + &xive->end_mmio); + } + } + break; + + case CQ_NVC_BAR: + xive->nvc_shift = val & CQ_BAR_64K ? 16 : 12; + if (!(val & CQ_BAR_VALID)) { + xive->nvc_base = 0; + if (xive->cq_regs[reg] & CQ_BAR_VALID) { + memory_region_del_subregion(sysmem, &xive->nvc_mmio); + } + } else { + xive->nvc_base = val & CQ_BAR_ADDR; + if (!(xive->cq_regs[reg] & CQ_BAR_VALID)) { + memory_region_set_size(&xive->nvc_mmio, + pnv_xive2_bar_size(val)); + memory_region_add_subregion(sysmem, xive->nvc_base, + &xive->nvc_mmio); + } + } + break; + + case CQ_NVPG_BAR: + xive->nvpg_shift = val & CQ_BAR_64K ? 16 : 12; + if (!(val & CQ_BAR_VALID)) { + xive->nvpg_base = 0; + if (xive->cq_regs[reg] & CQ_BAR_VALID) { + memory_region_del_subregion(sysmem, &xive->nvpg_mmio); + } + } else { + xive->nvpg_base = val & CQ_BAR_ADDR; + if (!(xive->cq_regs[reg] & CQ_BAR_VALID)) { + memory_region_set_size(&xive->nvpg_mmio, + pnv_xive2_bar_size(val)); + memory_region_add_subregion(sysmem, xive->nvpg_base, + &xive->nvpg_mmio); + } + } + break; + + case CQ_TAR: /* Set Translation Table Address */ + break; + case CQ_TDR: /* Set Translation Table Data */ + pnv_xive2_stt_set_data(xive, val); + break; + case CQ_FIRMASK_OR: /* FIR error reporting */ + break; + default: + xive2_error(xive, "CQ: invalid write 0x%"HWADDR_PRIx, offset); + return; + } + + xive->cq_regs[reg] = val; +} + +static const MemoryRegionOps pnv_xive2_ic_cq_ops = { + .read = pnv_xive2_ic_cq_read, + .write = pnv_xive2_ic_cq_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +static uint64_t pnv_xive2_ic_vc_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint64_t val = 0; + uint32_t reg = offset >> 3; + + switch (offset) { + /* + * VSD table settings. + */ + case VC_VSD_TABLE_ADDR: + case VC_VSD_TABLE_DATA: + val = xive->vc_regs[reg]; + break; + + /* + * ESB cache updates (not modeled) + */ + case VC_ESBC_FLUSH_CTRL: + xive->vc_regs[reg] &= ~VC_ESBC_FLUSH_CTRL_POLL_VALID; + val = xive->vc_regs[reg]; + break; + + /* + * EAS cache updates (not modeled) + */ + case VC_EASC_FLUSH_CTRL: + xive->vc_regs[reg] &= ~VC_EASC_FLUSH_CTRL_POLL_VALID; + val = xive->vc_regs[reg]; + break; + + /* + * END cache updates + */ + case VC_ENDC_WATCH0_SPEC: + xive->vc_regs[reg] &= ~(VC_ENDC_WATCH_FULL | VC_ENDC_WATCH_CONFLICT); + val = xive->vc_regs[reg]; + break; + + case VC_ENDC_WATCH0_DATA0: + /* + * Load DATA registers from cache with data requested by the + * SPEC register + */ + pnv_xive2_end_cache_load(xive); + val = xive->vc_regs[reg]; + break; + + case VC_ENDC_WATCH0_DATA1 ... VC_ENDC_WATCH0_DATA3: + val = xive->vc_regs[reg]; + break; + + case VC_ENDC_FLUSH_CTRL: + xive->vc_regs[reg] &= ~VC_ENDC_FLUSH_CTRL_POLL_VALID; + val = xive->vc_regs[reg]; + break; + + /* + * Indirect invalidation + */ + case VC_AT_MACRO_KILL_MASK: + val = xive->vc_regs[reg]; + break; + + case VC_AT_MACRO_KILL: + xive->vc_regs[reg] &= ~VC_AT_MACRO_KILL_VALID; + val = xive->vc_regs[reg]; + break; + + /* + * Interrupt fifo overflow in memory backing store (Not modeled) + */ + case VC_QUEUES_CFG_REM0 ... VC_QUEUES_CFG_REM6: + val = xive->vc_regs[reg]; + break; + + /* + * Synchronisation + */ + case VC_ENDC_SYNC_DONE: + val = VC_ENDC_SYNC_POLL_DONE; + break; + default: + xive2_error(xive, "VC: invalid read @%"HWADDR_PRIx, offset); + } + + return val; +} + +static void pnv_xive2_ic_vc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t reg = offset >> 3; + + switch (offset) { + /* + * VSD table settings. + */ + case VC_VSD_TABLE_ADDR: + break; + case VC_VSD_TABLE_DATA: + pnv_xive2_vst_set_data(xive, val); + break; + + /* + * ESB cache updates (not modeled) + */ + /* case VC_ESBC_FLUSH_CTRL: */ + case VC_ESBC_FLUSH_POLL: + xive->vc_regs[VC_ESBC_FLUSH_CTRL >> 3] |= VC_ESBC_FLUSH_CTRL_POLL_VALID; + /* ESB update */ + break; + + /* + * EAS cache updates (not modeled) + */ + /* case VC_EASC_FLUSH_CTRL: */ + case VC_EASC_FLUSH_POLL: + xive->vc_regs[VC_EASC_FLUSH_CTRL >> 3] |= VC_EASC_FLUSH_CTRL_POLL_VALID; + /* EAS update */ + break; + + /* + * END cache updates + */ + case VC_ENDC_WATCH0_SPEC: + val &= ~VC_ENDC_WATCH_CONFLICT; /* HW will set this bit */ + break; + + case VC_ENDC_WATCH0_DATA1 ... VC_ENDC_WATCH0_DATA3: + break; + case VC_ENDC_WATCH0_DATA0: + /* writing to DATA0 triggers the cache write */ + xive->vc_regs[reg] = val; + pnv_xive2_end_update(xive); + break; + + + /* case VC_ENDC_FLUSH_CTRL: */ + case VC_ENDC_FLUSH_POLL: + xive->vc_regs[VC_ENDC_FLUSH_CTRL >> 3] |= VC_ENDC_FLUSH_CTRL_POLL_VALID; + break; + + /* + * Indirect invalidation + */ + case VC_AT_MACRO_KILL: + case VC_AT_MACRO_KILL_MASK: + break; + + /* + * Interrupt fifo overflow in memory backing store (Not modeled) + */ + case VC_QUEUES_CFG_REM0 ... VC_QUEUES_CFG_REM6: + break; + + /* + * Synchronisation + */ + case VC_ENDC_SYNC_DONE: + break; + + default: + xive2_error(xive, "VC: invalid write @%"HWADDR_PRIx, offset); + return; + } + + xive->vc_regs[reg] = val; +} + +static const MemoryRegionOps pnv_xive2_ic_vc_ops = { + .read = pnv_xive2_ic_vc_read, + .write = pnv_xive2_ic_vc_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +static uint64_t pnv_xive2_ic_pc_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint64_t val = -1; + uint32_t reg = offset >> 3; + + switch (offset) { + /* + * VSD table settings. + */ + case PC_VSD_TABLE_ADDR: + case PC_VSD_TABLE_DATA: + val = xive->pc_regs[reg]; + break; + + /* + * cache updates + */ + case PC_NXC_WATCH0_SPEC: + xive->pc_regs[reg] &= ~(PC_NXC_WATCH_FULL | PC_NXC_WATCH_CONFLICT); + val = xive->pc_regs[reg]; + break; + + case PC_NXC_WATCH0_DATA0: + /* + * Load DATA registers from cache with data requested by the + * SPEC register + */ + pnv_xive2_nvp_cache_load(xive); + val = xive->pc_regs[reg]; + break; + + case PC_NXC_WATCH0_DATA1 ... PC_NXC_WATCH0_DATA3: + val = xive->pc_regs[reg]; + break; + + case PC_NXC_FLUSH_CTRL: + xive->pc_regs[reg] &= ~PC_NXC_FLUSH_CTRL_POLL_VALID; + val = xive->pc_regs[reg]; + break; + + /* + * Indirect invalidation + */ + case PC_AT_KILL: + xive->pc_regs[reg] &= ~PC_AT_KILL_VALID; + val = xive->pc_regs[reg]; + break; + + default: + xive2_error(xive, "PC: invalid read @%"HWADDR_PRIx, offset); + } + + return val; +} + +static void pnv_xive2_ic_pc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t reg = offset >> 3; + + switch (offset) { + + /* + * VSD table settings. Only taken into account in the VC + * sub-engine because the Xive2Router model combines both VC and PC + * sub-engines + */ + case PC_VSD_TABLE_ADDR: + case PC_VSD_TABLE_DATA: + break; + + /* + * cache updates + */ + case PC_NXC_WATCH0_SPEC: + val &= ~PC_NXC_WATCH_CONFLICT; /* HW will set this bit */ + break; + + case PC_NXC_WATCH0_DATA1 ... PC_NXC_WATCH0_DATA3: + break; + case PC_NXC_WATCH0_DATA0: + /* writing to DATA0 triggers the cache write */ + xive->pc_regs[reg] = val; + pnv_xive2_nvp_update(xive); + break; + + /* case PC_NXC_FLUSH_CTRL: */ + case PC_NXC_FLUSH_POLL: + xive->pc_regs[PC_NXC_FLUSH_CTRL >> 3] |= PC_NXC_FLUSH_CTRL_POLL_VALID; + break; + + /* + * Indirect invalidation + */ + case PC_AT_KILL: + case PC_AT_KILL_MASK: + break; + + default: + xive2_error(xive, "PC: invalid write @%"HWADDR_PRIx, offset); + return; + } + + xive->pc_regs[reg] = val; +} + +static const MemoryRegionOps pnv_xive2_ic_pc_ops = { + .read = pnv_xive2_ic_pc_read, + .write = pnv_xive2_ic_pc_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + + +static uint64_t pnv_xive2_ic_tctxt_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint64_t val = -1; + uint32_t reg = offset >> 3; + + switch (offset) { + /* + * XIVE2 hardware thread enablement + */ + case TCTXT_EN0: + case TCTXT_EN1: + val = xive->tctxt_regs[reg]; + break; + + case TCTXT_EN0_SET: + case TCTXT_EN0_RESET: + val = xive->tctxt_regs[TCTXT_EN0 >> 3]; + break; + case TCTXT_EN1_SET: + case TCTXT_EN1_RESET: + val = xive->tctxt_regs[TCTXT_EN1 >> 3]; + break; + default: + xive2_error(xive, "TCTXT: invalid read @%"HWADDR_PRIx, offset); + } + + return val; +} + +static void pnv_xive2_ic_tctxt_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t reg = offset >> 3; + + switch (offset) { + /* + * XIVE2 hardware thread enablement + */ + case TCTXT_EN0: /* Physical Thread Enable */ + case TCTXT_EN1: /* Physical Thread Enable (fused core) */ + break; + + case TCTXT_EN0_SET: + xive->tctxt_regs[TCTXT_EN0 >> 3] |= val; + break; + case TCTXT_EN1_SET: + xive->tctxt_regs[TCTXT_EN1 >> 3] |= val; + break; + case TCTXT_EN0_RESET: + xive->tctxt_regs[TCTXT_EN0 >> 3] &= ~val; + break; + case TCTXT_EN1_RESET: + xive->tctxt_regs[TCTXT_EN1 >> 3] &= ~val; + break; + + default: + xive2_error(xive, "TCTXT: invalid write @%"HWADDR_PRIx, offset); + return; + } + + xive->pc_regs[reg] = val; +} + +static const MemoryRegionOps pnv_xive2_ic_tctxt_ops = { + .read = pnv_xive2_ic_tctxt_read, + .write = pnv_xive2_ic_tctxt_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +/* + * Redirect XSCOM to MMIO handlers + */ +static uint64_t pnv_xive2_xscom_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint64_t val = -1; + uint32_t xscom_reg = offset >> 3; + uint32_t mmio_offset = (xscom_reg & 0xFF) << 3; + + switch (xscom_reg) { + case 0x000 ... 0x0FF: + val = pnv_xive2_ic_cq_read(opaque, mmio_offset, size); + break; + case 0x100 ... 0x1FF: + val = pnv_xive2_ic_vc_read(opaque, mmio_offset, size); + break; + case 0x200 ... 0x2FF: + val = pnv_xive2_ic_pc_read(opaque, mmio_offset, size); + break; + case 0x300 ... 0x3FF: + val = pnv_xive2_ic_tctxt_read(opaque, mmio_offset, size); + break; + default: + xive2_error(xive, "XSCOM: invalid read @%"HWADDR_PRIx, offset); + } + + return val; +} + +static void pnv_xive2_xscom_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t xscom_reg = offset >> 3; + uint32_t mmio_offset = (xscom_reg & 0xFF) << 3; + + switch (xscom_reg) { + case 0x000 ... 0x0FF: + pnv_xive2_ic_cq_write(opaque, mmio_offset, val, size); + break; + case 0x100 ... 0x1FF: + pnv_xive2_ic_vc_write(opaque, mmio_offset, val, size); + break; + case 0x200 ... 0x2FF: + pnv_xive2_ic_pc_write(opaque, mmio_offset, val, size); + break; + case 0x300 ... 0x3FF: + pnv_xive2_ic_tctxt_write(opaque, mmio_offset, val, size); + break; + default: + xive2_error(xive, "XSCOM: invalid write @%"HWADDR_PRIx, offset); + } +} + +static const MemoryRegionOps pnv_xive2_xscom_ops = { + .read = pnv_xive2_xscom_read, + .write = pnv_xive2_xscom_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +/* + * Notify port page. The layout is compatible between 4K and 64K pages : + * + * Page 1 Notify page (writes only) + * 0x000 - 0x7FF IPI interrupt (NPU) + * 0x800 - 0xFFF HW interrupt triggers (PSI, PHB) + */ + +static void pnv_xive2_ic_hw_trigger(PnvXive2 *xive, hwaddr addr, + uint64_t val) +{ + uint8_t blk; + uint32_t idx; + + if (val & XIVE_TRIGGER_END) { + xive2_error(xive, "IC: END trigger at @0x%"HWADDR_PRIx" data 0x%"PRIx64, + addr, val); + return; + } + + /* + * Forward the source event notification directly to the Router. + * The source interrupt number should already be correctly encoded + * with the chip block id by the sending device (PHB, PSI). + */ + blk = XIVE_EAS_BLOCK(val); + idx = XIVE_EAS_INDEX(val); + + xive2_router_notify(XIVE_NOTIFIER(xive), XIVE_EAS(blk, idx), + !!(val & XIVE_TRIGGER_PQ)); +} + +static void pnv_xive2_ic_notify_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + /* VC: IPI triggers */ + switch (offset) { + case 0x000 ... 0x7FF: + /* TODO: check IPI notify sub-page routing */ + pnv_xive2_ic_hw_trigger(opaque, offset, val); + break; + + /* VC: HW triggers */ + case 0x800 ... 0xFFF: + pnv_xive2_ic_hw_trigger(opaque, offset, val); + break; + + default: + xive2_error(xive, "NOTIFY: invalid write @%"HWADDR_PRIx, offset); + } +} + +static uint64_t pnv_xive2_ic_notify_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + /* loads are invalid */ + xive2_error(xive, "NOTIFY: invalid read @%"HWADDR_PRIx, offset); + return -1; +} + +static const MemoryRegionOps pnv_xive2_ic_notify_ops = { + .read = pnv_xive2_ic_notify_read, + .write = pnv_xive2_ic_notify_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +static uint64_t pnv_xive2_ic_lsi_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + xive2_error(xive, "LSI: invalid read @%"HWADDR_PRIx, offset); + return -1; +} + +static void pnv_xive2_ic_lsi_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + xive2_error(xive, "LSI: invalid write @%"HWADDR_PRIx, offset); +} + +static const MemoryRegionOps pnv_xive2_ic_lsi_ops = { + .read = pnv_xive2_ic_lsi_read, + .write = pnv_xive2_ic_lsi_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +/* + * Sync MMIO page (write only) + */ +#define PNV_XIVE2_SYNC_IPI 0x000 +#define PNV_XIVE2_SYNC_HW 0x080 +#define PNV_XIVE2_SYNC_NxC 0x100 +#define PNV_XIVE2_SYNC_INT 0x180 +#define PNV_XIVE2_SYNC_OS_ESC 0x200 +#define PNV_XIVE2_SYNC_POOL_ESC 0x280 +#define PNV_XIVE2_SYNC_HARD_ESC 0x300 + +static uint64_t pnv_xive2_ic_sync_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + /* loads are invalid */ + xive2_error(xive, "SYNC: invalid read @%"HWADDR_PRIx, offset); + return -1; +} + +static void pnv_xive2_ic_sync_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + switch (offset) { + case PNV_XIVE2_SYNC_IPI: + case PNV_XIVE2_SYNC_HW: + case PNV_XIVE2_SYNC_NxC: + case PNV_XIVE2_SYNC_INT: + case PNV_XIVE2_SYNC_OS_ESC: + case PNV_XIVE2_SYNC_POOL_ESC: + case PNV_XIVE2_SYNC_HARD_ESC: + break; + default: + xive2_error(xive, "SYNC: invalid write @%"HWADDR_PRIx, offset); + } +} + +static const MemoryRegionOps pnv_xive2_ic_sync_ops = { + .read = pnv_xive2_ic_sync_read, + .write = pnv_xive2_ic_sync_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +/* + * When the TM direct pages of the IC controller are accessed, the + * target HW thread is deduced from the page offset. + */ +static XiveTCTX *pnv_xive2_get_indirect_tctx(PnvXive2 *xive, uint32_t pir) +{ + PnvChip *chip = xive->chip; + PowerPCCPU *cpu = NULL; + + cpu = pnv_chip_find_cpu(chip, pir); + if (!cpu) { + xive2_error(xive, "IC: invalid PIR %x for indirect access", pir); + return NULL; + } + + if (!pnv_xive2_is_cpu_enabled(xive, cpu)) { + xive2_error(xive, "IC: CPU %x is not enabled", pir); + } + + return XIVE_TCTX(pnv_cpu_state(cpu)->intc); +} + +static uint64_t pnv_xive2_ic_tm_indirect_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t pir = offset >> xive->ic_shift; + XiveTCTX *tctx = pnv_xive2_get_indirect_tctx(xive, pir); + uint64_t val = -1; + + if (tctx) { + val = xive_tctx_tm_read(NULL, tctx, offset, size); + } + + return val; +} + +static void pnv_xive2_ic_tm_indirect_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + uint32_t pir = offset >> xive->ic_shift; + XiveTCTX *tctx = pnv_xive2_get_indirect_tctx(xive, pir); + + if (tctx) { + xive_tctx_tm_write(NULL, tctx, offset, val, size); + } +} + +static const MemoryRegionOps pnv_xive2_ic_tm_indirect_ops = { + .read = pnv_xive2_ic_tm_indirect_read, + .write = pnv_xive2_ic_tm_indirect_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +/* + * TIMA ops + */ + +/* + * Special TIMA offsets to handle accesses in a POWER10 way. + * + * Only the CAM line updates done by the hypervisor should be handled + * specifically. + */ +#define HV_PAGE_OFFSET (XIVE_TM_HV_PAGE << TM_SHIFT) +#define HV_PUSH_OS_CTX_OFFSET (HV_PAGE_OFFSET | (TM_QW1_OS + TM_WORD2)) +#define HV_PULL_OS_CTX_OFFSET (HV_PAGE_OFFSET | TM_SPC_PULL_OS_CTX) + +static void pnv_xive2_tm_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + PowerPCCPU *cpu = POWERPC_CPU(current_cpu); + PnvXive2 *xive = pnv_xive2_tm_get_xive(cpu); + XiveTCTX *tctx = XIVE_TCTX(pnv_cpu_state(cpu)->intc); + XivePresenter *xptr = XIVE_PRESENTER(xive); + bool gen1_tima_os = + xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS; + + /* TODO: should we switch the TM ops table instead ? */ + if (!gen1_tima_os && offset == HV_PUSH_OS_CTX_OFFSET) { + xive2_tm_push_os_ctx(xptr, tctx, offset, value, size); + return; + } + + /* Other TM ops are the same as XIVE1 */ + xive_tctx_tm_write(xptr, tctx, offset, value, size); +} + +static uint64_t pnv_xive2_tm_read(void *opaque, hwaddr offset, unsigned size) +{ + PowerPCCPU *cpu = POWERPC_CPU(current_cpu); + PnvXive2 *xive = pnv_xive2_tm_get_xive(cpu); + XiveTCTX *tctx = XIVE_TCTX(pnv_cpu_state(cpu)->intc); + XivePresenter *xptr = XIVE_PRESENTER(xive); + bool gen1_tima_os = + xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS; + + /* TODO: should we switch the TM ops table instead ? */ + if (!gen1_tima_os && offset == HV_PULL_OS_CTX_OFFSET) { + return xive2_tm_pull_os_ctx(xptr, tctx, offset, size); + } + + /* Other TM ops are the same as XIVE1 */ + return xive_tctx_tm_read(xptr, tctx, offset, size); +} + +static const MemoryRegionOps pnv_xive2_tm_ops = { + .read = pnv_xive2_tm_read, + .write = pnv_xive2_tm_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 1, + .max_access_size = 8, + }, +}; + +static uint64_t pnv_xive2_nvc_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + xive2_error(xive, "NVC: invalid read @%"HWADDR_PRIx, offset); + return -1; +} + +static void pnv_xive2_nvc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + xive2_error(xive, "NVC: invalid write @%"HWADDR_PRIx, offset); +} + +static const MemoryRegionOps pnv_xive2_nvc_ops = { + .read = pnv_xive2_nvc_read, + .write = pnv_xive2_nvc_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +static uint64_t pnv_xive2_nvpg_read(void *opaque, hwaddr offset, + unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + xive2_error(xive, "NVPG: invalid read @%"HWADDR_PRIx, offset); + return -1; +} + +static void pnv_xive2_nvpg_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + PnvXive2 *xive = PNV_XIVE2(opaque); + + xive2_error(xive, "NVPG: invalid write @%"HWADDR_PRIx, offset); +} + +static const MemoryRegionOps pnv_xive2_nvpg_ops = { + .read = pnv_xive2_nvpg_read, + .write = pnv_xive2_nvpg_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +/* + * POWER10 default capabilities: 0x2000120076f000FC + */ +#define PNV_XIVE2_CAPABILITIES 0x2000120076f000FC + +/* + * POWER10 default configuration: 0x0030000033000000 + * + * 8bits thread id was dropped for P10 + */ +#define PNV_XIVE2_CONFIGURATION 0x0030000033000000 + +static void pnv_xive2_reset(void *dev) +{ + PnvXive2 *xive = PNV_XIVE2(dev); + XiveSource *xsrc = &xive->ipi_source; + Xive2EndSource *end_xsrc = &xive->end_source; + + xive->cq_regs[CQ_XIVE_CAP >> 3] = xive->capabilities; + xive->cq_regs[CQ_XIVE_CFG >> 3] = xive->config; + + /* HW hardwires the #Topology of the chip in the block field */ + xive->cq_regs[CQ_XIVE_CFG >> 3] |= + SETFIELD(CQ_XIVE_CFG_HYP_HARD_BLOCK_ID, 0ull, xive->chip->chip_id); + + /* Set default page size to 64k */ + xive->ic_shift = xive->esb_shift = xive->end_shift = 16; + xive->nvc_shift = xive->nvpg_shift = xive->tm_shift = 16; + + /* Clear source MMIOs */ + if (memory_region_is_mapped(&xsrc->esb_mmio)) { + memory_region_del_subregion(&xive->esb_mmio, &xsrc->esb_mmio); + } + + if (memory_region_is_mapped(&end_xsrc->esb_mmio)) { + memory_region_del_subregion(&xive->end_mmio, &end_xsrc->esb_mmio); + } +} + +/* + * Maximum number of IRQs and ENDs supported by HW. Will be tuned by + * software. + */ +#define PNV_XIVE2_NR_IRQS (PNV10_XIVE2_ESB_SIZE / (1ull << XIVE_ESB_64K_2PAGE)) +#define PNV_XIVE2_NR_ENDS (PNV10_XIVE2_END_SIZE / (1ull << XIVE_ESB_64K_2PAGE)) + +static void pnv_xive2_realize(DeviceState *dev, Error **errp) +{ + PnvXive2 *xive = PNV_XIVE2(dev); + PnvXive2Class *pxc = PNV_XIVE2_GET_CLASS(dev); + XiveSource *xsrc = &xive->ipi_source; + Xive2EndSource *end_xsrc = &xive->end_source; + Error *local_err = NULL; + int i; + + pxc->parent_realize(dev, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + assert(xive->chip); + + /* + * The XiveSource and Xive2EndSource objects are realized with the + * maximum allowed HW configuration. The ESB MMIO regions will be + * resized dynamically when the controller is configured by the FW + * to limit accesses to resources not provisioned. + */ + object_property_set_int(OBJECT(xsrc), "flags", XIVE_SRC_STORE_EOI, + &error_fatal); + object_property_set_int(OBJECT(xsrc), "nr-irqs", PNV_XIVE2_NR_IRQS, + &error_fatal); + object_property_set_link(OBJECT(xsrc), "xive", OBJECT(xive), + &error_fatal); + qdev_realize(DEVICE(xsrc), NULL, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + object_property_set_int(OBJECT(end_xsrc), "nr-ends", PNV_XIVE2_NR_ENDS, + &error_fatal); + object_property_set_link(OBJECT(end_xsrc), "xive", OBJECT(xive), + &error_abort); + qdev_realize(DEVICE(end_xsrc), NULL, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + /* XSCOM region, used for initial configuration of the BARs */ + memory_region_init_io(&xive->xscom_regs, OBJECT(dev), + &pnv_xive2_xscom_ops, xive, "xscom-xive", + PNV10_XSCOM_XIVE2_SIZE << 3); + + /* Interrupt controller MMIO regions */ + xive->ic_shift = 16; + memory_region_init(&xive->ic_mmio, OBJECT(dev), "xive-ic", + PNV10_XIVE2_IC_SIZE); + + for (i = 0; i < ARRAY_SIZE(xive->ic_mmios); i++) { + memory_region_init_io(&xive->ic_mmios[i], OBJECT(dev), + pnv_xive2_ic_regions[i].ops, xive, + pnv_xive2_ic_regions[i].name, + pnv_xive2_ic_regions[i].pgsize << xive->ic_shift); + } + + /* + * VC MMIO regions. + */ + xive->esb_shift = 16; + xive->end_shift = 16; + memory_region_init(&xive->esb_mmio, OBJECT(xive), "xive-esb", + PNV10_XIVE2_ESB_SIZE); + memory_region_init(&xive->end_mmio, OBJECT(xive), "xive-end", + PNV10_XIVE2_END_SIZE); + + /* Presenter Controller MMIO region (not modeled) */ + xive->nvc_shift = 16; + xive->nvpg_shift = 16; + memory_region_init_io(&xive->nvc_mmio, OBJECT(dev), + &pnv_xive2_nvc_ops, xive, + "xive-nvc", PNV10_XIVE2_NVC_SIZE); + + memory_region_init_io(&xive->nvpg_mmio, OBJECT(dev), + &pnv_xive2_nvpg_ops, xive, + "xive-nvpg", PNV10_XIVE2_NVPG_SIZE); + + /* Thread Interrupt Management Area (Direct) */ + xive->tm_shift = 16; + memory_region_init_io(&xive->tm_mmio, OBJECT(dev), &pnv_xive2_tm_ops, + xive, "xive-tima", PNV10_XIVE2_TM_SIZE); + + qemu_register_reset(pnv_xive2_reset, dev); +} + +static Property pnv_xive2_properties[] = { + DEFINE_PROP_UINT64("ic-bar", PnvXive2, ic_base, 0), + DEFINE_PROP_UINT64("esb-bar", PnvXive2, esb_base, 0), + DEFINE_PROP_UINT64("end-bar", PnvXive2, end_base, 0), + DEFINE_PROP_UINT64("nvc-bar", PnvXive2, nvc_base, 0), + DEFINE_PROP_UINT64("nvpg-bar", PnvXive2, nvpg_base, 0), + DEFINE_PROP_UINT64("tm-bar", PnvXive2, tm_base, 0), + DEFINE_PROP_UINT64("capabilities", PnvXive2, capabilities, + PNV_XIVE2_CAPABILITIES), + DEFINE_PROP_UINT64("config", PnvXive2, config, + PNV_XIVE2_CONFIGURATION), + DEFINE_PROP_LINK("chip", PnvXive2, chip, TYPE_PNV_CHIP, PnvChip *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void pnv_xive2_instance_init(Object *obj) +{ + PnvXive2 *xive = PNV_XIVE2(obj); + + object_initialize_child(obj, "ipi_source", &xive->ipi_source, + TYPE_XIVE_SOURCE); + object_initialize_child(obj, "end_source", &xive->end_source, + TYPE_XIVE2_END_SOURCE); +} + +static int pnv_xive2_dt_xscom(PnvXScomInterface *dev, void *fdt, + int xscom_offset) +{ + const char compat_p10[] = "ibm,power10-xive-x"; + char *name; + int offset; + uint32_t reg[] = { + cpu_to_be32(PNV10_XSCOM_XIVE2_BASE), + cpu_to_be32(PNV10_XSCOM_XIVE2_SIZE) + }; + + name = g_strdup_printf("xive@%x", PNV10_XSCOM_XIVE2_BASE); + offset = fdt_add_subnode(fdt, xscom_offset, name); + _FDT(offset); + g_free(name); + + _FDT((fdt_setprop(fdt, offset, "reg", reg, sizeof(reg)))); + _FDT(fdt_setprop(fdt, offset, "compatible", compat_p10, + sizeof(compat_p10))); + return 0; +} + +static void pnv_xive2_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PnvXScomInterfaceClass *xdc = PNV_XSCOM_INTERFACE_CLASS(klass); + Xive2RouterClass *xrc = XIVE2_ROUTER_CLASS(klass); + XiveNotifierClass *xnc = XIVE_NOTIFIER_CLASS(klass); + XivePresenterClass *xpc = XIVE_PRESENTER_CLASS(klass); + PnvXive2Class *pxc = PNV_XIVE2_CLASS(klass); + + xdc->dt_xscom = pnv_xive2_dt_xscom; + + dc->desc = "PowerNV XIVE2 Interrupt Controller (POWER10)"; + device_class_set_parent_realize(dc, pnv_xive2_realize, + &pxc->parent_realize); + device_class_set_props(dc, pnv_xive2_properties); + + xrc->get_eas = pnv_xive2_get_eas; + xrc->get_pq = pnv_xive2_get_pq; + xrc->set_pq = pnv_xive2_set_pq; + xrc->get_end = pnv_xive2_get_end; + xrc->write_end = pnv_xive2_write_end; + xrc->get_nvp = pnv_xive2_get_nvp; + xrc->write_nvp = pnv_xive2_write_nvp; + xrc->get_config = pnv_xive2_get_config; + xrc->get_block_id = pnv_xive2_get_block_id; + + xnc->notify = pnv_xive2_notify; + + xpc->match_nvt = pnv_xive2_match_nvt; +}; + +static const TypeInfo pnv_xive2_info = { + .name = TYPE_PNV_XIVE2, + .parent = TYPE_XIVE2_ROUTER, + .instance_init = pnv_xive2_instance_init, + .instance_size = sizeof(PnvXive2), + .class_init = pnv_xive2_class_init, + .class_size = sizeof(PnvXive2Class), + .interfaces = (InterfaceInfo[]) { + { TYPE_PNV_XSCOM_INTERFACE }, + { } + } +}; + +static void pnv_xive2_register_types(void) +{ + type_register_static(&pnv_xive2_info); +} + +type_init(pnv_xive2_register_types) + +static void xive2_nvp_pic_print_info(Xive2Nvp *nvp, uint32_t nvp_idx, + Monitor *mon) +{ + uint8_t eq_blk = xive_get_field32(NVP2_W5_VP_END_BLOCK, nvp->w5); + uint32_t eq_idx = xive_get_field32(NVP2_W5_VP_END_INDEX, nvp->w5); + + if (!xive2_nvp_is_valid(nvp)) { + return; + } + + monitor_printf(mon, " %08x end:%02x/%04x IPB:%02x", + nvp_idx, eq_blk, eq_idx, + xive_get_field32(NVP2_W2_IPB, nvp->w2)); + /* + * When the NVP is HW controlled, more fields are updated + */ + if (xive2_nvp_is_hw(nvp)) { + monitor_printf(mon, " CPPR:%02x", + xive_get_field32(NVP2_W2_CPPR, nvp->w2)); + if (xive2_nvp_is_co(nvp)) { + monitor_printf(mon, " CO:%04x", + xive_get_field32(NVP2_W1_CO_THRID, nvp->w1)); + } + } + monitor_printf(mon, "\n"); +} + +/* + * If the table is direct, we can compute the number of PQ entries + * provisioned by FW. + */ +static uint32_t pnv_xive2_nr_esbs(PnvXive2 *xive) +{ + uint8_t blk = pnv_xive2_block_id(xive); + uint64_t vsd = xive->vsds[VST_ESB][blk]; + uint64_t vst_tsize = 1ull << (GETFIELD(VSD_TSIZE, vsd) + 12); + + return VSD_INDIRECT & vsd ? 0 : vst_tsize * SBE_PER_BYTE; +} + +/* + * Compute the number of entries per indirect subpage. + */ +static uint64_t pnv_xive2_vst_per_subpage(PnvXive2 *xive, uint32_t type) +{ + uint8_t blk = pnv_xive2_block_id(xive); + uint64_t vsd = xive->vsds[type][blk]; + const XiveVstInfo *info = &vst_infos[type]; + uint64_t vsd_addr; + uint32_t page_shift; + + /* For direct tables, fake a valid value */ + if (!(VSD_INDIRECT & vsd)) { + return 1; + } + + /* Get the page size of the indirect table. */ + vsd_addr = vsd & VSD_ADDRESS_MASK; + ldq_be_dma(&address_space_memory, vsd_addr, &vsd, MEMTXATTRS_UNSPECIFIED); + + if (!(vsd & VSD_ADDRESS_MASK)) { +#ifdef XIVE2_DEBUG + xive2_error(xive, "VST: invalid %s entry!?", info->name); +#endif + return 0; + } + + page_shift = GETFIELD(VSD_TSIZE, vsd) + 12; + + if (!pnv_xive2_vst_page_size_allowed(page_shift)) { + xive2_error(xive, "VST: invalid %s page shift %d", info->name, + page_shift); + return 0; + } + + return (1ull << page_shift) / info->size; +} + +void pnv_xive2_pic_print_info(PnvXive2 *xive, Monitor *mon) +{ + Xive2Router *xrtr = XIVE2_ROUTER(xive); + uint8_t blk = pnv_xive2_block_id(xive); + uint8_t chip_id = xive->chip->chip_id; + uint32_t srcno0 = XIVE_EAS(blk, 0); + uint32_t nr_esbs = pnv_xive2_nr_esbs(xive); + Xive2Eas eas; + Xive2End end; + Xive2Nvp nvp; + int i; + uint64_t xive_nvp_per_subpage; + + monitor_printf(mon, "XIVE[%x] Source %08x .. %08x\n", blk, srcno0, + srcno0 + nr_esbs - 1); + xive_source_pic_print_info(&xive->ipi_source, srcno0, mon); + + monitor_printf(mon, "XIVE[%x] EAT %08x .. %08x\n", blk, srcno0, + srcno0 + nr_esbs - 1); + for (i = 0; i < nr_esbs; i++) { + if (xive2_router_get_eas(xrtr, blk, i, &eas)) { + break; + } + if (!xive2_eas_is_masked(&eas)) { + xive2_eas_pic_print_info(&eas, i, mon); + } + } + + monitor_printf(mon, "XIVE[%x] #%d END Escalation EAT\n", chip_id, blk); + i = 0; + while (!xive2_router_get_end(xrtr, blk, i, &end)) { + xive2_end_eas_pic_print_info(&end, i++, mon); + } + + monitor_printf(mon, "XIVE[%x] #%d ENDT\n", chip_id, blk); + i = 0; + while (!xive2_router_get_end(xrtr, blk, i, &end)) { + xive2_end_pic_print_info(&end, i++, mon); + } + + monitor_printf(mon, "XIVE[%x] #%d NVPT %08x .. %08x\n", chip_id, blk, + 0, XIVE2_NVP_COUNT - 1); + xive_nvp_per_subpage = pnv_xive2_vst_per_subpage(xive, VST_NVP); + for (i = 0; i < XIVE2_NVP_COUNT; i += xive_nvp_per_subpage) { + while (!xive2_router_get_nvp(xrtr, blk, i, &nvp)) { + xive2_nvp_pic_print_info(&nvp, i++, mon); + } + } +} diff --git a/hw/intc/pnv_xive2_regs.h b/hw/intc/pnv_xive2_regs.h new file mode 100644 index 0000000000..0c096e4adb --- /dev/null +++ b/hw/intc/pnv_xive2_regs.h @@ -0,0 +1,442 @@ +/* + * QEMU PowerPC XIVE2 interrupt controller model (POWER10) + * + * Copyright (c) 2019-2022, IBM Corporation. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ + +#ifndef PPC_PNV_XIVE2_REGS_H +#define PPC_PNV_XIVE2_REGS_H + +/* + * CQ Common Queue (PowerBus bridge) Registers + */ + +/* XIVE2 Capabilities */ +#define X_CQ_XIVE_CAP 0x02 +#define CQ_XIVE_CAP 0x010 +#define CQ_XIVE_CAP_VERSION PPC_BITMASK(0, 3) +/* 4:6 reserved */ +#define CQ_XIVE_CAP_USER_INT_PRIO PPC_BITMASK(8, 9) +#define CQ_XIVE_CAP_USER_INT_PRIO_1 0 +#define CQ_XIVE_CAP_USER_INT_PRIO_1_2 1 +#define CQ_XIVE_CAP_USER_INT_PRIO_1_4 2 +#define CQ_XIVE_CAP_USER_INT_PRIO_1_8 3 +#define CQ_XIVE_CAP_VP_INT_PRIO PPC_BITMASK(10, 11) +#define CQ_XIVE_CAP_VP_INT_PRIO_1_8 0 +#define CQ_XIVE_CAP_VP_INT_PRIO_2_8 1 +#define CQ_XIVE_CAP_VP_INT_PRIO_4_8 2 +#define CQ_XIVE_CAP_VP_INT_PRIO_8 3 +#define CQ_XIVE_CAP_BLOCK_ID_WIDTH PPC_BITMASK(12, 13) +#define CQ_XIVE_CAP_VP_SAVE_RESTORE PPC_BIT(38) + +#define CQ_XIVE_CAP_PHB_PQ_DISABLE PPC_BIT(56) +#define CQ_XIVE_CAP_PHB_ABT PPC_BIT(57) +#define CQ_XIVE_CAP_EXPLOITATION_MODE PPC_BIT(58) +#define CQ_XIVE_CAP_STORE_EOI PPC_BIT(59) + +/* XIVE2 Configuration */ +#define X_CQ_XIVE_CFG 0x03 +#define CQ_XIVE_CFG 0x018 + +/* 0:7 reserved */ +#define CQ_XIVE_CFG_USER_INT_PRIO PPC_BITMASK(8, 9) +#define CQ_XIVE_CFG_VP_INT_PRIO PPC_BITMASK(10, 11) +#define CQ_XIVE_CFG_INT_PRIO_1 0 +#define CQ_XIVE_CFG_INT_PRIO_2 1 +#define CQ_XIVE_CFG_INT_PRIO_4 2 +#define CQ_XIVE_CFG_INT_PRIO_8 3 +#define CQ_XIVE_CFG_BLOCK_ID_WIDTH PPC_BITMASK(12, 13) +#define CQ_XIVE_CFG_BLOCK_ID_4BITS 0 +#define CQ_XIVE_CFG_BLOCK_ID_5BITS 1 +#define CQ_XIVE_CFG_BLOCK_ID_6BITS 2 +#define CQ_XIVE_CFG_BLOCK_ID_7BITS 3 +#define CQ_XIVE_CFG_HYP_HARD_RANGE PPC_BITMASK(14, 15) +#define CQ_XIVE_CFG_THREADID_7BITS 0 +#define CQ_XIVE_CFG_THREADID_8BITS 1 +#define CQ_XIVE_CFG_THREADID_9BITS 2 +#define CQ_XIVE_CFG_THREADID_10BITs 3 +#define CQ_XIVE_CFG_HYP_HARD_BLKID_OVERRIDE PPC_BIT(16) +#define CQ_XIVE_CFG_HYP_HARD_BLOCK_ID PPC_BITMASK(17, 23) + +#define CQ_XIVE_CFG_GEN1_TIMA_OS PPC_BIT(24) +#define CQ_XIVE_CFG_GEN1_TIMA_HYP PPC_BIT(25) +#define CQ_XIVE_CFG_GEN1_TIMA_HYP_BLK0 PPC_BIT(26) /* 0 if bit[25]=0 */ +#define CQ_XIVE_CFG_GEN1_TIMA_CROWD_DIS PPC_BIT(27) /* 0 if bit[25]=0 */ +#define CQ_XIVE_CFG_GEN1_END_ESX PPC_BIT(28) +#define CQ_XIVE_CFG_EN_VP_SAVE_RESTORE PPC_BIT(38) /* 0 if bit[25]=1 */ +#define CQ_XIVE_CFG_EN_VP_SAVE_REST_STRICT PPC_BIT(39) /* 0 if bit[25]=1 */ + +/* Interrupt Controller Base Address Register - 512 pages (32M) */ +#define X_CQ_IC_BAR 0x08 +#define CQ_IC_BAR 0x040 +#define CQ_IC_BAR_VALID PPC_BIT(0) +#define CQ_IC_BAR_64K PPC_BIT(1) +/* 2:7 reserved */ +#define CQ_IC_BAR_ADDR PPC_BITMASK(8, 42) +/* 43:63 reserved */ + +/* Thread Management Base Address Register - 4 pages */ +#define X_CQ_TM_BAR 0x09 +#define CQ_TM_BAR 0x048 +#define CQ_TM_BAR_VALID PPC_BIT(0) +#define CQ_TM_BAR_64K PPC_BIT(1) +#define CQ_TM_BAR_ADDR PPC_BITMASK(8, 49) + +/* ESB Base Address Register */ +#define X_CQ_ESB_BAR 0x0A +#define CQ_ESB_BAR 0x050 +#define CQ_BAR_VALID PPC_BIT(0) +#define CQ_BAR_64K PPC_BIT(1) +/* 2:7 reserved */ +#define CQ_BAR_ADDR PPC_BITMASK(8, 39) +#define CQ_BAR_SET_DIV PPC_BITMASK(56, 58) +#define CQ_BAR_RANGE PPC_BITMASK(59, 63) + /* 0 (16M) - 16 (16T) */ + +/* END Base Address Register */ +#define X_CQ_END_BAR 0x0B +#define CQ_END_BAR 0x058 + +/* NVPG Base Address Register */ +#define X_CQ_NVPG_BAR 0x0C +#define CQ_NVPG_BAR 0x060 + +/* NVC Base Address Register */ +#define X_CQ_NVC_BAR 0x0D +#define CQ_NVC_BAR 0x068 + +/* Table Address Register */ +#define X_CQ_TAR 0x0E +#define CQ_TAR 0x070 +#define CQ_TAR_AUTOINC PPC_BIT(0) +#define CQ_TAR_SELECT PPC_BITMASK(12, 15) +#define CQ_TAR_ESB 0 /* 0 - 15 */ +#define CQ_TAR_END 2 /* 0 - 15 */ +#define CQ_TAR_NVPG 3 /* 0 - 15 */ +#define CQ_TAR_NVC 5 /* 0 - 15 */ +#define CQ_TAR_ENTRY_SELECT PPC_BITMASK(28, 31) + +/* Table Data Register */ +#define X_CQ_TDR 0x0F +#define CQ_TDR 0x078 +/* for the NVPG, NVC, ESB, END Set Translation Tables */ +#define CQ_TDR_VALID PPC_BIT(0) +#define CQ_TDR_BLOCK_ID PPC_BITMASK(60, 63) + +/* + * Processor Cores Enabled for MsgSnd + * Identifies which of the 32 possible core chiplets are enabled and + * available to receive the MsgSnd command + */ +#define X_CQ_MSGSND 0x10 +#define CQ_MSGSND 0x080 + +/* Interrupt Unit Reset Control */ +#define X_CQ_RST_CTL 0x12 +#define CQ_RST_CTL 0x090 +#define CQ_RST_SYNC_RESET PPC_BIT(0) /* Write Only */ +#define CQ_RST_QUIESCE_PB PPC_BIT(1) /* RW */ +#define CQ_RST_MASTER_IDLE PPC_BIT(2) /* Read Only */ +#define CQ_RST_SAVE_IDLE PPC_BIT(3) /* Read Only */ +#define CQ_RST_PB_BAR_RESET PPC_BIT(4) /* Write Only */ + +/* PowerBus General Configuration */ +#define X_CQ_CFG_PB_GEN 0x14 +#define CQ_CFG_PB_GEN 0x0A0 +#define CQ_CFG_PB_GEN_PB_INIT PPC_BIT(45) + +/* + * FIR + * (And-Mask) + * (Or-Mask) + */ +#define X_CQ_FIR 0x30 +#define X_CQ_FIR_AND 0x31 +#define X_CQ_FIR_OR 0x32 +#define CQ_FIR 0x180 +#define CQ_FIR_AND 0x188 +#define CQ_FIR_OR 0x190 +#define CQ_FIR_PB_RCMDX_CI_ERR1 PPC_BIT(19) +#define CQ_FIR_VC_INFO_ERROR_0_2 PPC_BITMASK(61, 63) + +/* + * FIR Mask + * (And-Mask) + * (Or-Mask) + */ +#define X_CQ_FIRMASK 0x33 +#define X_CQ_FIRMASK_AND 0x34 +#define X_CQ_FIRMASK_OR 0x35 +#define CQ_FIRMASK 0x198 +#define CQ_FIRMASK_AND 0x1A0 +#define CQ_FIRMASK_OR 0x1A8 + +/* + * VC0 + */ + +/* VSD table address */ +#define X_VC_VSD_TABLE_ADDR 0x100 +#define VC_VSD_TABLE_ADDR 0x000 +#define VC_VSD_TABLE_AUTOINC PPC_BIT(0) +#define VC_VSD_TABLE_SELECT PPC_BITMASK(12, 15) +#define VC_VSD_TABLE_ADDRESS PPC_BITMASK(28, 31) + +/* VSD table data */ +#define X_VC_VSD_TABLE_DATA 0x101 +#define VC_VSD_TABLE_DATA 0x008 + +/* AIB AT macro indirect kill */ +#define X_VC_AT_MACRO_KILL 0x102 +#define VC_AT_MACRO_KILL 0x010 +#define VC_AT_MACRO_KILL_VALID PPC_BIT(0) +#define VC_AT_MACRO_KILL_VSD PPC_BITMASK(12, 15) +#define VC_AT_MACRO_KILL_BLOCK_ID PPC_BITMASK(28, 31) +#define VC_AT_MACRO_KILL_OFFSET PPC_BITMASK(48, 60) + +/* AIB AT macro indirect kill mask (same bit definitions) */ +#define X_VC_AT_MACRO_KILL_MASK 0x103 +#define VC_AT_MACRO_KILL_MASK 0x018 + +/* Remote IRQs and ERQs configuration [n] (n = 0:6) */ +#define X_VC_QUEUES_CFG_REM0 0x117 + +#define VC_QUEUES_CFG_REM0 0x0B8 +#define VC_QUEUES_CFG_REM1 0x0C0 +#define VC_QUEUES_CFG_REM2 0x0C8 +#define VC_QUEUES_CFG_REM3 0x0D0 +#define VC_QUEUES_CFG_REM4 0x0D8 +#define VC_QUEUES_CFG_REM5 0x0E0 +#define VC_QUEUES_CFG_REM6 0x0E8 +#define VC_QUEUES_CFG_MEMB_EN PPC_BIT(38) +#define VC_QUEUES_CFG_MEMB_SZ PPC_BITMASK(42, 47) + +/* + * VC1 + */ + +/* ESBC cache flush control trigger */ +#define X_VC_ESBC_FLUSH_CTRL 0x140 +#define VC_ESBC_FLUSH_CTRL 0x200 +#define VC_ESBC_FLUSH_CTRL_POLL_VALID PPC_BIT(0) +#define VC_ESBC_FLUSH_CTRL_WANT_CACHE_DISABLE PPC_BIT(2) + +/* ESBC cache flush poll trigger */ +#define X_VC_ESBC_FLUSH_POLL 0x141 +#define VC_ESBC_FLUSH_POLL 0x208 +#define VC_ESBC_FLUSH_POLL_BLOCK_ID PPC_BITMASK(0, 3) +#define VC_ESBC_FLUSH_POLL_OFFSET PPC_BITMASK(4, 31) /* 28-bit */ +#define VC_ESBC_FLUSH_POLL_BLOCK_ID_MASK PPC_BITMASK(32, 35) +#define VC_ESBC_FLUSH_POLL_OFFSET_MASK PPC_BITMASK(36, 63) /* 28-bit */ + +/* EASC flush control register */ +#define X_VC_EASC_FLUSH_CTRL 0x160 +#define VC_EASC_FLUSH_CTRL 0x300 +#define VC_EASC_FLUSH_CTRL_POLL_VALID PPC_BIT(0) +#define VC_EASC_FLUSH_CTRL_WANT_CACHE_DISABLE PPC_BIT(2) + +/* EASC flush poll register */ +#define X_VC_EASC_FLUSH_POLL 0x161 +#define VC_EASC_FLUSH_POLL 0x308 +#define VC_EASC_FLUSH_POLL_BLOCK_ID PPC_BITMASK(0, 3) +#define VC_EASC_FLUSH_POLL_OFFSET PPC_BITMASK(4, 31) /* 28-bit */ +#define VC_EASC_FLUSH_POLL_BLOCK_ID_MASK PPC_BITMASK(32, 35) +#define VC_EASC_FLUSH_POLL_OFFSET_MASK PPC_BITMASK(36, 63) /* 28-bit */ + +/* + * VC2 + */ + +/* ENDC flush control register */ +#define X_VC_ENDC_FLUSH_CTRL 0x180 +#define VC_ENDC_FLUSH_CTRL 0x400 +#define VC_ENDC_FLUSH_CTRL_POLL_VALID PPC_BIT(0) +#define VC_ENDC_FLUSH_CTRL_WANT_CACHE_DISABLE PPC_BIT(2) +#define VC_ENDC_FLUSH_CTRL_WANT_INVALIDATE PPC_BIT(3) +#define VC_ENDC_FLUSH_CTRL_INJECT_INVALIDATE PPC_BIT(7) + +/* ENDC flush poll register */ +#define X_VC_ENDC_FLUSH_POLL 0x181 +#define VC_ENDC_FLUSH_POLL 0x408 +#define VC_ENDC_FLUSH_POLL_BLOCK_ID PPC_BITMASK(4, 7) +#define VC_ENDC_FLUSH_POLL_OFFSET PPC_BITMASK(8, 31) /* 24-bit */ +#define VC_ENDC_FLUSH_POLL_BLOCK_ID_MASK PPC_BITMASK(36, 39) +#define VC_ENDC_FLUSH_POLL_OFFSET_MASK PPC_BITMASK(40, 63) /* 24-bit */ + +/* ENDC Sync done */ +#define X_VC_ENDC_SYNC_DONE 0x184 +#define VC_ENDC_SYNC_DONE 0x420 +#define VC_ENDC_SYNC_POLL_DONE PPC_BITMASK(0, 6) +#define VC_ENDC_SYNC_QUEUE_IPI PPC_BIT(0) +#define VC_ENDC_SYNC_QUEUE_HWD PPC_BIT(1) +#define VC_ENDC_SYNC_QUEUE_NXC PPC_BIT(2) +#define VC_ENDC_SYNC_QUEUE_INT PPC_BIT(3) +#define VC_ENDC_SYNC_QUEUE_OS PPC_BIT(4) +#define VC_ENDC_SYNC_QUEUE_POOL PPC_BIT(5) +#define VC_ENDC_SYNC_QUEUE_HARD PPC_BIT(6) +#define VC_QUEUE_COUNT 7 + +/* ENDC cache watch specification 0 */ +#define X_VC_ENDC_WATCH0_SPEC 0x1A0 +#define VC_ENDC_WATCH0_SPEC 0x500 +#define VC_ENDC_WATCH_CONFLICT PPC_BIT(0) +#define VC_ENDC_WATCH_FULL PPC_BIT(8) +#define VC_ENDC_WATCH_BLOCK_ID PPC_BITMASK(28, 31) +#define VC_ENDC_WATCH_INDEX PPC_BITMASK(40, 63) + +/* ENDC cache watch data 0 */ +#define X_VC_ENDC_WATCH0_DATA0 0x1A4 +#define X_VC_ENDC_WATCH0_DATA1 0x1A5 +#define X_VC_ENDC_WATCH0_DATA2 0x1A6 +#define X_VC_ENDC_WATCH0_DATA3 0x1A7 + +#define VC_ENDC_WATCH0_DATA0 0x520 +#define VC_ENDC_WATCH0_DATA1 0x528 +#define VC_ENDC_WATCH0_DATA2 0x530 +#define VC_ENDC_WATCH0_DATA3 0x538 + +/* + * PC LSB1 + */ + +/* VSD table address register */ +#define X_PC_VSD_TABLE_ADDR 0x200 +#define PC_VSD_TABLE_ADDR 0x000 +#define PC_VSD_TABLE_AUTOINC PPC_BIT(0) +#define PC_VSD_TABLE_SELECT PPC_BITMASK(12, 15) +#define PC_VSD_TABLE_ADDRESS PPC_BITMASK(28, 31) + +/* VSD table data register */ +#define X_PC_VSD_TABLE_DATA 0x201 +#define PC_VSD_TABLE_DATA 0x008 + +/* AT indirect kill register */ +#define X_PC_AT_KILL 0x202 +#define PC_AT_KILL 0x010 +#define PC_AT_KILL_VALID PPC_BIT(0) +#define PC_AT_KILL_VSD_TYPE PPC_BITMASK(24, 27) +/* Only NVP, NVG, NVC */ +#define PC_AT_KILL_BLOCK_ID PPC_BITMASK(28, 31) +#define PC_AT_KILL_OFFSET PPC_BITMASK(48, 60) + +/* AT indirect kill mask register */ +#define X_PC_AT_KILL_MASK 0x203 +#define PC_AT_KILL_MASK 0x018 +#define PC_AT_KILL_MASK_VSD_TYPE PPC_BITMASK(24, 27) +#define PC_AT_KILL_MASK_BLOCK_ID PPC_BITMASK(28, 31) +#define PC_AT_KILL_MASK_OFFSET PPC_BITMASK(48, 60) + +/* + * PC LSB2 + */ + +/* NxC Cache flush control */ +#define X_PC_NXC_FLUSH_CTRL 0x280 +#define PC_NXC_FLUSH_CTRL 0x400 +#define PC_NXC_FLUSH_CTRL_POLL_VALID PPC_BIT(0) +#define PC_NXC_FLUSH_CTRL_WANT_CACHE_DISABLE PPC_BIT(2) +#define PC_NXC_FLUSH_CTRL_WANT_INVALIDATE PPC_BIT(3) +#define PC_NXC_FLUSH_CTRL_INJECT_INVALIDATE PPC_BIT(7) + +/* NxC Cache flush poll */ +#define X_PC_NXC_FLUSH_POLL 0x281 +#define PC_NXC_FLUSH_POLL 0x408 +#define PC_NXC_FLUSH_POLL_NXC_TYPE PPC_BITMASK(2, 3) +#define PC_NXC_FLUSH_POLL_NXC_TYPE_NVP 0 +#define PC_NXC_FLUSH_POLL_NXC_TYPE_NVG 2 +#define PC_NXC_FLUSH_POLL_NXC_TYPE_NVC 3 +#define PC_NXC_FLUSH_POLL_BLOCK_ID PPC_BITMASK(4, 7) +#define PC_NXC_FLUSH_POLL_OFFSET PPC_BITMASK(8, 31) /* 24-bit */ +#define PC_NXC_FLUSH_POLL_NXC_TYPE_MASK PPC_BITMASK(34, 35) /* 0: Ign */ +#define PC_NXC_FLUSH_POLL_BLOCK_ID_MASK PPC_BITMASK(36, 39) +#define PC_NXC_FLUSH_POLL_OFFSET_MASK PPC_BITMASK(40, 63) /* 24-bit */ + +/* NxC Cache Watch 0 Specification */ +#define X_PC_NXC_WATCH0_SPEC 0x2A0 +#define PC_NXC_WATCH0_SPEC 0x500 +#define PC_NXC_WATCH_CONFLICT PPC_BIT(0) +#define PC_NXC_WATCH_FULL PPC_BIT(8) +#define PC_NXC_WATCH_NXC_TYPE PPC_BITMASK(26, 27) +#define PC_NXC_WATCH_NXC_NVP 0 +#define PC_NXC_WATCH_NXC_NVG 2 +#define PC_NXC_WATCH_NXC_NVC 3 +#define PC_NXC_WATCH_BLOCK_ID PPC_BITMASK(28, 31) +#define PC_NXC_WATCH_INDEX PPC_BITMASK(40, 63) + +/* NxC Cache Watch 0 Data */ +#define X_PC_NXC_WATCH0_DATA0 0x2A4 +#define X_PC_NXC_WATCH0_DATA1 0x2A5 +#define X_PC_NXC_WATCH0_DATA2 0x2A6 +#define X_PC_NXC_WATCH0_DATA3 0x2A7 + +#define PC_NXC_WATCH0_DATA0 0x520 +#define PC_NXC_WATCH0_DATA1 0x528 +#define PC_NXC_WATCH0_DATA2 0x530 +#define PC_NXC_WATCH0_DATA3 0x538 + +/* + * TCTXT Registers + */ + +/* Physical Thread Enable0 register */ +#define X_TCTXT_EN0 0x300 +#define TCTXT_EN0 0x000 + +/* Physical Thread Enable0 Set register */ +#define X_TCTXT_EN0_SET 0x302 +#define TCTXT_EN0_SET 0x010 + +/* Physical Thread Enable0 Reset register */ +#define X_TCTXT_EN0_RESET 0x303 +#define TCTXT_EN0_RESET 0x018 + +/* Physical Thread Enable1 register */ +#define X_TCTXT_EN1 0x304 +#define TCTXT_EN1 0x020 + +/* Physical Thread Enable1 Set register */ +#define X_TCTXT_EN1_SET 0x306 +#define TCTXT_EN1_SET 0x030 + +/* Physical Thread Enable1 Reset register */ +#define X_TCTXT_EN1_RESET 0x307 +#define TCTXT_EN1_RESET 0x038 + +/* + * VSD Tables + */ +#define VST_ESB 0 +#define VST_EAS 1 /* No used by PC */ +#define VST_END 2 +#define VST_NVP 3 +#define VST_NVG 4 +#define VST_NVC 5 +#define VST_IC 6 /* No used by PC */ +#define VST_SYNC 7 +#define VST_ERQ 8 /* No used by PC */ + +/* + * Bits in a VSD entry. + * + * Note: the address is naturally aligned, we don't use a PPC_BITMASK, + * but just a mask to apply to the address before OR'ing it in. + * + * Note: VSD_FIRMWARE is a SW bit ! It hijacks an unused bit in the + * VSD and is only meant to be used in indirect mode ! + */ +#define VSD_MODE PPC_BITMASK(0, 1) +#define VSD_MODE_SHARED 1 +#define VSD_MODE_EXCLUSIVE 2 +#define VSD_MODE_FORWARD 3 +#define VSD_FIRMWARE PPC_BIT(2) /* Read warning */ +#define VSD_FIRMWARE2 PPC_BIT(3) /* unused */ +#define VSD_RESERVED PPC_BITMASK(4, 7) /* P10 reserved */ +#define VSD_ADDRESS_MASK 0x00fffffffffff000ull +#define VSD_MIGRATION_REG PPC_BITMASK(52, 55) +#define VSD_INDIRECT PPC_BIT(56) +#define VSD_TSIZE PPC_BITMASK(59, 63) + +#endif /* PPC_PNV_XIVE2_REGS_H */ diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c index eae95c716f..dc641cc604 100644 --- a/hw/intc/spapr_xive.c +++ b/hw/intc/spapr_xive.c @@ -480,6 +480,29 @@ static uint8_t spapr_xive_get_block_id(XiveRouter *xrtr) return SPAPR_XIVE_BLOCK_ID; } +static int spapr_xive_get_pq(XiveRouter *xrtr, uint8_t blk, uint32_t idx, + uint8_t *pq) +{ + SpaprXive *xive = SPAPR_XIVE(xrtr); + + assert(SPAPR_XIVE_BLOCK_ID == blk); + + *pq = xive_source_esb_get(&xive->source, idx); + return 0; +} + +static int spapr_xive_set_pq(XiveRouter *xrtr, uint8_t blk, uint32_t idx, + uint8_t *pq) +{ + SpaprXive *xive = SPAPR_XIVE(xrtr); + + assert(SPAPR_XIVE_BLOCK_ID == blk); + + *pq = xive_source_esb_set(&xive->source, idx, *pq); + return 0; +} + + static const VMStateDescription vmstate_spapr_xive_end = { .name = TYPE_SPAPR_XIVE "/end", .version_id = 1, @@ -788,6 +811,8 @@ static void spapr_xive_class_init(ObjectClass *klass, void *data) dc->vmsd = &vmstate_spapr_xive; xrc->get_eas = spapr_xive_get_eas; + xrc->get_pq = spapr_xive_get_pq; + xrc->set_pq = spapr_xive_set_pq; xrc->get_end = spapr_xive_get_end; xrc->write_end = spapr_xive_write_end; xrc->get_nvt = spapr_xive_get_nvt; diff --git a/hw/intc/xive.c b/hw/intc/xive.c index f15f98588a..b8e4c7294d 100644 --- a/hw/intc/xive.c +++ b/hw/intc/xive.c @@ -887,6 +887,16 @@ static bool xive_source_lsi_trigger(XiveSource *xsrc, uint32_t srcno) } /* + * Sources can be configured with PQ offloading in which case the check + * on the PQ state bits of MSIs is disabled + */ +static bool xive_source_esb_disabled(XiveSource *xsrc, uint32_t srcno) +{ + return (xsrc->esb_flags & XIVE_SRC_PQ_DISABLE) && + !xive_source_irq_is_lsi(xsrc, srcno); +} + +/* * Returns whether the event notification should be forwarded. */ static bool xive_source_esb_trigger(XiveSource *xsrc, uint32_t srcno) @@ -895,6 +905,10 @@ static bool xive_source_esb_trigger(XiveSource *xsrc, uint32_t srcno) assert(srcno < xsrc->nr_irqs); + if (xive_source_esb_disabled(xsrc, srcno)) { + return true; + } + ret = xive_esb_trigger(&xsrc->status[srcno]); if (xive_source_irq_is_lsi(xsrc, srcno) && @@ -915,6 +929,11 @@ static bool xive_source_esb_eoi(XiveSource *xsrc, uint32_t srcno) assert(srcno < xsrc->nr_irqs); + if (xive_source_esb_disabled(xsrc, srcno)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid EOI for IRQ %d\n", srcno); + return false; + } + ret = xive_esb_eoi(&xsrc->status[srcno]); /* @@ -936,9 +955,10 @@ static bool xive_source_esb_eoi(XiveSource *xsrc, uint32_t srcno) static void xive_source_notify(XiveSource *xsrc, int srcno) { XiveNotifierClass *xnc = XIVE_NOTIFIER_GET_CLASS(xsrc->xive); + bool pq_checked = !xive_source_esb_disabled(xsrc, srcno); if (xnc->notify) { - xnc->notify(xsrc->xive, srcno); + xnc->notify(xsrc->xive, srcno, pq_checked); } } @@ -1061,6 +1081,15 @@ static void xive_source_esb_write(void *opaque, hwaddr addr, notify = xive_source_esb_eoi(xsrc, srcno); break; + /* + * This is an internal offset used to inject triggers when the PQ + * state bits are not controlled locally. Such as for LSIs when + * under ABT mode. + */ + case XIVE_ESB_INJECT ... XIVE_ESB_INJECT + 0x3FF: + notify = true; + break; + case XIVE_ESB_SET_PQ_00 ... XIVE_ESB_SET_PQ_00 + 0x0FF: case XIVE_ESB_SET_PQ_01 ... XIVE_ESB_SET_PQ_01 + 0x0FF: case XIVE_ESB_SET_PQ_10 ... XIVE_ESB_SET_PQ_10 + 0x0FF: @@ -1361,6 +1390,24 @@ int xive_router_get_eas(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx, return xrc->get_eas(xrtr, eas_blk, eas_idx, eas); } +static +int xive_router_get_pq(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq) +{ + XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr); + + return xrc->get_pq(xrtr, eas_blk, eas_idx, pq); +} + +static +int xive_router_set_pq(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq) +{ + XiveRouterClass *xrc = XIVE_ROUTER_GET_CLASS(xrtr); + + return xrc->set_pq(xrtr, eas_blk, eas_idx, pq); +} + int xive_router_get_end(XiveRouter *xrtr, uint8_t end_blk, uint32_t end_idx, XiveEND *end) { @@ -1712,7 +1759,7 @@ do_escalation: xive_get_field32(END_W5_ESC_END_DATA, end.w5)); } -void xive_router_notify(XiveNotifier *xn, uint32_t lisn) +void xive_router_notify(XiveNotifier *xn, uint32_t lisn, bool pq_checked) { XiveRouter *xrtr = XIVE_ROUTER(xn); uint8_t eas_blk = XIVE_EAS_BLOCK(lisn); @@ -1725,11 +1772,27 @@ void xive_router_notify(XiveNotifier *xn, uint32_t lisn) return; } - /* - * The IVRE checks the State Bit Cache at this point. We skip the - * SBC lookup because the state bits of the sources are modeled - * internally in QEMU. - */ + if (!pq_checked) { + bool notify; + uint8_t pq; + + /* PQ cache lookup */ + if (xive_router_get_pq(xrtr, eas_blk, eas_idx, &pq)) { + /* Set FIR */ + g_assert_not_reached(); + } + + notify = xive_esb_trigger(&pq); + + if (xive_router_set_pq(xrtr, eas_blk, eas_idx, &pq)) { + /* Set FIR */ + g_assert_not_reached(); + } + + if (!notify) { + return; + } + } if (!xive_eas_is_valid(&eas)) { qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid LISN %x\n", lisn); diff --git a/hw/intc/xive2.c b/hw/intc/xive2.c new file mode 100644 index 0000000000..b6452f1478 --- /dev/null +++ b/hw/intc/xive2.c @@ -0,0 +1,1018 @@ +/* + * QEMU PowerPC XIVE2 interrupt controller model (POWER10) + * + * Copyright (c) 2019-2022, IBM Corporation.. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qapi/error.h" +#include "target/ppc/cpu.h" +#include "sysemu/cpus.h" +#include "sysemu/dma.h" +#include "hw/qdev-properties.h" +#include "monitor/monitor.h" +#include "hw/ppc/xive.h" +#include "hw/ppc/xive2.h" +#include "hw/ppc/xive2_regs.h" + +uint32_t xive2_router_get_config(Xive2Router *xrtr) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_config(xrtr); +} + +void xive2_eas_pic_print_info(Xive2Eas *eas, uint32_t lisn, Monitor *mon) +{ + if (!xive2_eas_is_valid(eas)) { + return; + } + + monitor_printf(mon, " %08x %s end:%02x/%04x data:%08x\n", + lisn, xive2_eas_is_masked(eas) ? "M" : " ", + (uint8_t) xive_get_field64(EAS2_END_BLOCK, eas->w), + (uint32_t) xive_get_field64(EAS2_END_INDEX, eas->w), + (uint32_t) xive_get_field64(EAS2_END_DATA, eas->w)); +} + +void xive2_end_queue_pic_print_info(Xive2End *end, uint32_t width, + Monitor *mon) +{ + uint64_t qaddr_base = xive2_end_qaddr(end); + uint32_t qsize = xive_get_field32(END2_W3_QSIZE, end->w3); + uint32_t qindex = xive_get_field32(END2_W1_PAGE_OFF, end->w1); + uint32_t qentries = 1 << (qsize + 10); + int i; + + /* + * print out the [ (qindex - (width - 1)) .. (qindex + 1)] window + */ + monitor_printf(mon, " [ "); + qindex = (qindex - (width - 1)) & (qentries - 1); + for (i = 0; i < width; i++) { + uint64_t qaddr = qaddr_base + (qindex << 2); + uint32_t qdata = -1; + + if (dma_memory_read(&address_space_memory, qaddr, &qdata, + sizeof(qdata), MEMTXATTRS_UNSPECIFIED)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: failed to read EQ @0x%" + HWADDR_PRIx "\n", qaddr); + return; + } + monitor_printf(mon, "%s%08x ", i == width - 1 ? "^" : "", + be32_to_cpu(qdata)); + qindex = (qindex + 1) & (qentries - 1); + } + monitor_printf(mon, "]"); +} + +void xive2_end_pic_print_info(Xive2End *end, uint32_t end_idx, Monitor *mon) +{ + uint64_t qaddr_base = xive2_end_qaddr(end); + uint32_t qindex = xive_get_field32(END2_W1_PAGE_OFF, end->w1); + uint32_t qgen = xive_get_field32(END2_W1_GENERATION, end->w1); + uint32_t qsize = xive_get_field32(END2_W3_QSIZE, end->w3); + uint32_t qentries = 1 << (qsize + 10); + + uint32_t nvp_blk = xive_get_field32(END2_W6_VP_BLOCK, end->w6); + uint32_t nvp_idx = xive_get_field32(END2_W6_VP_OFFSET, end->w6); + uint8_t priority = xive_get_field32(END2_W7_F0_PRIORITY, end->w7); + uint8_t pq; + + if (!xive2_end_is_valid(end)) { + return; + } + + pq = xive_get_field32(END2_W1_ESn, end->w1); + + monitor_printf(mon, + " %08x %c%c %c%c%c%c%c%c%c%c%c%c prio:%d nvp:%02x/%04x", + end_idx, + pq & XIVE_ESB_VAL_P ? 'P' : '-', + pq & XIVE_ESB_VAL_Q ? 'Q' : '-', + xive2_end_is_valid(end) ? 'v' : '-', + xive2_end_is_enqueue(end) ? 'q' : '-', + xive2_end_is_notify(end) ? 'n' : '-', + xive2_end_is_backlog(end) ? 'b' : '-', + xive2_end_is_escalate(end) ? 'e' : '-', + xive2_end_is_escalate_end(end) ? 'N' : '-', + xive2_end_is_uncond_escalation(end) ? 'u' : '-', + xive2_end_is_silent_escalation(end) ? 's' : '-', + xive2_end_is_firmware1(end) ? 'f' : '-', + xive2_end_is_firmware2(end) ? 'F' : '-', + priority, nvp_blk, nvp_idx); + + if (qaddr_base) { + monitor_printf(mon, " eq:@%08"PRIx64"% 6d/%5d ^%d", + qaddr_base, qindex, qentries, qgen); + xive2_end_queue_pic_print_info(end, 6, mon); + } + monitor_printf(mon, "\n"); +} + +void xive2_end_eas_pic_print_info(Xive2End *end, uint32_t end_idx, + Monitor *mon) +{ + Xive2Eas *eas = (Xive2Eas *) &end->w4; + uint8_t pq; + + if (!xive2_end_is_escalate(end)) { + return; + } + + pq = xive_get_field32(END2_W1_ESe, end->w1); + + monitor_printf(mon, " %08x %c%c %c%c end:%02x/%04x data:%08x\n", + end_idx, + pq & XIVE_ESB_VAL_P ? 'P' : '-', + pq & XIVE_ESB_VAL_Q ? 'Q' : '-', + xive2_eas_is_valid(eas) ? 'v' : ' ', + xive2_eas_is_masked(eas) ? 'M' : ' ', + (uint8_t) xive_get_field64(EAS2_END_BLOCK, eas->w), + (uint32_t) xive_get_field64(EAS2_END_INDEX, eas->w), + (uint32_t) xive_get_field64(EAS2_END_DATA, eas->w)); +} + +static void xive2_end_enqueue(Xive2End *end, uint32_t data) +{ + uint64_t qaddr_base = xive2_end_qaddr(end); + uint32_t qsize = xive_get_field32(END2_W3_QSIZE, end->w3); + uint32_t qindex = xive_get_field32(END2_W1_PAGE_OFF, end->w1); + uint32_t qgen = xive_get_field32(END2_W1_GENERATION, end->w1); + + uint64_t qaddr = qaddr_base + (qindex << 2); + uint32_t qdata = cpu_to_be32((qgen << 31) | (data & 0x7fffffff)); + uint32_t qentries = 1 << (qsize + 10); + + if (dma_memory_write(&address_space_memory, qaddr, &qdata, sizeof(qdata), + MEMTXATTRS_UNSPECIFIED)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: failed to write END data @0x%" + HWADDR_PRIx "\n", qaddr); + return; + } + + qindex = (qindex + 1) & (qentries - 1); + if (qindex == 0) { + qgen ^= 1; + end->w1 = xive_set_field32(END2_W1_GENERATION, end->w1, qgen); + + /* TODO(PowerNV): reset GF bit on a cache watch operation */ + end->w1 = xive_set_field32(END2_W1_GEN_FLIPPED, end->w1, qgen); + } + end->w1 = xive_set_field32(END2_W1_PAGE_OFF, end->w1, qindex); +} + +/* + * XIVE Thread Interrupt Management Area (TIMA) - Gen2 mode + * + * TIMA Gen2 VP “save & restore” (S&R) indicated by H bit next to V bit + * + * - if a context is enabled with the H bit set, the VP context + * information is retrieved from the NVP structure (“check out”) + * and stored back on a context pull (“check in”), the SW receives + * the same context pull information as on P9 + * + * - the H bit cannot be changed while the V bit is set, i.e. a + * context cannot be set up in the TIMA and then be “pushed” into + * the NVP by changing the H bit while the context is enabled + */ + +static void xive2_tctx_save_os_ctx(Xive2Router *xrtr, XiveTCTX *tctx, + uint8_t nvp_blk, uint32_t nvp_idx) +{ + CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env; + uint32_t pir = env->spr_cb[SPR_PIR].default_value; + Xive2Nvp nvp; + uint8_t *regs = &tctx->regs[TM_QW1_OS]; + + if (xive2_router_get_nvp(xrtr, nvp_blk, nvp_idx, &nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + if (!xive2_nvp_is_valid(&nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + if (!xive2_nvp_is_hw(&nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: NVP %x/%x is not HW owned\n", + nvp_blk, nvp_idx); + return; + } + + if (!xive2_nvp_is_co(&nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: NVP %x/%x is not checkout\n", + nvp_blk, nvp_idx); + return; + } + + if (xive_get_field32(NVP2_W1_CO_THRID_VALID, nvp.w1) && + xive_get_field32(NVP2_W1_CO_THRID, nvp.w1) != pir) { + qemu_log_mask(LOG_GUEST_ERROR, + "XIVE: NVP %x/%x invalid checkout Thread %x\n", + nvp_blk, nvp_idx, pir); + return; + } + + nvp.w2 = xive_set_field32(NVP2_W2_IPB, nvp.w2, regs[TM_IPB]); + nvp.w2 = xive_set_field32(NVP2_W2_CPPR, nvp.w2, regs[TM_CPPR]); + nvp.w2 = xive_set_field32(NVP2_W2_LSMFB, nvp.w2, regs[TM_LSMFB]); + xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, &nvp, 2); + + nvp.w1 = xive_set_field32(NVP2_W1_CO, nvp.w1, 0); + /* NVP2_W1_CO_THRID_VALID only set once */ + nvp.w1 = xive_set_field32(NVP2_W1_CO_THRID, nvp.w1, 0xFFFF); + xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, &nvp, 1); +} + +static void xive2_os_cam_decode(uint32_t cam, uint8_t *nvp_blk, + uint32_t *nvp_idx, bool *vo, bool *ho) +{ + *nvp_blk = xive2_nvp_blk(cam); + *nvp_idx = xive2_nvp_idx(cam); + *vo = !!(cam & TM2_QW1W2_VO); + *ho = !!(cam & TM2_QW1W2_HO); +} + +uint64_t xive2_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size) +{ + Xive2Router *xrtr = XIVE2_ROUTER(xptr); + uint32_t qw1w2 = xive_tctx_word2(&tctx->regs[TM_QW1_OS]); + uint32_t qw1w2_new; + uint32_t cam = be32_to_cpu(qw1w2); + uint8_t nvp_blk; + uint32_t nvp_idx; + bool vo; + bool do_save; + + xive2_os_cam_decode(cam, &nvp_blk, &nvp_idx, &vo, &do_save); + + if (!vo) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: pulling invalid NVP %x/%x !?\n", + nvp_blk, nvp_idx); + } + + /* Invalidate CAM line */ + qw1w2_new = xive_set_field32(TM2_QW1W2_VO, qw1w2, 0); + memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1w2_new, 4); + + if (xive2_router_get_config(xrtr) & XIVE2_VP_SAVE_RESTORE && do_save) { + xive2_tctx_save_os_ctx(xrtr, tctx, nvp_blk, nvp_idx); + } + + return qw1w2; +} + +static uint8_t xive2_tctx_restore_os_ctx(Xive2Router *xrtr, XiveTCTX *tctx, + uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp) +{ + CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env; + uint32_t pir = env->spr_cb[SPR_PIR].default_value; + uint8_t cppr; + + if (!xive2_nvp_is_hw(nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: NVP %x/%x is not HW owned\n", + nvp_blk, nvp_idx); + return 0; + } + + cppr = xive_get_field32(NVP2_W2_CPPR, nvp->w2); + nvp->w2 = xive_set_field32(NVP2_W2_CPPR, nvp->w2, 0); + xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, nvp, 2); + + tctx->regs[TM_QW1_OS + TM_CPPR] = cppr; + /* we don't model LSMFB */ + + nvp->w1 = xive_set_field32(NVP2_W1_CO, nvp->w1, 1); + nvp->w1 = xive_set_field32(NVP2_W1_CO_THRID_VALID, nvp->w1, 1); + nvp->w1 = xive_set_field32(NVP2_W1_CO_THRID, nvp->w1, pir); + + /* + * Checkout privilege: 0:OS, 1:Pool, 2:Hard + * + * TODO: we only support OS push/pull + */ + nvp->w1 = xive_set_field32(NVP2_W1_CO_PRIV, nvp->w1, 0); + + xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, nvp, 1); + + /* return restored CPPR to generate a CPU exception if needed */ + return cppr; +} + +static void xive2_tctx_need_resend(Xive2Router *xrtr, XiveTCTX *tctx, + uint8_t nvp_blk, uint32_t nvp_idx, + bool do_restore) +{ + Xive2Nvp nvp; + uint8_t ipb; + uint8_t cppr = 0; + + /* + * Grab the associated thread interrupt context registers in the + * associated NVP + */ + if (xive2_router_get_nvp(xrtr, nvp_blk, nvp_idx, &nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + if (!xive2_nvp_is_valid(&nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + /* Automatically restore thread context registers */ + if (xive2_router_get_config(xrtr) & XIVE2_VP_SAVE_RESTORE && + do_restore) { + cppr = xive2_tctx_restore_os_ctx(xrtr, tctx, nvp_blk, nvp_idx, &nvp); + } + + ipb = xive_get_field32(NVP2_W2_IPB, nvp.w2); + if (ipb) { + nvp.w2 = xive_set_field32(NVP2_W2_IPB, nvp.w2, 0); + xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, &nvp, 2); + } + + /* An IPB or CPPR change can trigger a resend */ + if (ipb || cppr) { + xive_tctx_ipb_update(tctx, TM_QW1_OS, ipb); + } +} + +/* + * Updating the OS CAM line can trigger a resend of interrupt + */ +void xive2_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size) +{ + uint32_t cam = value; + uint32_t qw1w2 = cpu_to_be32(cam); + uint8_t nvp_blk; + uint32_t nvp_idx; + bool vo; + bool do_restore; + + xive2_os_cam_decode(cam, &nvp_blk, &nvp_idx, &vo, &do_restore); + + /* First update the thead context */ + memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1w2, 4); + + /* Check the interrupt pending bits */ + if (vo) { + xive2_tctx_need_resend(XIVE2_ROUTER(xptr), tctx, nvp_blk, nvp_idx, + do_restore); + } +} + +/* + * XIVE Router (aka. Virtualization Controller or IVRE) + */ + +int xive2_router_get_eas(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + Xive2Eas *eas) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_eas(xrtr, eas_blk, eas_idx, eas); +} + +static +int xive2_router_get_pq(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_pq(xrtr, eas_blk, eas_idx, pq); +} + +static +int xive2_router_set_pq(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->set_pq(xrtr, eas_blk, eas_idx, pq); +} + +int xive2_router_get_end(Xive2Router *xrtr, uint8_t end_blk, uint32_t end_idx, + Xive2End *end) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_end(xrtr, end_blk, end_idx, end); +} + +int xive2_router_write_end(Xive2Router *xrtr, uint8_t end_blk, uint32_t end_idx, + Xive2End *end, uint8_t word_number) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->write_end(xrtr, end_blk, end_idx, end, word_number); +} + +int xive2_router_get_nvp(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_nvp(xrtr, nvp_blk, nvp_idx, nvp); +} + +int xive2_router_write_nvp(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp, uint8_t word_number) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->write_nvp(xrtr, nvp_blk, nvp_idx, nvp, word_number); +} + +static int xive2_router_get_block_id(Xive2Router *xrtr) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_block_id(xrtr); +} + +/* + * Encode the HW CAM line with 7bit or 8bit thread id. The thread id + * width and block id width is configurable at the IC level. + * + * chipid << 24 | 0000 0000 0000 0000 1 threadid (7Bit) + * chipid << 24 | 0000 0000 0000 0001 threadid (8Bit) + */ +static uint32_t xive2_tctx_hw_cam_line(XivePresenter *xptr, XiveTCTX *tctx) +{ + Xive2Router *xrtr = XIVE2_ROUTER(xptr); + CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env; + uint32_t pir = env->spr_cb[SPR_PIR].default_value; + uint8_t blk = xive2_router_get_block_id(xrtr); + uint8_t tid_shift = + xive2_router_get_config(xrtr) & XIVE2_THREADID_8BITS ? 8 : 7; + uint8_t tid_mask = (1 << tid_shift) - 1; + + return xive2_nvp_cam_line(blk, 1 << tid_shift | (pir & tid_mask)); +} + +/* + * The thread context register words are in big-endian format. + */ +int xive2_presenter_tctx_match(XivePresenter *xptr, XiveTCTX *tctx, + uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool cam_ignore, uint32_t logic_serv) +{ + uint32_t cam = xive2_nvp_cam_line(nvt_blk, nvt_idx); + uint32_t qw3w2 = xive_tctx_word2(&tctx->regs[TM_QW3_HV_PHYS]); + uint32_t qw2w2 = xive_tctx_word2(&tctx->regs[TM_QW2_HV_POOL]); + uint32_t qw1w2 = xive_tctx_word2(&tctx->regs[TM_QW1_OS]); + uint32_t qw0w2 = xive_tctx_word2(&tctx->regs[TM_QW0_USER]); + + /* + * TODO (PowerNV): ignore mode. The low order bits of the NVT + * identifier are ignored in the "CAM" match. + */ + + if (format == 0) { + if (cam_ignore == true) { + /* + * F=0 & i=1: Logical server notification (bits ignored at + * the end of the NVT identifier) + */ + qemu_log_mask(LOG_UNIMP, "XIVE: no support for LS NVT %x/%x\n", + nvt_blk, nvt_idx); + return -1; + } + + /* F=0 & i=0: Specific NVT notification */ + + /* PHYS ring */ + if ((be32_to_cpu(qw3w2) & TM2_QW3W2_VT) && + cam == xive2_tctx_hw_cam_line(xptr, tctx)) { + return TM_QW3_HV_PHYS; + } + + /* HV POOL ring */ + if ((be32_to_cpu(qw2w2) & TM2_QW2W2_VP) && + cam == xive_get_field32(TM2_QW2W2_POOL_CAM, qw2w2)) { + return TM_QW2_HV_POOL; + } + + /* OS ring */ + if ((be32_to_cpu(qw1w2) & TM2_QW1W2_VO) && + cam == xive_get_field32(TM2_QW1W2_OS_CAM, qw1w2)) { + return TM_QW1_OS; + } + } else { + /* F=1 : User level Event-Based Branch (EBB) notification */ + + /* USER ring */ + if ((be32_to_cpu(qw1w2) & TM2_QW1W2_VO) && + (cam == xive_get_field32(TM2_QW1W2_OS_CAM, qw1w2)) && + (be32_to_cpu(qw0w2) & TM2_QW0W2_VU) && + (logic_serv == xive_get_field32(TM2_QW0W2_LOGIC_SERV, qw0w2))) { + return TM_QW0_USER; + } + } + return -1; +} + +static void xive2_router_realize(DeviceState *dev, Error **errp) +{ + Xive2Router *xrtr = XIVE2_ROUTER(dev); + + assert(xrtr->xfb); +} + +/* + * Notification using the END ESe/ESn bit (Event State Buffer for + * escalation and notification). Profide futher coalescing in the + * Router. + */ +static bool xive2_router_end_es_notify(Xive2Router *xrtr, uint8_t end_blk, + uint32_t end_idx, Xive2End *end, + uint32_t end_esmask) +{ + uint8_t pq = xive_get_field32(end_esmask, end->w1); + bool notify = xive_esb_trigger(&pq); + + if (pq != xive_get_field32(end_esmask, end->w1)) { + end->w1 = xive_set_field32(end_esmask, end->w1, pq); + xive2_router_write_end(xrtr, end_blk, end_idx, end, 1); + } + + /* ESe/n[Q]=1 : end of notification */ + return notify; +} + +/* + * An END trigger can come from an event trigger (IPI or HW) or from + * another chip. We don't model the PowerBus but the END trigger + * message has the same parameters than in the function below. + */ +static void xive2_router_end_notify(Xive2Router *xrtr, uint8_t end_blk, + uint32_t end_idx, uint32_t end_data) +{ + Xive2End end; + uint8_t priority; + uint8_t format; + bool found; + Xive2Nvp nvp; + uint8_t nvp_blk; + uint32_t nvp_idx; + + /* END cache lookup */ + if (xive2_router_get_end(xrtr, end_blk, end_idx, &end)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No END %x/%x\n", end_blk, + end_idx); + return; + } + + if (!xive2_end_is_valid(&end)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: END %x/%x is invalid\n", + end_blk, end_idx); + return; + } + + if (xive2_end_is_enqueue(&end)) { + xive2_end_enqueue(&end, end_data); + /* Enqueuing event data modifies the EQ toggle and index */ + xive2_router_write_end(xrtr, end_blk, end_idx, &end, 1); + } + + /* + * When the END is silent, we skip the notification part. + */ + if (xive2_end_is_silent_escalation(&end)) { + goto do_escalation; + } + + /* + * The W7 format depends on the F bit in W6. It defines the type + * of the notification : + * + * F=0 : single or multiple NVP notification + * F=1 : User level Event-Based Branch (EBB) notification, no + * priority + */ + format = xive_get_field32(END2_W6_FORMAT_BIT, end.w6); + priority = xive_get_field32(END2_W7_F0_PRIORITY, end.w7); + + /* The END is masked */ + if (format == 0 && priority == 0xff) { + return; + } + + /* + * Check the END ESn (Event State Buffer for notification) for + * even futher coalescing in the Router + */ + if (!xive2_end_is_notify(&end)) { + /* ESn[Q]=1 : end of notification */ + if (!xive2_router_end_es_notify(xrtr, end_blk, end_idx, + &end, END2_W1_ESn)) { + return; + } + } + + /* + * Follows IVPE notification + */ + nvp_blk = xive_get_field32(END2_W6_VP_BLOCK, end.w6); + nvp_idx = xive_get_field32(END2_W6_VP_OFFSET, end.w6); + + /* NVP cache lookup */ + if (xive2_router_get_nvp(xrtr, nvp_blk, nvp_idx, &nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: no NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + if (!xive2_nvp_is_valid(&nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: NVP %x/%x is invalid\n", + nvp_blk, nvp_idx); + return; + } + + found = xive_presenter_notify(xrtr->xfb, format, nvp_blk, nvp_idx, + xive_get_field32(END2_W6_IGNORE, end.w7), + priority, + xive_get_field32(END2_W7_F1_LOG_SERVER_ID, end.w7)); + + /* TODO: Auto EOI. */ + + if (found) { + return; + } + + /* + * If no matching NVP is dispatched on a HW thread : + * - specific VP: update the NVP structure if backlog is activated + * - logical server : forward request to IVPE (not supported) + */ + if (xive2_end_is_backlog(&end)) { + uint8_t ipb; + + if (format == 1) { + qemu_log_mask(LOG_GUEST_ERROR, + "XIVE: END %x/%x invalid config: F1 & backlog\n", + end_blk, end_idx); + return; + } + + /* + * Record the IPB in the associated NVP structure for later + * use. The presenter will resend the interrupt when the vCPU + * is dispatched again on a HW thread. + */ + ipb = xive_get_field32(NVP2_W2_IPB, nvp.w2) | + xive_priority_to_ipb(priority); + nvp.w2 = xive_set_field32(NVP2_W2_IPB, nvp.w2, ipb); + xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, &nvp, 2); + + /* + * On HW, follows a "Broadcast Backlog" to IVPEs + */ + } + +do_escalation: + /* + * If activated, escalate notification using the ESe PQ bits and + * the EAS in w4-5 + */ + if (!xive2_end_is_escalate(&end)) { + return; + } + + /* + * Check the END ESe (Event State Buffer for escalation) for even + * futher coalescing in the Router + */ + if (!xive2_end_is_uncond_escalation(&end)) { + /* ESe[Q]=1 : end of escalation notification */ + if (!xive2_router_end_es_notify(xrtr, end_blk, end_idx, + &end, END2_W1_ESe)) { + return; + } + } + + /* + * The END trigger becomes an Escalation trigger + */ + xive2_router_end_notify(xrtr, + xive_get_field32(END2_W4_END_BLOCK, end.w4), + xive_get_field32(END2_W4_ESC_END_INDEX, end.w4), + xive_get_field32(END2_W5_ESC_END_DATA, end.w5)); +} + +void xive2_router_notify(XiveNotifier *xn, uint32_t lisn, bool pq_checked) +{ + Xive2Router *xrtr = XIVE2_ROUTER(xn); + uint8_t eas_blk = XIVE_EAS_BLOCK(lisn); + uint32_t eas_idx = XIVE_EAS_INDEX(lisn); + Xive2Eas eas; + + /* EAS cache lookup */ + if (xive2_router_get_eas(xrtr, eas_blk, eas_idx, &eas)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: Unknown LISN %x\n", lisn); + return; + } + + if (!pq_checked) { + bool notify; + uint8_t pq; + + /* PQ cache lookup */ + if (xive2_router_get_pq(xrtr, eas_blk, eas_idx, &pq)) { + /* Set FIR */ + g_assert_not_reached(); + } + + notify = xive_esb_trigger(&pq); + + if (xive2_router_set_pq(xrtr, eas_blk, eas_idx, &pq)) { + /* Set FIR */ + g_assert_not_reached(); + } + + if (!notify) { + return; + } + } + + if (!xive2_eas_is_valid(&eas)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: Invalid LISN %x\n", lisn); + return; + } + + if (xive2_eas_is_masked(&eas)) { + /* Notification completed */ + return; + } + + /* + * The event trigger becomes an END trigger + */ + xive2_router_end_notify(xrtr, + xive_get_field64(EAS2_END_BLOCK, eas.w), + xive_get_field64(EAS2_END_INDEX, eas.w), + xive_get_field64(EAS2_END_DATA, eas.w)); +} + +static Property xive2_router_properties[] = { + DEFINE_PROP_LINK("xive-fabric", Xive2Router, xfb, + TYPE_XIVE_FABRIC, XiveFabric *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xive2_router_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + XiveNotifierClass *xnc = XIVE_NOTIFIER_CLASS(klass); + + dc->desc = "XIVE2 Router Engine"; + device_class_set_props(dc, xive2_router_properties); + /* Parent is SysBusDeviceClass. No need to call its realize hook */ + dc->realize = xive2_router_realize; + xnc->notify = xive2_router_notify; +} + +static const TypeInfo xive2_router_info = { + .name = TYPE_XIVE2_ROUTER, + .parent = TYPE_SYS_BUS_DEVICE, + .abstract = true, + .instance_size = sizeof(Xive2Router), + .class_size = sizeof(Xive2RouterClass), + .class_init = xive2_router_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_XIVE_NOTIFIER }, + { TYPE_XIVE_PRESENTER }, + { } + } +}; + +static inline bool addr_is_even(hwaddr addr, uint32_t shift) +{ + return !((addr >> shift) & 1); +} + +static uint64_t xive2_end_source_read(void *opaque, hwaddr addr, unsigned size) +{ + Xive2EndSource *xsrc = XIVE2_END_SOURCE(opaque); + uint32_t offset = addr & 0xFFF; + uint8_t end_blk; + uint32_t end_idx; + Xive2End end; + uint32_t end_esmask; + uint8_t pq; + uint64_t ret; + + /* + * The block id should be deduced from the load address on the END + * ESB MMIO but our model only supports a single block per XIVE chip. + */ + end_blk = xive2_router_get_block_id(xsrc->xrtr); + end_idx = addr >> (xsrc->esb_shift + 1); + + if (xive2_router_get_end(xsrc->xrtr, end_blk, end_idx, &end)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No END %x/%x\n", end_blk, + end_idx); + return -1; + } + + if (!xive2_end_is_valid(&end)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: END %x/%x is invalid\n", + end_blk, end_idx); + return -1; + } + + end_esmask = addr_is_even(addr, xsrc->esb_shift) ? END2_W1_ESn : + END2_W1_ESe; + pq = xive_get_field32(end_esmask, end.w1); + + switch (offset) { + case XIVE_ESB_LOAD_EOI ... XIVE_ESB_LOAD_EOI + 0x7FF: + ret = xive_esb_eoi(&pq); + + /* Forward the source event notification for routing ?? */ + break; + + case XIVE_ESB_GET ... XIVE_ESB_GET + 0x3FF: + ret = pq; + break; + + case XIVE_ESB_SET_PQ_00 ... XIVE_ESB_SET_PQ_00 + 0x0FF: + case XIVE_ESB_SET_PQ_01 ... XIVE_ESB_SET_PQ_01 + 0x0FF: + case XIVE_ESB_SET_PQ_10 ... XIVE_ESB_SET_PQ_10 + 0x0FF: + case XIVE_ESB_SET_PQ_11 ... XIVE_ESB_SET_PQ_11 + 0x0FF: + ret = xive_esb_set(&pq, (offset >> 8) & 0x3); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid END ESB load addr %d\n", + offset); + return -1; + } + + if (pq != xive_get_field32(end_esmask, end.w1)) { + end.w1 = xive_set_field32(end_esmask, end.w1, pq); + xive2_router_write_end(xsrc->xrtr, end_blk, end_idx, &end, 1); + } + + return ret; +} + +static void xive2_end_source_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + Xive2EndSource *xsrc = XIVE2_END_SOURCE(opaque); + uint32_t offset = addr & 0xFFF; + uint8_t end_blk; + uint32_t end_idx; + Xive2End end; + uint32_t end_esmask; + uint8_t pq; + bool notify = false; + + /* + * The block id should be deduced from the load address on the END + * ESB MMIO but our model only supports a single block per XIVE chip. + */ + end_blk = xive2_router_get_block_id(xsrc->xrtr); + end_idx = addr >> (xsrc->esb_shift + 1); + + if (xive2_router_get_end(xsrc->xrtr, end_blk, end_idx, &end)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No END %x/%x\n", end_blk, + end_idx); + return; + } + + if (!xive2_end_is_valid(&end)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: END %x/%x is invalid\n", + end_blk, end_idx); + return; + } + + end_esmask = addr_is_even(addr, xsrc->esb_shift) ? END2_W1_ESn : + END2_W1_ESe; + pq = xive_get_field32(end_esmask, end.w1); + + switch (offset) { + case 0 ... 0x3FF: + notify = xive_esb_trigger(&pq); + break; + + case XIVE_ESB_STORE_EOI ... XIVE_ESB_STORE_EOI + 0x3FF: + /* TODO: can we check StoreEOI availability from the router ? */ + notify = xive_esb_eoi(&pq); + break; + + case XIVE_ESB_INJECT ... XIVE_ESB_INJECT + 0x3FF: + if (end_esmask == END2_W1_ESe) { + qemu_log_mask(LOG_GUEST_ERROR, + "XIVE: END %x/%x can not EQ inject on ESe\n", + end_blk, end_idx); + return; + } + notify = true; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid END ESB write addr %d\n", + offset); + return; + } + + if (pq != xive_get_field32(end_esmask, end.w1)) { + end.w1 = xive_set_field32(end_esmask, end.w1, pq); + xive2_router_write_end(xsrc->xrtr, end_blk, end_idx, &end, 1); + } + + /* TODO: Forward the source event notification for routing */ + if (notify) { + ; + } +} + +static const MemoryRegionOps xive2_end_source_ops = { + .read = xive2_end_source_read, + .write = xive2_end_source_write, + .endianness = DEVICE_BIG_ENDIAN, + .valid = { + .min_access_size = 8, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 8, + .max_access_size = 8, + }, +}; + +static void xive2_end_source_realize(DeviceState *dev, Error **errp) +{ + Xive2EndSource *xsrc = XIVE2_END_SOURCE(dev); + + assert(xsrc->xrtr); + + if (!xsrc->nr_ends) { + error_setg(errp, "Number of interrupt needs to be greater than 0"); + return; + } + + if (xsrc->esb_shift != XIVE_ESB_4K && + xsrc->esb_shift != XIVE_ESB_64K) { + error_setg(errp, "Invalid ESB shift setting"); + return; + } + + /* + * Each END is assigned an even/odd pair of MMIO pages, the even page + * manages the ESn field while the odd page manages the ESe field. + */ + memory_region_init_io(&xsrc->esb_mmio, OBJECT(xsrc), + &xive2_end_source_ops, xsrc, "xive.end", + (1ull << (xsrc->esb_shift + 1)) * xsrc->nr_ends); +} + +static Property xive2_end_source_properties[] = { + DEFINE_PROP_UINT32("nr-ends", Xive2EndSource, nr_ends, 0), + DEFINE_PROP_UINT32("shift", Xive2EndSource, esb_shift, XIVE_ESB_64K), + DEFINE_PROP_LINK("xive", Xive2EndSource, xrtr, TYPE_XIVE2_ROUTER, + Xive2Router *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xive2_end_source_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "XIVE END Source"; + device_class_set_props(dc, xive2_end_source_properties); + dc->realize = xive2_end_source_realize; +} + +static const TypeInfo xive2_end_source_info = { + .name = TYPE_XIVE2_END_SOURCE, + .parent = TYPE_DEVICE, + .instance_size = sizeof(Xive2EndSource), + .class_init = xive2_end_source_class_init, +}; + +static void xive2_register_types(void) +{ + type_register_static(&xive2_router_info); + type_register_static(&xive2_end_source_info); +} + +type_init(xive2_register_types) diff --git a/hw/pci-host/pnv_phb4.c b/hw/pci-host/pnv_phb4.c index e91249ef64..b5b384e9ee 100644 --- a/hw/pci-host/pnv_phb4.c +++ b/hw/pci-host/pnv_phb4.c @@ -485,6 +485,15 @@ static void pnv_phb4_update_xsrc(PnvPHB4 *phb) flags = 0; } + /* + * When the PQ disable configuration bit is set, the check on the + * PQ state bits is disabled on the PHB side (for MSI only) and it + * is performed on the IC side instead. + */ + if (phb->regs[PHB_CTRLR >> 3] & PHB_CTRLR_IRQ_PQ_DISABLE) { + flags |= XIVE_SRC_PQ_DISABLE; + } + phb->xsrc.esb_shift = shift; phb->xsrc.esb_flags = flags; @@ -1568,40 +1577,36 @@ static PnvPhb4PecState *pnv_phb4_get_pec(PnvChip *chip, PnvPHB4 *phb, static void pnv_phb4_realize(DeviceState *dev, Error **errp) { PnvPHB4 *phb = PNV_PHB4(dev); + PnvMachineState *pnv = PNV_MACHINE(qdev_get_machine()); + PnvChip *chip = pnv_get_chip(pnv, phb->chip_id); PCIHostState *pci = PCI_HOST_BRIDGE(dev); XiveSource *xsrc = &phb->xsrc; + BusState *s; Error *local_err = NULL; int nr_irqs; char name[32]; - /* User created PHB */ - if (!phb->pec) { - PnvMachineState *pnv = PNV_MACHINE(qdev_get_machine()); - PnvChip *chip = pnv_get_chip(pnv, phb->chip_id); - BusState *s; - - if (!chip) { - error_setg(errp, "invalid chip id: %d", phb->chip_id); - return; - } + if (!chip) { + error_setg(errp, "invalid chip id: %d", phb->chip_id); + return; + } + /* User created PHBs need to be assigned to a PEC */ + if (!phb->pec) { phb->pec = pnv_phb4_get_pec(chip, phb, &local_err); if (local_err) { error_propagate(errp, local_err); return; } + } - /* - * Reparent user created devices to the chip to build - * correctly the device tree. - */ - pnv_chip_parent_fixup(chip, OBJECT(phb), phb->phb_id); + /* Reparent the PHB to the chip to build the device tree */ + pnv_chip_parent_fixup(chip, OBJECT(phb), phb->phb_id); - s = qdev_get_parent_bus(DEVICE(chip)); - if (!qdev_set_parent_bus(DEVICE(phb), s, &local_err)) { - error_propagate(errp, local_err); - return; - } + s = qdev_get_parent_bus(DEVICE(chip)); + if (!qdev_set_parent_bus(DEVICE(phb), s, &local_err)) { + error_propagate(errp, local_err); + return; } /* Set the "big_phb" flag */ @@ -1664,15 +1669,64 @@ static const char *pnv_phb4_root_bus_path(PCIHostState *host_bridge, return phb->bus_path; } -static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno) +/* + * Address base trigger mode (POWER10) + * + * Trigger directly the IC ESB page + */ +static void pnv_phb4_xive_notify_abt(PnvPHB4 *phb, uint32_t srcno, + bool pq_checked) +{ + uint64_t notif_port = phb->regs[PHB_INT_NOTIFY_ADDR >> 3]; + uint64_t data = 0; /* trigger data : don't care */ + hwaddr addr; + MemTxResult result; + int esb_shift; + + if (notif_port & PHB_INT_NOTIFY_ADDR_64K) { + esb_shift = 16; + } else { + esb_shift = 12; + } + + /* Compute the address of the IC ESB management page */ + addr = (notif_port & ~PHB_INT_NOTIFY_ADDR_64K); + addr |= (1ull << (esb_shift + 1)) * srcno; + addr |= (1ull << esb_shift); + + /* + * When the PQ state bits are checked on the PHB, the associated + * PQ state bits on the IC should be ignored. Use the unconditional + * trigger offset to inject a trigger on the IC. This is always + * the case for LSIs + */ + if (pq_checked) { + addr |= XIVE_ESB_INJECT; + } + + trace_pnv_phb4_xive_notify_ic(addr, data); + + address_space_stq_be(&address_space_memory, addr, data, + MEMTXATTRS_UNSPECIFIED, &result); + if (result != MEMTX_OK) { + phb_error(phb, "trigger failed @%"HWADDR_PRIx "\n", addr); + return; + } +} + +static void pnv_phb4_xive_notify_ic(PnvPHB4 *phb, uint32_t srcno, + bool pq_checked) { - PnvPHB4 *phb = PNV_PHB4(xf); uint64_t notif_port = phb->regs[PHB_INT_NOTIFY_ADDR >> 3]; uint32_t offset = phb->regs[PHB_INT_NOTIFY_INDEX >> 3]; - uint64_t data = XIVE_TRIGGER_PQ | offset | srcno; + uint64_t data = offset | srcno; MemTxResult result; - trace_pnv_phb4_xive_notify(notif_port, data); + if (pq_checked) { + data |= XIVE_TRIGGER_PQ; + } + + trace_pnv_phb4_xive_notify_ic(notif_port, data); address_space_stq_be(&address_space_memory, notif_port, data, MEMTXATTRS_UNSPECIFIED, &result); @@ -1682,6 +1736,18 @@ static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno) } } +static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno, + bool pq_checked) +{ + PnvPHB4 *phb = PNV_PHB4(xf); + + if (phb->regs[PHB_CTRLR >> 3] & PHB_CTRLR_IRQ_ABT_MODE) { + pnv_phb4_xive_notify_abt(phb, srcno, pq_checked); + } else { + pnv_phb4_xive_notify_ic(phb, srcno, pq_checked); + } +} + static Property pnv_phb4_properties[] = { DEFINE_PROP_UINT32("index", PnvPHB4, phb_id, 0), DEFINE_PROP_UINT32("chip-id", PnvPHB4, chip_id, 0), @@ -1816,9 +1882,29 @@ static const TypeInfo pnv_phb4_root_port_info = { .class_init = pnv_phb4_root_port_class_init, }; +static void pnv_phb5_root_port_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + + dc->desc = "IBM PHB5 PCIE Root Port"; + dc->user_creatable = true; + + k->vendor_id = PCI_VENDOR_ID_IBM; + k->device_id = PNV_PHB5_DEVICE_ID; +} + +static const TypeInfo pnv_phb5_root_port_info = { + .name = TYPE_PNV_PHB5_ROOT_PORT, + .parent = TYPE_PNV_PHB4_ROOT_PORT, + .instance_size = sizeof(PnvPHB4RootPort), + .class_init = pnv_phb5_root_port_class_init, +}; + static void pnv_phb4_register_types(void) { type_register_static(&pnv_phb4_root_bus_info); + type_register_static(&pnv_phb5_root_port_info); type_register_static(&pnv_phb4_root_port_info); type_register_static(&pnv_phb4_type_info); type_register_static(&pnv_phb4_iommu_memory_region_info); @@ -1828,10 +1914,15 @@ type_init(pnv_phb4_register_types); void pnv_phb4_pic_print_info(PnvPHB4 *phb, Monitor *mon) { + uint64_t notif_port = + phb->regs[PHB_INT_NOTIFY_ADDR >> 3] & ~PHB_INT_NOTIFY_ADDR_64K; uint32_t offset = phb->regs[PHB_INT_NOTIFY_INDEX >> 3]; + bool abt = !!(phb->regs[PHB_CTRLR >> 3] & PHB_CTRLR_IRQ_ABT_MODE); - monitor_printf(mon, "PHB4[%x:%x] Source %08x .. %08x\n", + monitor_printf(mon, "PHB4[%x:%x] Source %08x .. %08x %s @%"HWADDR_PRIx"\n", phb->chip_id, phb->phb_id, - offset, offset + phb->xsrc.nr_irqs - 1); + offset, offset + phb->xsrc.nr_irqs - 1, + abt ? "ABT" : "", + notif_port); xive_source_pic_print_info(&phb->xsrc, 0, mon); } diff --git a/hw/pci-host/pnv_phb4_pec.c b/hw/pci-host/pnv_phb4_pec.c index 40d89fda56..0ab36e9c8f 100644 --- a/hw/pci-host/pnv_phb4_pec.c +++ b/hw/pci-host/pnv_phb4_pec.c @@ -281,9 +281,62 @@ static const TypeInfo pnv_pec_type_info = { } }; +/* + * POWER10 definitions + */ + +static uint32_t pnv_phb5_pec_xscom_pci_base(PnvPhb4PecState *pec) +{ + return PNV10_XSCOM_PEC_PCI_BASE + 0x1000000 * pec->index; +} + +static uint32_t pnv_phb5_pec_xscom_nest_base(PnvPhb4PecState *pec) +{ + /* index goes down ... */ + return PNV10_XSCOM_PEC_NEST_BASE - 0x1000000 * pec->index; +} + +/* + * PEC0 -> 3 stacks + * PEC1 -> 3 stacks + */ +static const uint32_t pnv_phb5_pec_num_stacks[] = { 3, 3 }; + +static void pnv_phb5_pec_class_init(ObjectClass *klass, void *data) +{ + PnvPhb4PecClass *pecc = PNV_PHB4_PEC_CLASS(klass); + static const char compat[] = "ibm,power10-pbcq"; + static const char stk_compat[] = "ibm,power10-phb-stack"; + + pecc->xscom_nest_base = pnv_phb5_pec_xscom_nest_base; + pecc->xscom_pci_base = pnv_phb5_pec_xscom_pci_base; + pecc->xscom_nest_size = PNV10_XSCOM_PEC_NEST_SIZE; + pecc->xscom_pci_size = PNV10_XSCOM_PEC_PCI_SIZE; + pecc->compat = compat; + pecc->compat_size = sizeof(compat); + pecc->stk_compat = stk_compat; + pecc->stk_compat_size = sizeof(stk_compat); + pecc->version = PNV_PHB5_VERSION; + pecc->num_phbs = pnv_phb5_pec_num_stacks; + pecc->rp_model = TYPE_PNV_PHB5_ROOT_PORT; +} + +static const TypeInfo pnv_phb5_pec_type_info = { + .name = TYPE_PNV_PHB5_PEC, + .parent = TYPE_PNV_PHB4_PEC, + .instance_size = sizeof(PnvPhb4PecState), + .class_init = pnv_phb5_pec_class_init, + .class_size = sizeof(PnvPhb4PecClass), + .interfaces = (InterfaceInfo[]) { + { TYPE_PNV_XSCOM_INTERFACE }, + { } + } +}; + static void pnv_pec_register_types(void) { type_register_static(&pnv_pec_type_info); + type_register_static(&pnv_phb5_pec_type_info); } type_init(pnv_pec_register_types); diff --git a/hw/pci-host/trace-events b/hw/pci-host/trace-events index 630e9fcc5e..6e5d8d3355 100644 --- a/hw/pci-host/trace-events +++ b/hw/pci-host/trace-events @@ -32,3 +32,5 @@ unin_read(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64 # pnv_phb4.c pnv_phb4_xive_notify(uint64_t notif_port, uint64_t data) "notif=@0x%"PRIx64" data=0x%"PRIx64 +pnv_phb4_xive_notify_ic(uint64_t addr, uint64_t data) "addr=@0x%"PRIx64" data=0x%"PRIx64 +pnv_phb4_xive_notify_abt(uint64_t notif_port, uint64_t data) "notif=@0x%"PRIx64" data=0x%"PRIx64 diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index 837146a2fb..0ac86e104f 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -380,9 +380,12 @@ static void pnv_dt_serial(ISADevice *d, void *fdt, int lpc_off) cpu_to_be32(io_base), cpu_to_be32(8) }; + uint32_t irq; char *name; int node; + irq = object_property_get_uint(OBJECT(d), "irq", &error_fatal); + name = g_strdup_printf("%s@i%x", qdev_fw_name(DEVICE(d)), io_base); node = fdt_add_subnode(fdt, lpc_off, name); _FDT(node); @@ -394,7 +397,7 @@ static void pnv_dt_serial(ISADevice *d, void *fdt, int lpc_off) _FDT((fdt_setprop_cell(fdt, node, "clock-frequency", 1843200))); _FDT((fdt_setprop_cell(fdt, node, "current-speed", 115200))); - _FDT((fdt_setprop_cell(fdt, node, "interrupts", d->isairq[0]))); + _FDT((fdt_setprop_cell(fdt, node, "interrupts", irq))); _FDT((fdt_setprop_cell(fdt, node, "interrupt-parent", fdt_get_phandle(fdt, lpc_off)))); @@ -722,7 +725,11 @@ static void pnv_chip_power10_pic_print_info(PnvChip *chip, Monitor *mon) { Pnv10Chip *chip10 = PNV10_CHIP(chip); + pnv_xive2_pic_print_info(&chip10->xive, mon); pnv_psi_pic_print_info(&chip10->psi, mon); + + object_child_foreach_recursive(OBJECT(chip), + pnv_chip_power9_pic_print_info_child, mon); } /* Always give the first 1GB to chip 0 else we won't boot */ @@ -1044,27 +1051,45 @@ static void pnv_chip_power9_intc_print_info(PnvChip *chip, PowerPCCPU *cpu, static void pnv_chip_power10_intc_create(PnvChip *chip, PowerPCCPU *cpu, Error **errp) { + Pnv10Chip *chip10 = PNV10_CHIP(chip); + Error *local_err = NULL; + Object *obj; PnvCPUState *pnv_cpu = pnv_cpu_state(cpu); - /* Will be defined when the interrupt controller is */ - pnv_cpu->intc = NULL; + /* + * The core creates its interrupt presenter but the XIVE2 interrupt + * controller object is initialized afterwards. Hopefully, it's + * only used at runtime. + */ + obj = xive_tctx_create(OBJECT(cpu), XIVE_PRESENTER(&chip10->xive), + &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + pnv_cpu->intc = obj; } static void pnv_chip_power10_intc_reset(PnvChip *chip, PowerPCCPU *cpu) { - ; + PnvCPUState *pnv_cpu = pnv_cpu_state(cpu); + + xive_tctx_reset(XIVE_TCTX(pnv_cpu->intc)); } static void pnv_chip_power10_intc_destroy(PnvChip *chip, PowerPCCPU *cpu) { PnvCPUState *pnv_cpu = pnv_cpu_state(cpu); + xive_tctx_destroy(XIVE_TCTX(pnv_cpu->intc)); pnv_cpu->intc = NULL; } static void pnv_chip_power10_intc_print_info(PnvChip *chip, PowerPCCPU *cpu, Monitor *mon) { + xive_tctx_pic_print_info(XIVE_TCTX(pnv_cpu_state(cpu)->intc), mon); } /* @@ -1366,6 +1391,21 @@ static void pnv_chip_power9_instance_init(Object *obj) } } +static void pnv_chip_quad_realize_one(PnvChip *chip, PnvQuad *eq, + PnvCore *pnv_core) +{ + char eq_name[32]; + int core_id = CPU_CORE(pnv_core)->core_id; + + snprintf(eq_name, sizeof(eq_name), "eq[%d]", core_id); + object_initialize_child_with_props(OBJECT(chip), eq_name, eq, + sizeof(*eq), TYPE_PNV_QUAD, + &error_fatal, NULL); + + object_property_set_int(OBJECT(eq), "quad-id", core_id, &error_fatal); + qdev_realize(DEVICE(eq), NULL, &error_fatal); +} + static void pnv_chip_quad_realize(Pnv9Chip *chip9, Error **errp) { PnvChip *chip = PNV_CHIP(chip9); @@ -1375,18 +1415,9 @@ static void pnv_chip_quad_realize(Pnv9Chip *chip9, Error **errp) chip9->quads = g_new0(PnvQuad, chip9->nr_quads); for (i = 0; i < chip9->nr_quads; i++) { - char eq_name[32]; PnvQuad *eq = &chip9->quads[i]; - PnvCore *pnv_core = chip->cores[i * 4]; - int core_id = CPU_CORE(pnv_core)->core_id; - snprintf(eq_name, sizeof(eq_name), "eq[%d]", core_id); - object_initialize_child_with_props(OBJECT(chip), eq_name, eq, - sizeof(*eq), TYPE_PNV_QUAD, - &error_fatal, NULL); - - object_property_set_int(OBJECT(eq), "quad-id", core_id, &error_fatal); - qdev_realize(DEVICE(eq), NULL, &error_fatal); + pnv_chip_quad_realize_one(chip, eq, chip->cores[i * 4]); pnv_xscom_add_subregion(chip, PNV9_XSCOM_EQ_BASE(eq->quad_id), &eq->xscom_regs); @@ -1469,6 +1500,9 @@ static void pnv_chip_power9_realize(DeviceState *dev, Error **errp) /* Processor Service Interface (PSI) Host Bridge */ object_property_set_int(OBJECT(&chip9->psi), "bar", PNV9_PSIHB_BASE(chip), &error_fatal); + /* This is the only device with 4k ESB pages */ + object_property_set_int(OBJECT(&chip9->psi), "shift", XIVE_ESB_4K, + &error_fatal); if (!qdev_realize(DEVICE(&chip9->psi), NULL, errp)) { return; } @@ -1553,10 +1587,73 @@ static void pnv_chip_power9_class_init(ObjectClass *klass, void *data) static void pnv_chip_power10_instance_init(Object *obj) { + PnvChip *chip = PNV_CHIP(obj); Pnv10Chip *chip10 = PNV10_CHIP(obj); + PnvChipClass *pcc = PNV_CHIP_GET_CLASS(obj); + int i; + object_initialize_child(obj, "xive", &chip10->xive, TYPE_PNV_XIVE2); + object_property_add_alias(obj, "xive-fabric", OBJECT(&chip10->xive), + "xive-fabric"); object_initialize_child(obj, "psi", &chip10->psi, TYPE_PNV10_PSI); object_initialize_child(obj, "lpc", &chip10->lpc, TYPE_PNV10_LPC); + object_initialize_child(obj, "occ", &chip10->occ, TYPE_PNV10_OCC); + object_initialize_child(obj, "homer", &chip10->homer, TYPE_PNV10_HOMER); + + if (defaults_enabled()) { + chip->num_pecs = pcc->num_pecs; + } + + for (i = 0; i < chip->num_pecs; i++) { + object_initialize_child(obj, "pec[*]", &chip10->pecs[i], + TYPE_PNV_PHB5_PEC); + } +} + +static void pnv_chip_power10_quad_realize(Pnv10Chip *chip10, Error **errp) +{ + PnvChip *chip = PNV_CHIP(chip10); + int i; + + chip10->nr_quads = DIV_ROUND_UP(chip->nr_cores, 4); + chip10->quads = g_new0(PnvQuad, chip10->nr_quads); + + for (i = 0; i < chip10->nr_quads; i++) { + PnvQuad *eq = &chip10->quads[i]; + + pnv_chip_quad_realize_one(chip, eq, chip->cores[i * 4]); + + pnv_xscom_add_subregion(chip, PNV10_XSCOM_EQ_BASE(eq->quad_id), + &eq->xscom_regs); + } +} + +static void pnv_chip_power10_phb_realize(PnvChip *chip, Error **errp) +{ + Pnv10Chip *chip10 = PNV10_CHIP(chip); + int i; + + for (i = 0; i < chip->num_pecs; i++) { + PnvPhb4PecState *pec = &chip10->pecs[i]; + PnvPhb4PecClass *pecc = PNV_PHB4_PEC_GET_CLASS(pec); + uint32_t pec_nest_base; + uint32_t pec_pci_base; + + object_property_set_int(OBJECT(pec), "index", i, &error_fatal); + object_property_set_int(OBJECT(pec), "chip-id", chip->chip_id, + &error_fatal); + object_property_set_link(OBJECT(pec), "chip", OBJECT(chip), + &error_fatal); + if (!qdev_realize(DEVICE(pec), NULL, errp)) { + return; + } + + pec_nest_base = pecc->xscom_nest_base(pec); + pec_pci_base = pecc->xscom_pci_base(pec); + + pnv_xscom_add_subregion(chip, pec_nest_base, &pec->nest_regs_mr); + pnv_xscom_add_subregion(chip, pec_pci_base, &pec->pci_regs_mr); + } } static void pnv_chip_power10_realize(DeviceState *dev, Error **errp) @@ -1580,9 +1677,39 @@ static void pnv_chip_power10_realize(DeviceState *dev, Error **errp) return; } + pnv_chip_power10_quad_realize(chip10, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + /* XIVE2 interrupt controller (POWER10) */ + object_property_set_int(OBJECT(&chip10->xive), "ic-bar", + PNV10_XIVE2_IC_BASE(chip), &error_fatal); + object_property_set_int(OBJECT(&chip10->xive), "esb-bar", + PNV10_XIVE2_ESB_BASE(chip), &error_fatal); + object_property_set_int(OBJECT(&chip10->xive), "end-bar", + PNV10_XIVE2_END_BASE(chip), &error_fatal); + object_property_set_int(OBJECT(&chip10->xive), "nvpg-bar", + PNV10_XIVE2_NVPG_BASE(chip), &error_fatal); + object_property_set_int(OBJECT(&chip10->xive), "nvc-bar", + PNV10_XIVE2_NVC_BASE(chip), &error_fatal); + object_property_set_int(OBJECT(&chip10->xive), "tm-bar", + PNV10_XIVE2_TM_BASE(chip), &error_fatal); + object_property_set_link(OBJECT(&chip10->xive), "chip", OBJECT(chip), + &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&chip10->xive), errp)) { + return; + } + pnv_xscom_add_subregion(chip, PNV10_XSCOM_XIVE2_BASE, + &chip10->xive.xscom_regs); + /* Processor Service Interface (PSI) Host Bridge */ object_property_set_int(OBJECT(&chip10->psi), "bar", PNV10_PSIHB_BASE(chip), &error_fatal); + /* PSI can now be configured to use 64k ESB pages on POWER10 */ + object_property_set_int(OBJECT(&chip10->psi), "shift", XIVE_ESB_64K, + &error_fatal); if (!qdev_realize(DEVICE(&chip10->psi), NULL, errp)) { return; } @@ -1601,6 +1728,41 @@ static void pnv_chip_power10_realize(DeviceState *dev, Error **errp) chip->fw_mr = &chip10->lpc.isa_fw; chip->dt_isa_nodename = g_strdup_printf("/lpcm-opb@%" PRIx64 "/lpc@0", (uint64_t) PNV10_LPCM_BASE(chip)); + + /* Create the simplified OCC model */ + object_property_set_link(OBJECT(&chip10->occ), "psi", OBJECT(&chip10->psi), + &error_abort); + if (!qdev_realize(DEVICE(&chip10->occ), NULL, errp)) { + return; + } + pnv_xscom_add_subregion(chip, PNV10_XSCOM_OCC_BASE, + &chip10->occ.xscom_regs); + + /* OCC SRAM model */ + memory_region_add_subregion(get_system_memory(), + PNV10_OCC_SENSOR_BASE(chip), + &chip10->occ.sram_regs); + + /* HOMER */ + object_property_set_link(OBJECT(&chip10->homer), "chip", OBJECT(chip), + &error_abort); + if (!qdev_realize(DEVICE(&chip10->homer), NULL, errp)) { + return; + } + /* Homer Xscom region */ + pnv_xscom_add_subregion(chip, PNV10_XSCOM_PBA_BASE, + &chip10->homer.pba_regs); + + /* Homer mmio region */ + memory_region_add_subregion(get_system_memory(), PNV10_HOMER_BASE(chip), + &chip10->homer.regs); + + /* PHBs */ + pnv_chip_power10_phb_realize(chip, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } } static uint32_t pnv_chip_power10_xscom_pcba(PnvChip *chip, uint64_t addr) @@ -1627,6 +1789,7 @@ static void pnv_chip_power10_class_init(ObjectClass *klass, void *data) k->xscom_core_base = pnv_chip_power10_xscom_core_base; k->xscom_pcba = pnv_chip_power10_xscom_pcba; dc->desc = "PowerNV Chip POWER10"; + k->num_pecs = PNV10_CHIP_MAX_PEC; device_class_set_parent_realize(dc, pnv_chip_power10_realize, &k->parent_realize); @@ -1924,6 +2087,35 @@ static int pnv_match_nvt(XiveFabric *xfb, uint8_t format, return total_count; } +static int pnv10_xive_match_nvt(XiveFabric *xfb, uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool cam_ignore, uint8_t priority, + uint32_t logic_serv, + XiveTCTXMatch *match) +{ + PnvMachineState *pnv = PNV_MACHINE(xfb); + int total_count = 0; + int i; + + for (i = 0; i < pnv->num_chips; i++) { + Pnv10Chip *chip10 = PNV10_CHIP(pnv->chips[i]); + XivePresenter *xptr = XIVE_PRESENTER(&chip10->xive); + XivePresenterClass *xpc = XIVE_PRESENTER_GET_CLASS(xptr); + int count; + + count = xpc->match_nvt(xptr, format, nvt_blk, nvt_idx, cam_ignore, + priority, logic_serv, match); + + if (count < 0) { + return count; + } + + total_count += count; + } + + return total_count; +} + static void pnv_machine_power8_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -1968,6 +2160,7 @@ static void pnv_machine_power10_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); PnvMachineClass *pmc = PNV_MACHINE_CLASS(oc); + XiveFabricClass *xfc = XIVE_FABRIC_CLASS(oc); static const char compat[] = "qemu,powernv10\0ibm,powernv"; mc->desc = "IBM PowerNV (Non-Virtualized) POWER10"; @@ -1976,6 +2169,8 @@ static void pnv_machine_power10_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size = sizeof(compat); pmc->dt_power_mgt = pnv_dt_power_mgt; + + xfc->match_nvt = pnv10_xive_match_nvt; } static bool pnv_machine_get_hb(Object *obj, Error **errp) @@ -2087,6 +2282,10 @@ static const TypeInfo types[] = { .name = MACHINE_TYPE_NAME("powernv10"), .parent = TYPE_PNV_MACHINE, .class_init = pnv_machine_power10_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_XIVE_FABRIC }, + { }, + }, }, { .name = MACHINE_TYPE_NAME("powernv9"), diff --git a/hw/ppc/pnv_homer.c b/hw/ppc/pnv_homer.c index 9a262629b7..ea73919e54 100644 --- a/hw/ppc/pnv_homer.c +++ b/hw/ppc/pnv_homer.c @@ -332,6 +332,69 @@ static const TypeInfo pnv_homer_power9_type_info = { .class_init = pnv_homer_power9_class_init, }; +static uint64_t pnv_homer_power10_pba_read(void *opaque, hwaddr addr, + unsigned size) +{ + PnvHomer *homer = PNV_HOMER(opaque); + PnvChip *chip = homer->chip; + uint32_t reg = addr >> 3; + uint64_t val = 0; + + switch (reg) { + case PBA_BAR0: + val = PNV10_HOMER_BASE(chip); + break; + case PBA_BARMASK0: /* P10 homer region mask */ + val = (PNV10_HOMER_SIZE - 1) & 0x300000; + break; + case PBA_BAR2: /* P10 occ common area */ + val = PNV10_OCC_COMMON_AREA_BASE; + break; + case PBA_BARMASK2: /* P10 occ common area size */ + val = (PNV10_OCC_COMMON_AREA_SIZE - 1) & 0x700000; + break; + default: + qemu_log_mask(LOG_UNIMP, "PBA: read to unimplemented register: Ox%" + HWADDR_PRIx "\n", addr >> 3); + } + return val; +} + +static void pnv_homer_power10_pba_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + qemu_log_mask(LOG_UNIMP, "PBA: write to unimplemented register: Ox%" + HWADDR_PRIx "\n", addr >> 3); +} + +static const MemoryRegionOps pnv_homer_power10_pba_ops = { + .read = pnv_homer_power10_pba_read, + .write = pnv_homer_power10_pba_write, + .valid.min_access_size = 8, + .valid.max_access_size = 8, + .impl.min_access_size = 8, + .impl.max_access_size = 8, + .endianness = DEVICE_BIG_ENDIAN, +}; + +static void pnv_homer_power10_class_init(ObjectClass *klass, void *data) +{ + PnvHomerClass *homer = PNV_HOMER_CLASS(klass); + + homer->pba_size = PNV10_XSCOM_PBA_SIZE; + homer->pba_ops = &pnv_homer_power10_pba_ops; + homer->homer_size = PNV10_HOMER_SIZE; + homer->homer_ops = &pnv_power9_homer_ops; /* TODO */ + homer->core_max_base = PNV9_CORE_MAX_BASE; +} + +static const TypeInfo pnv_homer_power10_type_info = { + .name = TYPE_PNV10_HOMER, + .parent = TYPE_PNV_HOMER, + .instance_size = sizeof(PnvHomer), + .class_init = pnv_homer_power10_class_init, +}; + static void pnv_homer_realize(DeviceState *dev, Error **errp) { PnvHomer *homer = PNV_HOMER(dev); @@ -377,6 +440,7 @@ static void pnv_homer_register_types(void) type_register_static(&pnv_homer_type_info); type_register_static(&pnv_homer_power8_type_info); type_register_static(&pnv_homer_power9_type_info); + type_register_static(&pnv_homer_power10_type_info); } type_init(pnv_homer_register_types); diff --git a/hw/ppc/pnv_occ.c b/hw/ppc/pnv_occ.c index 5a716c256e..4ed66f5e1f 100644 --- a/hw/ppc/pnv_occ.c +++ b/hw/ppc/pnv_occ.c @@ -236,7 +236,9 @@ static const MemoryRegionOps pnv_occ_power9_xscom_ops = { static void pnv_occ_power9_class_init(ObjectClass *klass, void *data) { PnvOCCClass *poc = PNV_OCC_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + dc->desc = "PowerNV OCC Controller (POWER9)"; poc->xscom_size = PNV9_XSCOM_OCC_SIZE; poc->xscom_ops = &pnv_occ_power9_xscom_ops; poc->psi_irq = PSIHB9_IRQ_OCC; @@ -249,6 +251,19 @@ static const TypeInfo pnv_occ_power9_type_info = { .class_init = pnv_occ_power9_class_init, }; +static void pnv_occ_power10_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "PowerNV OCC Controller (POWER10)"; +} + +static const TypeInfo pnv_occ_power10_type_info = { + .name = TYPE_PNV10_OCC, + .parent = TYPE_PNV9_OCC, + .class_init = pnv_occ_power10_class_init, +}; + static void pnv_occ_realize(DeviceState *dev, Error **errp) { PnvOCC *occ = PNV_OCC(dev); @@ -297,6 +312,7 @@ static void pnv_occ_register_types(void) type_register_static(&pnv_occ_type_info); type_register_static(&pnv_occ_power8_type_info); type_register_static(&pnv_occ_power9_type_info); + type_register_static(&pnv_occ_power10_type_info); } type_init(pnv_occ_register_types); diff --git a/hw/ppc/pnv_psi.c b/hw/ppc/pnv_psi.c index cd9a2c5952..466fb79798 100644 --- a/hw/ppc/pnv_psi.c +++ b/hw/ppc/pnv_psi.c @@ -601,7 +601,6 @@ static const TypeInfo pnv_psi_power8_info = { #define PSIHB9_IRQ_METHOD PPC_BIT(0) #define PSIHB9_IRQ_RESET PPC_BIT(1) #define PSIHB9_ESB_CI_BASE 0x60 -#define PSIHB9_ESB_CI_64K PPC_BIT(1) #define PSIHB9_ESB_CI_ADDR_MASK PPC_BITMASK(8, 47) #define PSIHB9_ESB_CI_VALID PPC_BIT(63) #define PSIHB9_ESB_NOTIF_ADDR 0x68 @@ -646,7 +645,15 @@ static const TypeInfo pnv_psi_power8_info = { #define PSIHB9_IRQ_STAT_DIO PPC_BIT(12) #define PSIHB9_IRQ_STAT_PSU PPC_BIT(13) -static void pnv_psi_notify(XiveNotifier *xf, uint32_t srcno) +/* P10 register extensions */ + +#define PSIHB10_CR PSIHB9_CR +#define PSIHB10_CR_STORE_EOI PPC_BIT(12) + +#define PSIHB10_ESB_CI_BASE PSIHB9_ESB_CI_BASE +#define PSIHB10_ESB_CI_64K PPC_BIT(1) + +static void pnv_psi_notify(XiveNotifier *xf, uint32_t srcno, bool pq_checked) { PnvPsi *psi = PNV_PSI(xf); uint64_t notif_port = psi->regs[PSIHB_REG(PSIHB9_ESB_NOTIF_ADDR)]; @@ -655,9 +662,13 @@ static void pnv_psi_notify(XiveNotifier *xf, uint32_t srcno) uint32_t offset = (psi->regs[PSIHB_REG(PSIHB9_IVT_OFFSET)] >> PSIHB9_IVT_OFF_SHIFT); - uint64_t data = XIVE_TRIGGER_PQ | offset | srcno; + uint64_t data = offset | srcno; MemTxResult result; + if (pq_checked) { + data |= XIVE_TRIGGER_PQ; + } + if (!valid) { return; } @@ -704,6 +715,13 @@ static void pnv_psi_p9_mmio_write(void *opaque, hwaddr addr, switch (addr) { case PSIHB9_CR: + if (val & PSIHB10_CR_STORE_EOI) { + psi9->source.esb_flags |= XIVE_SRC_STORE_EOI; + } else { + psi9->source.esb_flags &= ~XIVE_SRC_STORE_EOI; + } + break; + case PSIHB9_SEMR: /* FSP stuff */ break; @@ -715,15 +733,20 @@ static void pnv_psi_p9_mmio_write(void *opaque, hwaddr addr, break; case PSIHB9_ESB_CI_BASE: + if (val & PSIHB10_ESB_CI_64K) { + psi9->source.esb_shift = XIVE_ESB_64K; + } else { + psi9->source.esb_shift = XIVE_ESB_4K; + } if (!(val & PSIHB9_ESB_CI_VALID)) { if (psi->regs[reg] & PSIHB9_ESB_CI_VALID) { memory_region_del_subregion(sysmem, &psi9->source.esb_mmio); } } else { if (!(psi->regs[reg] & PSIHB9_ESB_CI_VALID)) { - memory_region_add_subregion(sysmem, - val & ~PSIHB9_ESB_CI_VALID, - &psi9->source.esb_mmio); + hwaddr addr = val & ~(PSIHB9_ESB_CI_VALID | PSIHB10_ESB_CI_64K); + memory_region_add_subregion(sysmem, addr, + &psi9->source.esb_mmio); } } psi->regs[reg] = val; @@ -831,6 +854,7 @@ static void pnv_psi_power9_instance_init(Object *obj) Pnv9Psi *psi = PNV9_PSI(obj); object_initialize_child(obj, "source", &psi->source, TYPE_XIVE_SOURCE); + object_property_add_alias(obj, "shift", OBJECT(&psi->source), "shift"); } static void pnv_psi_power9_realize(DeviceState *dev, Error **errp) @@ -839,8 +863,6 @@ static void pnv_psi_power9_realize(DeviceState *dev, Error **errp) XiveSource *xsrc = &PNV9_PSI(psi)->source; int i; - /* This is the only device with 4k ESB pages */ - object_property_set_int(OBJECT(xsrc), "shift", XIVE_ESB_4K, &error_fatal); object_property_set_int(OBJECT(xsrc), "nr-irqs", PSIHB9_NUM_IRQS, &error_fatal); object_property_set_link(OBJECT(xsrc), "xive", OBJECT(psi), &error_abort); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index f0b75b22bb..4cc204f90d 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -1018,9 +1018,9 @@ static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt, bool reset) if (reset) { const char *boot_device = spapr->boot_device; - char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus); + g_autofree char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus); size_t cb = 0; - char *bootlist = get_boot_devices_list(&cb); + g_autofree char *bootlist = get_boot_devices_list(&cb); if (machine->kernel_cmdline && machine->kernel_cmdline[0]) { _FDT(fdt_setprop_string(fdt, chosen, "bootargs", @@ -1087,9 +1087,6 @@ static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt, bool reset) } spapr_dt_ov5_platform_support(spapr, fdt, chosen); - - g_free(stdout_path); - g_free(bootlist); } _FDT(spapr_dt_ovec(fdt, chosen, spapr->ov5_cas, "ibm,architecture-vec-5")); @@ -2710,15 +2707,25 @@ static void spapr_machine_init(MachineState *machine) MachineClass *mc = MACHINE_GET_CLASS(machine); const char *bios_default = spapr->vof ? FW_FILE_NAME_VOF : FW_FILE_NAME; const char *bios_name = machine->firmware ?: bios_default; + g_autofree char *filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); const char *kernel_filename = machine->kernel_filename; const char *initrd_filename = machine->initrd_filename; PCIHostState *phb; int i; MemoryRegion *sysmem = get_system_memory(); long load_limit, fw_size; - char *filename; Error *resize_hpt_err = NULL; + if (!filename) { + error_report("Could not find LPAR firmware '%s'", bios_name); + exit(1); + } + fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE); + if (fw_size <= 0) { + error_report("Could not load LPAR firmware '%s'", filename); + exit(1); + } + /* * if Secure VM (PEF) support is configured, then initialize it */ @@ -2999,18 +3006,6 @@ static void spapr_machine_init(MachineState *machine) } } - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); - if (!filename) { - error_report("Could not find LPAR firmware '%s'", bios_name); - exit(1); - } - fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE); - if (fw_size <= 0) { - error_report("Could not load LPAR firmware '%s'", filename); - exit(1); - } - g_free(filename); - /* FIXME: Should register things through the MachineState's qdev * interface, this is a legacy from the sPAPREnvironment structure * which predated MachineState but had a similar function */ diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c index 6167431271..655ab856a0 100644 --- a/hw/ppc/spapr_caps.c +++ b/hw/ppc/spapr_caps.c @@ -95,12 +95,12 @@ static void spapr_cap_set_bool(Object *obj, Visitor *v, const char *name, } -static void spapr_cap_get_string(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) +static void spapr_cap_get_string(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) { SpaprCapabilityInfo *cap = opaque; SpaprMachineState *spapr = SPAPR_MACHINE(obj); - char *val = NULL; + g_autofree char *val = NULL; uint8_t value = spapr_get_cap(spapr, cap->index); if (value >= cap->possible->num) { @@ -111,7 +111,6 @@ static void spapr_cap_get_string(Object *obj, Visitor *v, const char *name, val = g_strdup(cap->possible->vals[value]); visit_type_str(v, name, &val, errp); - g_free(val); } static void spapr_cap_set_string(Object *obj, Visitor *v, const char *name, @@ -120,7 +119,7 @@ static void spapr_cap_set_string(Object *obj, Visitor *v, const char *name, SpaprCapabilityInfo *cap = opaque; SpaprMachineState *spapr = SPAPR_MACHINE(obj); uint8_t i; - char *val; + g_autofree char *val = NULL; if (!visit_type_str(v, name, &val, errp)) { return; @@ -128,20 +127,18 @@ static void spapr_cap_set_string(Object *obj, Visitor *v, const char *name, if (!strcmp(val, "?")) { error_setg(errp, "%s", cap->possible->help); - goto out; + return; } for (i = 0; i < cap->possible->num; i++) { if (!strcasecmp(val, cap->possible->vals[i])) { spapr->cmd_line_caps[cap->index] = true; spapr->eff.caps[cap->index] = i; - goto out; + return; } } error_setg(errp, "Invalid capability mode \"%s\" for cap-%s", val, cap->name); -out: - g_free(val); } static void spapr_cap_get_pagesize(Object *obj, Visitor *v, const char *name, @@ -933,16 +930,13 @@ void spapr_caps_add_properties(SpaprMachineClass *smc) for (i = 0; i < ARRAY_SIZE(capability_table); i++) { SpaprCapabilityInfo *cap = &capability_table[i]; - char *name = g_strdup_printf("cap-%s", cap->name); - char *desc; + g_autofree char *name = g_strdup_printf("cap-%s", cap->name); + g_autofree char *desc = g_strdup_printf("%s", cap->description); object_class_property_add(klass, name, cap->type, cap->get, cap->set, NULL, cap); - desc = g_strdup_printf("%s", cap->description); object_class_property_set_description(klass, name, desc); - g_free(name); - g_free(desc); } } diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index f8ac0a10df..76bc5d42a0 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -519,8 +519,8 @@ static const VMStateDescription vmstate_spapr_drc = { static void drc_realize(DeviceState *d, Error **errp) { SpaprDrc *drc = SPAPR_DR_CONNECTOR(d); + g_autofree gchar *link_name = g_strdup_printf("%x", spapr_drc_index(drc)); Object *root_container; - gchar *link_name; const char *child_name; trace_spapr_drc_realize(spapr_drc_index(drc)); @@ -532,12 +532,10 @@ static void drc_realize(DeviceState *d, Error **errp) * existing in the composition tree */ root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); - link_name = g_strdup_printf("%x", spapr_drc_index(drc)); child_name = object_get_canonical_path_component(OBJECT(drc)); trace_spapr_drc_realize_child(spapr_drc_index(drc), child_name); object_property_add_alias(root_container, link_name, drc->owner, child_name); - g_free(link_name); vmstate_register(VMSTATE_IF(drc), spapr_drc_index(drc), &vmstate_spapr_drc, drc); trace_spapr_drc_realize_complete(spapr_drc_index(drc)); @@ -546,22 +544,20 @@ static void drc_realize(DeviceState *d, Error **errp) static void drc_unrealize(DeviceState *d) { SpaprDrc *drc = SPAPR_DR_CONNECTOR(d); + g_autofree gchar *name = g_strdup_printf("%x", spapr_drc_index(drc)); Object *root_container; - gchar *name; trace_spapr_drc_unrealize(spapr_drc_index(drc)); vmstate_unregister(VMSTATE_IF(drc), &vmstate_spapr_drc, drc); root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); - name = g_strdup_printf("%x", spapr_drc_index(drc)); object_property_del(root_container, name); - g_free(name); } SpaprDrc *spapr_dr_connector_new(Object *owner, const char *type, uint32_t id) { SpaprDrc *drc = SPAPR_DR_CONNECTOR(object_new(type)); - char *prop_name; + g_autofree char *prop_name = NULL; drc->id = id; drc->owner = owner; @@ -570,7 +566,6 @@ SpaprDrc *spapr_dr_connector_new(Object *owner, const char *type, object_property_add_child(owner, prop_name, OBJECT(drc)); object_unref(OBJECT(drc)); qdev_realize(DEVICE(drc), NULL, NULL); - g_free(prop_name); return drc; } @@ -803,11 +798,9 @@ static const TypeInfo spapr_drc_pmem_info = { SpaprDrc *spapr_drc_by_index(uint32_t index) { Object *obj; - gchar *name; - - name = g_strdup_printf("%s/%x", DRC_CONTAINER_PATH, index); + g_autofree gchar *name = g_strdup_printf("%s/%x", DRC_CONTAINER_PATH, + index); obj = object_resolve_path(name, NULL); - g_free(name); return !obj ? NULL : SPAPR_DR_CONNECTOR(obj); } @@ -841,8 +834,14 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask) ObjectProperty *prop; ObjectPropertyIterator iter; uint32_t drc_count = 0; - GArray *drc_indexes, *drc_power_domains; - GString *drc_names, *drc_types; + g_autoptr(GArray) drc_indexes = g_array_new(false, true, + sizeof(uint32_t)); + g_autoptr(GArray) drc_power_domains = g_array_new(false, true, + sizeof(uint32_t)); + g_autoptr(GString) drc_names = g_string_set_size(g_string_new(NULL), + sizeof(uint32_t)); + g_autoptr(GString) drc_types = g_string_set_size(g_string_new(NULL), + sizeof(uint32_t)); int ret; /* @@ -857,12 +856,8 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask) * reserve the space now and set the offsets accordingly so we * can fill them in later. */ - drc_indexes = g_array_new(false, true, sizeof(uint32_t)); drc_indexes = g_array_set_size(drc_indexes, 1); - drc_power_domains = g_array_new(false, true, sizeof(uint32_t)); drc_power_domains = g_array_set_size(drc_power_domains, 1); - drc_names = g_string_set_size(g_string_new(NULL), sizeof(uint32_t)); - drc_types = g_string_set_size(g_string_new(NULL), sizeof(uint32_t)); /* aliases for all DRConnector objects will be rooted in QOM * composition tree at DRC_CONTAINER_PATH @@ -874,7 +869,7 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask) Object *obj; SpaprDrc *drc; SpaprDrcClass *drck; - char *drc_name = NULL; + g_autofree char *drc_name = NULL; uint32_t drc_index, drc_power_domain; if (!strstart(prop->type, "link<", NULL)) { @@ -908,7 +903,6 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask) drc_name = spapr_drc_name(drc); drc_names = g_string_append(drc_names, drc_name); drc_names = g_string_insert_len(drc_names, -1, "\0", 1); - g_free(drc_name); /* ibm,drc-types */ drc_types = g_string_append(drc_types, drck->typename); @@ -928,7 +922,7 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask) drc_indexes->len * sizeof(uint32_t)); if (ret) { error_report("Couldn't create ibm,drc-indexes property"); - goto out; + return ret; } ret = fdt_setprop(fdt, offset, "ibm,drc-power-domains", @@ -936,29 +930,22 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask) drc_power_domains->len * sizeof(uint32_t)); if (ret) { error_report("Couldn't finalize ibm,drc-power-domains property"); - goto out; + return ret; } ret = fdt_setprop(fdt, offset, "ibm,drc-names", drc_names->str, drc_names->len); if (ret) { error_report("Couldn't finalize ibm,drc-names property"); - goto out; + return ret; } ret = fdt_setprop(fdt, offset, "ibm,drc-types", drc_types->str, drc_types->len); if (ret) { error_report("Couldn't finalize ibm,drc-types property"); - goto out; } -out: - g_array_free(drc_indexes, true); - g_array_free(drc_power_domains, true); - g_string_free(drc_names, true); - g_string_free(drc_types, true); - return ret; } diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c index e9ef7e7646..4f93bdefec 100644 --- a/hw/ppc/spapr_numa.c +++ b/hw/ppc/spapr_numa.c @@ -431,12 +431,14 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt, int max_distance_ref_points = get_max_dist_ref_points(spapr); int nb_numa_nodes = machine->numa_state->num_nodes; int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1; - uint32_t *int_buf, *cur_index, buf_len; - int ret, i; + g_autofree uint32_t *int_buf = NULL; + uint32_t *cur_index; + int i; /* ibm,associativity-lookup-arrays */ - buf_len = (nr_nodes * max_distance_ref_points + 2) * sizeof(uint32_t); - cur_index = int_buf = g_malloc0(buf_len); + int_buf = g_malloc0((nr_nodes * max_distance_ref_points + 2) * + sizeof(uint32_t)); + cur_index = int_buf; int_buf[0] = cpu_to_be32(nr_nodes); /* Number of entries per associativity list */ int_buf[1] = cpu_to_be32(max_distance_ref_points); @@ -451,11 +453,9 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt, sizeof(uint32_t) * max_distance_ref_points); cur_index += max_distance_ref_points; } - ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf, - (cur_index - int_buf) * sizeof(uint32_t)); - g_free(int_buf); - return ret; + return fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", + int_buf, (cur_index - int_buf) * sizeof(uint32_t)); } static void spapr_numa_FORM1_write_rtas_dt(SpaprMachineState *spapr, diff --git a/hw/ppc/spapr_pci_nvlink2.c b/hw/ppc/spapr_pci_nvlink2.c index 7fb0cf4d04..4678c79235 100644 --- a/hw/ppc/spapr_pci_nvlink2.c +++ b/hw/ppc/spapr_pci_nvlink2.c @@ -320,7 +320,7 @@ void spapr_phb_nvgpu_populate_dt(SpaprPhbState *sphb, void *fdt, int bus_off, void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt) { int i, j, linkidx, npuoff; - char *npuname; + g_autofree char *npuname = NULL; if (!sphb->nvgpus) { return; @@ -333,11 +333,10 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt) _FDT(fdt_setprop_cell(fdt, npuoff, "#size-cells", 0)); /* Advertise NPU as POWER9 so the guest can enable NPU2 contexts */ _FDT((fdt_setprop_string(fdt, npuoff, "compatible", "ibm,power9-npu"))); - g_free(npuname); for (i = 0, linkidx = 0; i < sphb->nvgpus->num; ++i) { for (j = 0; j < sphb->nvgpus->slots[i].linknum; ++j) { - char *linkname = g_strdup_printf("link@%d", linkidx); + g_autofree char *linkname = g_strdup_printf("link@%d", linkidx); int off = fdt_add_subnode(fdt, npuoff, linkname); _FDT(off); @@ -347,7 +346,6 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt) _FDT((fdt_setprop_cell(fdt, off, "phandle", PHANDLE_NVLINK(sphb, i, j)))); _FDT((fdt_setprop_cell(fdt, off, "ibm,npu-link-index", linkidx))); - g_free(linkname); ++linkidx; } } @@ -360,7 +358,8 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt) &error_abort); uint64_t size = object_property_get_uint(nv_mrobj, "size", NULL); uint64_t mem_reg[2] = { cpu_to_be64(nvslot->gpa), cpu_to_be64(size) }; - char *mem_name = g_strdup_printf("memory@%"PRIx64, nvslot->gpa); + g_autofree char *mem_name = g_strdup_printf("memory@%"PRIx64, + nvslot->gpa); int off = fdt_add_subnode(fdt, 0, mem_name); _FDT(off); @@ -378,7 +377,6 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt) sizeof(mem_reg)))); _FDT((fdt_setprop_cell(fdt, off, "phandle", PHANDLE_GPURAM(sphb, i)))); - g_free(mem_name); } } diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index b476382ae6..d7c04237fe 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -279,30 +279,29 @@ static void rtas_ibm_get_system_parameter(PowerPCCPU *cpu, switch (parameter) { case RTAS_SYSPARM_SPLPAR_CHARACTERISTICS: { - char *param_val = g_strdup_printf("MaxEntCap=%d," - "DesMem=%" PRIu64 "," - "DesProcs=%d," - "MaxPlatProcs=%d", - ms->smp.max_cpus, - ms->ram_size / MiB, - ms->smp.cpus, - ms->smp.max_cpus); + g_autofree char *param_val = g_strdup_printf("MaxEntCap=%d," + "DesMem=%" PRIu64 "," + "DesProcs=%d," + "MaxPlatProcs=%d", + ms->smp.max_cpus, + ms->ram_size / MiB, + ms->smp.cpus, + ms->smp.max_cpus); if (pcc->n_host_threads > 0) { - char *hostthr_val, *old = param_val; - /* * Add HostThrs property. This property is not present in PAPR but * is expected by some guests to communicate the number of physical * host threads per core on the system so that they can scale * information which varies based on the thread configuration. */ - hostthr_val = g_strdup_printf(",HostThrs=%d", pcc->n_host_threads); + g_autofree char *hostthr_val = g_strdup_printf(",HostThrs=%d", + pcc->n_host_threads); + char *old = param_val; + param_val = g_strconcat(param_val, hostthr_val, NULL); - g_free(hostthr_val); g_free(old); } ret = sysparm_st(buffer, length, param_val, strlen(param_val) + 1); - g_free(param_val); break; } case RTAS_SYSPARM_DIAGNOSTICS_RUN_MODE: { diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c index b975ed29ca..9d4fec2c04 100644 --- a/hw/ppc/spapr_vio.c +++ b/hw/ppc/spapr_vio.c @@ -726,7 +726,7 @@ void spapr_dt_vdevice(SpaprVioBus *bus, void *fdt) gchar *spapr_vio_stdout_path(SpaprVioBus *bus) { SpaprVioDevice *dev; - char *name, *path; + g_autofree char *name = NULL; dev = spapr_vty_get_default(bus); if (!dev) { @@ -734,8 +734,6 @@ gchar *spapr_vio_stdout_path(SpaprVioBus *bus) } name = spapr_vio_get_dev_name(DEVICE(dev)); - path = g_strdup_printf("/vdevice/%s", name); - g_free(name); - return path; + return g_strdup_printf("/vdevice/%s", name); } diff --git a/include/hw/pci-host/pnv_phb4.h b/include/hw/pci-host/pnv_phb4.h index 0c7635dec5..fbcf5bfb55 100644 --- a/include/hw/pci-host/pnv_phb4.h +++ b/include/hw/pci-host/pnv_phb4.h @@ -49,6 +49,7 @@ typedef struct PnvPhb4DMASpace { */ #define TYPE_PNV_PHB4_ROOT_BUS "pnv-phb4-root" #define TYPE_PNV_PHB4_ROOT_PORT "pnv-phb4-root-port" +#define TYPE_PNV_PHB5_ROOT_PORT "pnv-phb5-root-port" typedef struct PnvPHB4RootPort { PCIESlot parent_obj; @@ -206,4 +207,15 @@ struct PnvPhb4PecClass { const char *rp_model; }; +/* + * POWER10 definitions + */ + +#define PNV_PHB5_VERSION 0x000000a500000001ull +#define PNV_PHB5_DEVICE_ID 0x0652 + +#define TYPE_PNV_PHB5_PEC "pnv-phb5-pec" +#define PNV_PHB5_PEC(obj) \ + OBJECT_CHECK(PnvPhb4PecState, (obj), TYPE_PNV_PHB5_PEC) + #endif /* PCI_HOST_PNV_PHB4_H */ diff --git a/include/hw/pci-host/pnv_phb4_regs.h b/include/hw/pci-host/pnv_phb4_regs.h index 55df2c3e5e..4a0d3b28ef 100644 --- a/include/hw/pci-host/pnv_phb4_regs.h +++ b/include/hw/pci-host/pnv_phb4_regs.h @@ -220,11 +220,14 @@ #define PHB_PAPR_ERR_INJ_MASK_MMIO PPC_BITMASK(16, 63) #define PHB_ETU_ERR_SUMMARY 0x2c8 #define PHB_INT_NOTIFY_ADDR 0x300 +#define PHB_INT_NOTIFY_ADDR_64K PPC_BIT(1) /* P10 */ #define PHB_INT_NOTIFY_INDEX 0x308 /* Fundamental register set B */ #define PHB_VERSION 0x800 #define PHB_CTRLR 0x810 +#define PHB_CTRLR_IRQ_PQ_DISABLE PPC_BIT(9) /* P10 */ +#define PHB_CTRLR_IRQ_ABT_MODE PPC_BIT(10) /* P10 */ #define PHB_CTRLR_IRQ_PGSZ_64K PPC_BIT(11) #define PHB_CTRLR_IRQ_STORE_EOI PPC_BIT(12) #define PHB_CTRLR_MMIO_RD_STRICT PPC_BIT(13) diff --git a/include/hw/ppc/pnv.h b/include/hw/ppc/pnv.h index 0e9e16544f..1e34ddd502 100644 --- a/include/hw/ppc/pnv.h +++ b/include/hw/ppc/pnv.h @@ -125,10 +125,22 @@ struct Pnv10Chip { PnvChip parent_obj; /*< public >*/ + PnvXive2 xive; Pnv9Psi psi; PnvLpcController lpc; + PnvOCC occ; + PnvHomer homer; + + uint32_t nr_quads; + PnvQuad *quads; + +#define PNV10_CHIP_MAX_PEC 2 + PnvPhb4PecState pecs[PNV10_CHIP_MAX_PEC]; }; +#define PNV10_PIR2FUSEDCORE(pir) (((pir) >> 3) & 0xf) +#define PNV10_PIR2CHIP(pir) (((pir) >> 8) & 0x7f) + struct PnvChipClass { /*< private >*/ SysBusDeviceClass parent_class; @@ -329,10 +341,37 @@ void pnv_bmc_set_pnor(IPMIBmc *bmc, PnvPnor *pnor); #define PNV10_LPCM_SIZE 0x0000000100000000ull #define PNV10_LPCM_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006030000000000ull) +#define PNV10_XIVE2_IC_SIZE 0x0000000002000000ull +#define PNV10_XIVE2_IC_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006030200000000ull) + #define PNV10_PSIHB_ESB_SIZE 0x0000000000100000ull #define PNV10_PSIHB_ESB_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006030202000000ull) #define PNV10_PSIHB_SIZE 0x0000000000100000ull #define PNV10_PSIHB_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006030203000000ull) +#define PNV10_XIVE2_TM_SIZE 0x0000000000040000ull +#define PNV10_XIVE2_TM_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006030203180000ull) + +#define PNV10_XIVE2_NVC_SIZE 0x0000000008000000ull +#define PNV10_XIVE2_NVC_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006030208000000ull) + +#define PNV10_XIVE2_NVPG_SIZE 0x0000010000000000ull +#define PNV10_XIVE2_NVPG_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006040000000000ull) + +#define PNV10_XIVE2_ESB_SIZE 0x0000010000000000ull +#define PNV10_XIVE2_ESB_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006050000000000ull) + +#define PNV10_XIVE2_END_SIZE 0x0000020000000000ull +#define PNV10_XIVE2_END_BASE(chip) PNV10_CHIP_BASE(chip, 0x0006060000000000ull) + +#define PNV10_OCC_COMMON_AREA_SIZE 0x0000000000800000ull +#define PNV10_OCC_COMMON_AREA_BASE 0x300fff800000ull +#define PNV10_OCC_SENSOR_BASE(chip) (PNV10_OCC_COMMON_AREA_BASE + \ + PNV_OCC_SENSOR_DATA_BLOCK_BASE((chip)->chip_id)) + +#define PNV10_HOMER_SIZE 0x0000000000400000ull +#define PNV10_HOMER_BASE(chip) \ + (0x300ffd800000ll + ((uint64_t)(chip)->chip_id) * PNV10_HOMER_SIZE) + #endif /* PPC_PNV_H */ diff --git a/include/hw/ppc/pnv_homer.h b/include/hw/ppc/pnv_homer.h index 1889e3083c..07e8b19311 100644 --- a/include/hw/ppc/pnv_homer.h +++ b/include/hw/ppc/pnv_homer.h @@ -32,6 +32,9 @@ DECLARE_INSTANCE_CHECKER(PnvHomer, PNV8_HOMER, #define TYPE_PNV9_HOMER TYPE_PNV_HOMER "-POWER9" DECLARE_INSTANCE_CHECKER(PnvHomer, PNV9_HOMER, TYPE_PNV9_HOMER) +#define TYPE_PNV10_HOMER TYPE_PNV_HOMER "-POWER10" +DECLARE_INSTANCE_CHECKER(PnvHomer, PNV10_HOMER, + TYPE_PNV10_HOMER) struct PnvHomer { DeviceState parent; diff --git a/include/hw/ppc/pnv_occ.h b/include/hw/ppc/pnv_occ.h index b78185aeca..f982ba0024 100644 --- a/include/hw/ppc/pnv_occ.h +++ b/include/hw/ppc/pnv_occ.h @@ -32,6 +32,8 @@ DECLARE_INSTANCE_CHECKER(PnvOCC, PNV8_OCC, #define TYPE_PNV9_OCC TYPE_PNV_OCC "-POWER9" DECLARE_INSTANCE_CHECKER(PnvOCC, PNV9_OCC, TYPE_PNV9_OCC) +#define TYPE_PNV10_OCC TYPE_PNV_OCC "-POWER10" +DECLARE_INSTANCE_CHECKER(PnvOCC, PNV10_OCC, TYPE_PNV10_OCC) #define PNV_OCC_SENSOR_DATA_BLOCK_OFFSET 0x00580000 #define PNV_OCC_SENSOR_DATA_BLOCK_SIZE 0x00025800 diff --git a/include/hw/ppc/pnv_xive.h b/include/hw/ppc/pnv_xive.h index 7928e27963..b5d91505e5 100644 --- a/include/hw/ppc/pnv_xive.h +++ b/include/hw/ppc/pnv_xive.h @@ -12,6 +12,7 @@ #include "hw/ppc/xive.h" #include "qom/object.h" +#include "hw/ppc/xive2.h" struct PnvChip; @@ -95,4 +96,74 @@ struct PnvXiveClass { void pnv_xive_pic_print_info(PnvXive *xive, Monitor *mon); +/* + * XIVE2 interrupt controller (POWER10) + */ +#define TYPE_PNV_XIVE2 "pnv-xive2" +OBJECT_DECLARE_TYPE(PnvXive2, PnvXive2Class, PNV_XIVE2); + +typedef struct PnvXive2 { + Xive2Router parent_obj; + + /* Owning chip */ + struct PnvChip *chip; + + /* XSCOM addresses giving access to the controller registers */ + MemoryRegion xscom_regs; + + MemoryRegion ic_mmio; + MemoryRegion ic_mmios[8]; + MemoryRegion esb_mmio; + MemoryRegion end_mmio; + MemoryRegion nvc_mmio; + MemoryRegion nvpg_mmio; + MemoryRegion tm_mmio; + + /* Shortcut values for the Main MMIO regions */ + hwaddr ic_base; + uint32_t ic_shift; + hwaddr esb_base; + uint32_t esb_shift; + hwaddr end_base; + uint32_t end_shift; + hwaddr nvc_base; + uint32_t nvc_shift; + hwaddr nvpg_base; + uint32_t nvpg_shift; + hwaddr tm_base; + uint32_t tm_shift; + + /* Interrupt controller registers */ + uint64_t cq_regs[0x40]; + uint64_t vc_regs[0x100]; + uint64_t pc_regs[0x100]; + uint64_t tctxt_regs[0x30]; + + /* To change default behavior */ + uint64_t capabilities; + uint64_t config; + + /* Our XIVE source objects for IPIs and ENDs */ + XiveSource ipi_source; + Xive2EndSource end_source; + + /* + * Virtual Structure Descriptor tables + * These are in a SRAM protected by ECC. + */ + uint64_t vsds[9][XIVE_BLOCK_MAX]; + + /* Translation tables */ + uint64_t tables[8][XIVE_BLOCK_MAX]; + +} PnvXive2; + +typedef struct PnvXive2Class { + Xive2RouterClass parent_class; + + DeviceRealize parent_realize; +} PnvXive2Class; + +void pnv_xive2_pic_print_info(PnvXive2 *xive, Monitor *mon); + #endif /* PPC_PNV_XIVE_H */ diff --git a/include/hw/ppc/pnv_xscom.h b/include/hw/ppc/pnv_xscom.h index 2ff9f7a8d6..7c7440de0c 100644 --- a/include/hw/ppc/pnv_xscom.h +++ b/include/hw/ppc/pnv_xscom.h @@ -131,6 +131,21 @@ struct PnvXScomInterfaceClass { #define PNV10_XSCOM_PSIHB_BASE 0x3011D00 #define PNV10_XSCOM_PSIHB_SIZE 0x100 +#define PNV10_XSCOM_OCC_BASE PNV9_XSCOM_OCC_BASE +#define PNV10_XSCOM_OCC_SIZE PNV9_XSCOM_OCC_SIZE + +#define PNV10_XSCOM_PBA_BASE 0x01010CDA +#define PNV10_XSCOM_PBA_SIZE 0x40 + +#define PNV10_XSCOM_XIVE2_BASE 0x2010800 +#define PNV10_XSCOM_XIVE2_SIZE 0x400 + +#define PNV10_XSCOM_PEC_NEST_BASE 0x3011800 /* index goes downwards ... */ +#define PNV10_XSCOM_PEC_NEST_SIZE 0x100 + +#define PNV10_XSCOM_PEC_PCI_BASE 0x8010800 /* index goes upwards ... */ +#define PNV10_XSCOM_PEC_PCI_SIZE 0x200 + void pnv_xscom_realize(PnvChip *chip, uint64_t size, Error **errp); int pnv_dt_xscom(PnvChip *chip, void *fdt, int root_offset, uint64_t xscom_base, uint64_t xscom_size, diff --git a/include/hw/ppc/xive.h b/include/hw/ppc/xive.h index b8ab0bf749..126e4e2c3a 100644 --- a/include/hw/ppc/xive.h +++ b/include/hw/ppc/xive.h @@ -160,7 +160,7 @@ DECLARE_CLASS_CHECKERS(XiveNotifierClass, XIVE_NOTIFIER, struct XiveNotifierClass { InterfaceClass parent; - void (*notify)(XiveNotifier *xn, uint32_t lisn); + void (*notify)(XiveNotifier *xn, uint32_t lisn, bool pq_checked); }; /* @@ -176,6 +176,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(XiveSource, XIVE_SOURCE) */ #define XIVE_SRC_H_INT_ESB 0x1 /* ESB managed with hcall H_INT_ESB */ #define XIVE_SRC_STORE_EOI 0x2 /* Store EOI supported */ +#define XIVE_SRC_PQ_DISABLE 0x4 /* Disable check on the PQ state bits */ struct XiveSource { DeviceState parent; @@ -278,6 +279,7 @@ uint8_t xive_esb_set(uint8_t *pq, uint8_t value); #define XIVE_ESB_STORE_EOI 0x400 /* Store */ #define XIVE_ESB_LOAD_EOI 0x000 /* Load */ #define XIVE_ESB_GET 0x800 /* Load */ +#define XIVE_ESB_INJECT 0x800 /* Store */ #define XIVE_ESB_SET_PQ_00 0xc00 /* Load */ #define XIVE_ESB_SET_PQ_01 0xd00 /* Load */ #define XIVE_ESB_SET_PQ_10 0xe00 /* Load */ @@ -385,6 +387,10 @@ struct XiveRouterClass { /* XIVE table accessors */ int (*get_eas)(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx, XiveEAS *eas); + int (*get_pq)(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq); + int (*set_pq)(XiveRouter *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq); int (*get_end)(XiveRouter *xrtr, uint8_t end_blk, uint32_t end_idx, XiveEND *end); int (*write_end)(XiveRouter *xrtr, uint8_t end_blk, uint32_t end_idx, @@ -406,7 +412,7 @@ int xive_router_get_nvt(XiveRouter *xrtr, uint8_t nvt_blk, uint32_t nvt_idx, XiveNVT *nvt); int xive_router_write_nvt(XiveRouter *xrtr, uint8_t nvt_blk, uint32_t nvt_idx, XiveNVT *nvt, uint8_t word_number); -void xive_router_notify(XiveNotifier *xn, uint32_t lisn); +void xive_router_notify(XiveNotifier *xn, uint32_t lisn, bool pq_checked); /* * XIVE Presenter diff --git a/include/hw/ppc/xive2.h b/include/hw/ppc/xive2.h new file mode 100644 index 0000000000..e9e3ea135e --- /dev/null +++ b/include/hw/ppc/xive2.h @@ -0,0 +1,109 @@ +/* + * QEMU PowerPC XIVE2 interrupt controller model (POWER10) + * + * Copyright (c) 2019-2022, IBM Corporation. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + * + */ + +#ifndef PPC_XIVE2_H +#define PPC_XIVE2_H + +#include "hw/ppc/xive2_regs.h" + +/* + * XIVE2 Router (POWER10) + */ +typedef struct Xive2Router { + SysBusDevice parent; + + XiveFabric *xfb; +} Xive2Router; + +#define TYPE_XIVE2_ROUTER "xive2-router" +OBJECT_DECLARE_TYPE(Xive2Router, Xive2RouterClass, XIVE2_ROUTER); + +/* + * Configuration flags + */ + +#define XIVE2_GEN1_TIMA_OS 0x00000001 +#define XIVE2_VP_SAVE_RESTORE 0x00000002 +#define XIVE2_THREADID_8BITS 0x00000004 + +typedef struct Xive2RouterClass { + SysBusDeviceClass parent; + + /* XIVE table accessors */ + int (*get_eas)(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + Xive2Eas *eas); + int (*get_pq)(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq); + int (*set_pq)(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + uint8_t *pq); + int (*get_end)(Xive2Router *xrtr, uint8_t end_blk, uint32_t end_idx, + Xive2End *end); + int (*write_end)(Xive2Router *xrtr, uint8_t end_blk, uint32_t end_idx, + Xive2End *end, uint8_t word_number); + int (*get_nvp)(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp); + int (*write_nvp)(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp, uint8_t word_number); + uint8_t (*get_block_id)(Xive2Router *xrtr); + uint32_t (*get_config)(Xive2Router *xrtr); +} Xive2RouterClass; + +int xive2_router_get_eas(Xive2Router *xrtr, uint8_t eas_blk, uint32_t eas_idx, + Xive2Eas *eas); +int xive2_router_get_end(Xive2Router *xrtr, uint8_t end_blk, uint32_t end_idx, + Xive2End *end); +int xive2_router_write_end(Xive2Router *xrtr, uint8_t end_blk, uint32_t end_idx, + Xive2End *end, uint8_t word_number); +int xive2_router_get_nvp(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp); +int xive2_router_write_nvp(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, + Xive2Nvp *nvp, uint8_t word_number); +uint32_t xive2_router_get_config(Xive2Router *xrtr); + +void xive2_router_notify(XiveNotifier *xn, uint32_t lisn, bool pq_checked); + +/* + * XIVE2 Presenter (POWER10) + */ + +int xive2_presenter_tctx_match(XivePresenter *xptr, XiveTCTX *tctx, + uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool cam_ignore, uint32_t logic_serv); + +/* + * XIVE2 END ESBs (POWER10) + */ + +#define TYPE_XIVE2_END_SOURCE "xive2-end-source" +OBJECT_DECLARE_SIMPLE_TYPE(Xive2EndSource, XIVE2_END_SOURCE) + +typedef struct Xive2EndSource { + DeviceState parent; + + uint32_t nr_ends; + + /* ESB memory region */ + uint32_t esb_shift; + MemoryRegion esb_mmio; + + Xive2Router *xrtr; +} Xive2EndSource; + +/* + * XIVE2 Thread Interrupt Management Area (POWER10) + */ + +void xive2_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, + uint64_t value, unsigned size); +uint64_t xive2_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size); + +#endif /* PPC_XIVE2_H */ diff --git a/include/hw/ppc/xive2_regs.h b/include/hw/ppc/xive2_regs.h new file mode 100644 index 0000000000..14605bd458 --- /dev/null +++ b/include/hw/ppc/xive2_regs.h @@ -0,0 +1,210 @@ +/* + * QEMU PowerPC XIVE2 internal structure definitions (POWER10) + * + * Copyright (c) 2019-2022, IBM Corporation. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ + +#ifndef PPC_XIVE2_REGS_H +#define PPC_XIVE2_REGS_H + +/* + * Thread Interrupt Management Area (TIMA) + * + * In Gen1 mode (P9 compat mode) word 2 is the same. However in Gen2 + * mode (P10), the CAM line is slightly different as the VP space was + * increased. + */ +#define TM2_QW0W2_VU PPC_BIT32(0) +#define TM2_QW0W2_LOGIC_SERV PPC_BITMASK32(4, 31) +#define TM2_QW1W2_VO PPC_BIT32(0) +#define TM2_QW1W2_HO PPC_BIT32(1) +#define TM2_QW1W2_OS_CAM PPC_BITMASK32(4, 31) +#define TM2_QW2W2_VP PPC_BIT32(0) +#define TM2_QW2W2_HP PPC_BIT32(1) +#define TM2_QW2W2_POOL_CAM PPC_BITMASK32(4, 31) +#define TM2_QW3W2_VT PPC_BIT32(0) +#define TM2_QW3W2_HT PPC_BIT32(1) +#define TM2_QW3W2_LP PPC_BIT32(6) +#define TM2_QW3W2_LE PPC_BIT32(7) + +/* + * Event Assignment Structure (EAS) + */ + +typedef struct Xive2Eas { + uint64_t w; +#define EAS2_VALID PPC_BIT(0) +#define EAS2_END_BLOCK PPC_BITMASK(4, 7) /* Destination EQ block# */ +#define EAS2_END_INDEX PPC_BITMASK(8, 31) /* Destination EQ index */ +#define EAS2_MASKED PPC_BIT(32) /* Masked */ +#define EAS2_END_DATA PPC_BITMASK(33, 63) /* written to the EQ */ +} Xive2Eas; + +#define xive2_eas_is_valid(eas) (be64_to_cpu((eas)->w) & EAS2_VALID) +#define xive2_eas_is_masked(eas) (be64_to_cpu((eas)->w) & EAS2_MASKED) + +void xive2_eas_pic_print_info(Xive2Eas *eas, uint32_t lisn, Monitor *mon); + +/* + * Event Notifification Descriptor (END) + */ + +typedef struct Xive2End { + uint32_t w0; +#define END2_W0_VALID PPC_BIT32(0) /* "v" bit */ +#define END2_W0_ENQUEUE PPC_BIT32(5) /* "q" bit */ +#define END2_W0_UCOND_NOTIFY PPC_BIT32(6) /* "n" bit */ +#define END2_W0_SILENT_ESCALATE PPC_BIT32(7) /* "s" bit */ +#define END2_W0_BACKLOG PPC_BIT32(8) /* "b" bit */ +#define END2_W0_PRECL_ESC_CTL PPC_BIT32(9) /* "p" bit */ +#define END2_W0_UNCOND_ESCALATE PPC_BIT32(10) /* "u" bit */ +#define END2_W0_ESCALATE_CTL PPC_BIT32(11) /* "e" bit */ +#define END2_W0_ADAPTIVE_ESC PPC_BIT32(12) /* "a" bit */ +#define END2_W0_ESCALATE_END PPC_BIT32(13) /* "N" bit */ +#define END2_W0_FIRMWARE1 PPC_BIT32(16) /* Owned by FW */ +#define END2_W0_FIRMWARE2 PPC_BIT32(17) /* Owned by FW */ +#define END2_W0_AEC_SIZE PPC_BITMASK32(18, 19) +#define END2_W0_AEG_SIZE PPC_BITMASK32(20, 23) +#define END2_W0_EQ_VG_PREDICT PPC_BITMASK32(24, 31) /* Owned by HW */ + uint32_t w1; +#define END2_W1_ESn PPC_BITMASK32(0, 1) +#define END2_W1_ESn_P PPC_BIT32(0) +#define END2_W1_ESn_Q PPC_BIT32(1) +#define END2_W1_ESe PPC_BITMASK32(2, 3) +#define END2_W1_ESe_P PPC_BIT32(2) +#define END2_W1_ESe_Q PPC_BIT32(3) +#define END2_W1_GEN_FLIPPED PPC_BIT32(8) +#define END2_W1_GENERATION PPC_BIT32(9) +#define END2_W1_PAGE_OFF PPC_BITMASK32(10, 31) + uint32_t w2; +#define END2_W2_RESERVED PPC_BITMASK32(4, 7) +#define END2_W2_EQ_ADDR_HI PPC_BITMASK32(8, 31) + uint32_t w3; +#define END2_W3_EQ_ADDR_LO PPC_BITMASK32(0, 24) +#define END2_W3_QSIZE PPC_BITMASK32(28, 31) + uint32_t w4; +#define END2_W4_END_BLOCK PPC_BITMASK32(4, 7) +#define END2_W4_ESC_END_INDEX PPC_BITMASK32(8, 31) +#define END2_W4_ESB_BLOCK PPC_BITMASK32(0, 3) +#define END2_W4_ESC_ESB_INDEX PPC_BITMASK32(4, 31) + uint32_t w5; +#define END2_W5_ESC_END_DATA PPC_BITMASK32(1, 31) + uint32_t w6; +#define END2_W6_FORMAT_BIT PPC_BIT32(0) +#define END2_W6_IGNORE PPC_BIT32(1) +#define END2_W6_VP_BLOCK PPC_BITMASK32(4, 7) +#define END2_W6_VP_OFFSET PPC_BITMASK32(8, 31) +#define END2_W6_VP_OFFSET_GEN1 PPC_BITMASK32(13, 31) + uint32_t w7; +#define END2_W7_TOPO PPC_BITMASK32(0, 3) /* Owned by HW */ +#define END2_W7_F0_PRIORITY PPC_BITMASK32(8, 15) +#define END2_W7_F1_LOG_SERVER_ID PPC_BITMASK32(4, 31) +} Xive2End; + +#define xive2_end_is_valid(end) (be32_to_cpu((end)->w0) & END2_W0_VALID) +#define xive2_end_is_enqueue(end) (be32_to_cpu((end)->w0) & END2_W0_ENQUEUE) +#define xive2_end_is_notify(end) \ + (be32_to_cpu((end)->w0) & END2_W0_UCOND_NOTIFY) +#define xive2_end_is_backlog(end) (be32_to_cpu((end)->w0) & END2_W0_BACKLOG) +#define xive2_end_is_escalate(end) \ + (be32_to_cpu((end)->w0) & END2_W0_ESCALATE_CTL) +#define xive2_end_is_uncond_escalation(end) \ + (be32_to_cpu((end)->w0) & END2_W0_UNCOND_ESCALATE) +#define xive2_end_is_silent_escalation(end) \ + (be32_to_cpu((end)->w0) & END2_W0_SILENT_ESCALATE) +#define xive2_end_is_escalate_end(end) \ + (be32_to_cpu((end)->w0) & END2_W0_ESCALATE_END) +#define xive2_end_is_firmware1(end) \ + (be32_to_cpu((end)->w0) & END2_W0_FIRMWARE1) +#define xive2_end_is_firmware2(end) \ + (be32_to_cpu((end)->w0) & END2_W0_FIRMWARE2) + +static inline uint64_t xive2_end_qaddr(Xive2End *end) +{ + return ((uint64_t) be32_to_cpu(end->w2) & END2_W2_EQ_ADDR_HI) << 32 | + (be32_to_cpu(end->w3) & END2_W3_EQ_ADDR_LO); +} + +void xive2_end_pic_print_info(Xive2End *end, uint32_t end_idx, Monitor *mon); +void xive2_end_queue_pic_print_info(Xive2End *end, uint32_t width, + Monitor *mon); +void xive2_end_eas_pic_print_info(Xive2End *end, uint32_t end_idx, + Monitor *mon); + +/* + * Notification Virtual Processor (NVP) + */ +typedef struct Xive2Nvp { + uint32_t w0; +#define NVP2_W0_VALID PPC_BIT32(0) +#define NVP2_W0_HW PPC_BIT32(7) +#define NVP2_W0_ESC_END PPC_BIT32(25) /* 'N' bit 0:ESB 1:END */ + uint32_t w1; +#define NVP2_W1_CO PPC_BIT32(13) +#define NVP2_W1_CO_PRIV PPC_BITMASK32(14, 15) +#define NVP2_W1_CO_THRID_VALID PPC_BIT32(16) +#define NVP2_W1_CO_THRID PPC_BITMASK32(17, 31) + uint32_t w2; +#define NVP2_W2_CPPR PPC_BITMASK32(0, 7) +#define NVP2_W2_IPB PPC_BITMASK32(8, 15) +#define NVP2_W2_LSMFB PPC_BITMASK32(16, 23) + uint32_t w3; + uint32_t w4; +#define NVP2_W4_ESC_ESB_BLOCK PPC_BITMASK32(0, 3) /* N:0 */ +#define NVP2_W4_ESC_ESB_INDEX PPC_BITMASK32(4, 31) /* N:0 */ +#define NVP2_W4_ESC_END_BLOCK PPC_BITMASK32(4, 7) /* N:1 */ +#define NVP2_W4_ESC_END_INDEX PPC_BITMASK32(8, 31) /* N:1 */ + uint32_t w5; +#define NVP2_W5_PSIZE PPC_BITMASK32(0, 1) +#define NVP2_W5_VP_END_BLOCK PPC_BITMASK32(4, 7) +#define NVP2_W5_VP_END_INDEX PPC_BITMASK32(8, 31) + uint32_t w6; + uint32_t w7; +} Xive2Nvp; + +#define xive2_nvp_is_valid(nvp) (be32_to_cpu((nvp)->w0) & NVP2_W0_VALID) +#define xive2_nvp_is_hw(nvp) (be32_to_cpu((nvp)->w0) & NVP2_W0_HW) +#define xive2_nvp_is_co(nvp) (be32_to_cpu((nvp)->w1) & NVP2_W1_CO) + +/* + * The VP number space in a block is defined by the END2_W6_VP_OFFSET + * field of the XIVE END. When running in Gen1 mode (P9 compat mode), + * the VP space is reduced to (1 << 19) VPs per block + */ +#define XIVE2_NVP_SHIFT 24 +#define XIVE2_NVP_COUNT (1 << XIVE2_NVP_SHIFT) + +static inline uint32_t xive2_nvp_cam_line(uint8_t nvp_blk, uint32_t nvp_idx) +{ + return (nvp_blk << XIVE2_NVP_SHIFT) | nvp_idx; +} + +static inline uint32_t xive2_nvp_idx(uint32_t cam_line) +{ + return cam_line & ((1 << XIVE2_NVP_SHIFT) - 1); +} + +static inline uint32_t xive2_nvp_blk(uint32_t cam_line) +{ + return (cam_line >> XIVE2_NVP_SHIFT) & 0xf; +} + +/* + * Notification Virtual Group or Crowd (NVG/NVC) + */ +typedef struct Xive2Nvgc { + uint32_t w0; +#define NVGC2_W0_VALID PPC_BIT32(0) + uint32_t w1; + uint32_t w2; + uint32_t w3; + uint32_t w4; + uint32_t w5; + uint32_t w6; + uint32_t w7; +} Xive2Nvgc; + +#endif /* PPC_XIVE2_REGS_H */ diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h index da55fed870..28cafbcc5c 100644 --- a/include/tcg/tcg-op-gvec.h +++ b/include/tcg/tcg-op-gvec.h @@ -218,6 +218,25 @@ typedef struct { bool write_aofs; } GVecGen4; +typedef struct { + /* + * Expand inline as a 64-bit or 32-bit integer. Only one of these will be + * non-NULL. + */ + void (*fni8)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, int64_t); + void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32, int32_t); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, TCGv_vec, int64_t); + /* Expand out-of-line helper w/descriptor, data in descriptor. */ + gen_helper_gvec_4 *fno; + /* The optional opcodes, if any, utilized by .fniv. */ + const TCGOpcode *opt_opc; + /* The vector element size, if applicable. */ + uint8_t vece; + /* Prefer i64 to v64. */ + bool prefer_i64; +} GVecGen4i; + void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz, const GVecGen2 *); void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz, @@ -231,6 +250,9 @@ void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, const GVecGen3i *); void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, uint32_t oprsz, uint32_t maxsz, const GVecGen4 *); +void tcg_gen_gvec_4i(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, + uint32_t oprsz, uint32_t maxsz, int64_t c, + const GVecGen4i *); /* Expand a specific vector operation. */ diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 5b01d409b3..1b687521c7 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -127,8 +127,10 @@ enum { /* ISA 3.00 additions */ POWERPC_EXCP_HVIRT = 101, POWERPC_EXCP_SYSCALL_VECTORED = 102, /* scv exception */ + POWERPC_EXCP_PERFM_EBB = 103, /* Performance Monitor EBB Exception */ + POWERPC_EXCP_EXTERNAL_EBB = 104, /* External EBB Exception */ /* EOL */ - POWERPC_EXCP_NB = 103, + POWERPC_EXCP_NB = 105, /* QEMU exceptions: special cases we want to stop translation */ POWERPC_EXCP_SYSCALL_USER = 0x203, /* System call in user mode only */ }; @@ -2434,6 +2436,7 @@ enum { PPC_INTERRUPT_HMI, /* Hypervisor Maintenance interrupt */ PPC_INTERRUPT_HDOORBELL, /* Hypervisor Doorbell interrupt */ PPC_INTERRUPT_HVIRT, /* Hypervisor virtualization interrupt */ + PPC_INTERRUPT_EBB, /* Event-based Branch exception */ }; /* Processor Compatibility mask (PCR) */ @@ -2499,6 +2502,11 @@ void QEMU_NORETURN raise_exception_err(CPUPPCState *env, uint32_t exception, void QEMU_NORETURN raise_exception_err_ra(CPUPPCState *env, uint32_t exception, uint32_t error_code, uintptr_t raddr); +/* PERFM EBB helper*/ +#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY) +void raise_ebb_perfm_exception(CPUPPCState *env); +#endif + #if !defined(CONFIG_USER_ONLY) static inline int booke206_tlbm_id(CPUPPCState *env, ppcmas_tlb_t *tlbm) { diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index 61d36b11a0..073fd10168 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -2060,6 +2060,10 @@ static void init_excp_POWER8(CPUPPCState *env) env->excp_vectors[POWERPC_EXCP_FU] = 0x00000F60; env->excp_vectors[POWERPC_EXCP_HV_FU] = 0x00000F80; env->excp_vectors[POWERPC_EXCP_SDOOR_HV] = 0x00000E80; + + /* Userland exceptions without vector value in PowerISA v3.1 */ + env->excp_vectors[POWERPC_EXCP_PERFM_EBB] = 0x0; + env->excp_vectors[POWERPC_EXCP_EXTERNAL_EBB] = 0x0; #endif } @@ -5698,12 +5702,10 @@ static void register_power9_mmu_sprs(CPUPPCState *env) */ static void init_tcg_pmu_power8(CPUPPCState *env) { -#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY) /* Init PMU overflow timers */ - if (!kvm_enabled()) { + if (tcg_enabled()) { cpu_ppc_pmu_init(env); } -#endif } static void init_proc_book3s_common(CPUPPCState *env) @@ -7167,14 +7169,14 @@ static void ppc_cpu_reset(DeviceState *dev) #if !defined(CONFIG_USER_ONLY) env->nip = env->hreset_vector | env->excp_prefix; -#if defined(CONFIG_TCG) - if (env->mmu_model != POWERPC_MMU_REAL) { - ppc_tlb_invalidate_all(env); + + if (tcg_enabled()) { + if (env->mmu_model != POWERPC_MMU_REAL) { + ppc_tlb_invalidate_all(env); + } + pmu_update_summaries(env); } -#endif /* CONFIG_TCG */ #endif - - pmu_update_summaries(env); hreg_compute_hflags(env); env->reserve_addr = (target_ulong)-1ULL; /* Be sure no exception or interrupt is pending */ diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c index 6538c56ab0..d3e2cfcd71 100644 --- a/target/ppc/excp_helper.c +++ b/target/ppc/excp_helper.c @@ -1554,6 +1554,21 @@ static void powerpc_excp_books(PowerPCCPU *cpu, int excp) new_msr |= (target_ulong)MSR_HVB; new_msr |= env->msr & ((target_ulong)1 << MSR_RI); break; + case POWERPC_EXCP_PERFM_EBB: /* Performance Monitor EBB Exception */ + case POWERPC_EXCP_EXTERNAL_EBB: /* External EBB Exception */ + env->spr[SPR_BESCR] &= ~BESCR_GE; + + /* + * Save NIP for rfebb insn in SPR_EBBRR. Next nip is + * stored in the EBB Handler SPR_EBBHR. + */ + env->spr[SPR_EBBRR] = env->nip; + powerpc_set_excp_state(cpu, env->spr[SPR_EBBHR], env->msr); + + /* + * This exception is handled in userspace. No need to proceed. + */ + return; case POWERPC_EXCP_THERM: /* Thermal interrupt */ case POWERPC_EXCP_PERFM: /* Embedded performance monitor interrupt */ case POWERPC_EXCP_VPUA: /* Vector assist exception */ @@ -1797,6 +1812,24 @@ static void ppc_hw_interrupt(CPUPPCState *env) powerpc_excp(cpu, POWERPC_EXCP_THERM); return; } + /* EBB exception */ + if (env->pending_interrupts & (1 << PPC_INTERRUPT_EBB)) { + /* + * EBB exception must be taken in problem state and + * with BESCR_GE set. + */ + if (msr_pr == 1 && env->spr[SPR_BESCR] & BESCR_GE) { + env->pending_interrupts &= ~(1 << PPC_INTERRUPT_EBB); + + if (env->spr[SPR_BESCR] & BESCR_PMEO) { + powerpc_excp(cpu, POWERPC_EXCP_PERFM_EBB); + } else if (env->spr[SPR_BESCR] & BESCR_EEO) { + powerpc_excp(cpu, POWERPC_EXCP_EXTERNAL_EBB); + } + + return; + } + } } if (env->resume_as_sreset) { @@ -2033,6 +2066,54 @@ void helper_rfebb(CPUPPCState *env, target_ulong s) env->spr[SPR_BESCR] &= ~BESCR_GE; } } + +/* + * Triggers or queues an 'ebb_excp' EBB exception. All checks + * but FSCR, HFSCR and msr_pr must be done beforehand. + * + * PowerISA v3.1 isn't clear about whether an EBB should be + * postponed or cancelled if the EBB facility is unavailable. + * Our assumption here is that the EBB is cancelled if both + * FSCR and HFSCR EBB facilities aren't available. + */ +static void do_ebb(CPUPPCState *env, int ebb_excp) +{ + PowerPCCPU *cpu = env_archcpu(env); + CPUState *cs = CPU(cpu); + + /* + * FSCR_EBB and FSCR_IC_EBB are the same bits used with + * HFSCR. + */ + helper_fscr_facility_check(env, FSCR_EBB, 0, FSCR_IC_EBB); + helper_hfscr_facility_check(env, FSCR_EBB, "EBB", FSCR_IC_EBB); + + if (ebb_excp == POWERPC_EXCP_PERFM_EBB) { + env->spr[SPR_BESCR] |= BESCR_PMEO; + } else if (ebb_excp == POWERPC_EXCP_EXTERNAL_EBB) { + env->spr[SPR_BESCR] |= BESCR_EEO; + } + + if (msr_pr == 1) { + powerpc_excp(cpu, ebb_excp); + } else { + env->pending_interrupts |= 1 << PPC_INTERRUPT_EBB; + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } +} + +void raise_ebb_perfm_exception(CPUPPCState *env) +{ + bool perfm_ebb_enabled = env->spr[SPR_POWER_MMCR0] & MMCR0_EBE && + env->spr[SPR_BESCR] & BESCR_PME && + env->spr[SPR_BESCR] & BESCR_GE; + + if (!perfm_ebb_enabled) { + return; + } + + do_ebb(env, POWERPC_EXCP_PERFM_EBB); +} #endif /*****************************************************************************/ diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index bd76bee7f1..8f970288f5 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -2156,10 +2156,11 @@ VSX_TSQRT(xvtsqrtsp, 4, float32, VsrW(i), -126, 23) * maddflgs - flags for the float*muladd routine that control the * various forms (madd, msub, nmadd, nmsub) * sfprf - set FPRF + * r2sp - round intermediate double precision result to single precision */ #define VSX_MADD(op, nels, tp, fld, maddflgs, sfprf, r2sp) \ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \ - ppc_vsr_t *xa, ppc_vsr_t *b, ppc_vsr_t *c) \ + ppc_vsr_t *s1, ppc_vsr_t *s2, ppc_vsr_t *s3) \ { \ ppc_vsr_t t = *xt; \ int i; \ @@ -2175,12 +2176,12 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \ * result to odd. \ */ \ set_float_rounding_mode(float_round_to_zero, &tstat); \ - t.fld = tp##_muladd(xa->fld, b->fld, c->fld, \ + t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld, \ maddflgs, &tstat); \ t.fld |= (get_float_exception_flags(&tstat) & \ float_flag_inexact) != 0; \ } else { \ - t.fld = tp##_muladd(xa->fld, b->fld, c->fld, \ + t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld, \ maddflgs, &tstat); \ } \ env->fp_status.float_exception_flags |= tstat.float_exception_flags; \ @@ -2202,14 +2203,14 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \ do_float_check_status(env, GETPC()); \ } -VSX_MADD(xsmadddp, 1, float64, VsrD(0), MADD_FLGS, 1, 0) -VSX_MADD(xsmsubdp, 1, float64, VsrD(0), MSUB_FLGS, 1, 0) -VSX_MADD(xsnmadddp, 1, float64, VsrD(0), NMADD_FLGS, 1, 0) -VSX_MADD(xsnmsubdp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 0) -VSX_MADD(xsmaddsp, 1, float64, VsrD(0), MADD_FLGS, 1, 1) -VSX_MADD(xsmsubsp, 1, float64, VsrD(0), MSUB_FLGS, 1, 1) -VSX_MADD(xsnmaddsp, 1, float64, VsrD(0), NMADD_FLGS, 1, 1) -VSX_MADD(xsnmsubsp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1) +VSX_MADD(XSMADDDP, 1, float64, VsrD(0), MADD_FLGS, 1, 0) +VSX_MADD(XSMSUBDP, 1, float64, VsrD(0), MSUB_FLGS, 1, 0) +VSX_MADD(XSNMADDDP, 1, float64, VsrD(0), NMADD_FLGS, 1, 0) +VSX_MADD(XSNMSUBDP, 1, float64, VsrD(0), NMSUB_FLGS, 1, 0) +VSX_MADD(XSMADDSP, 1, float64, VsrD(0), MADD_FLGS, 1, 1) +VSX_MADD(XSMSUBSP, 1, float64, VsrD(0), MSUB_FLGS, 1, 1) +VSX_MADD(XSNMADDSP, 1, float64, VsrD(0), NMADD_FLGS, 1, 1) +VSX_MADD(XSNMSUBSP, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1) VSX_MADD(xvmadddp, 2, float64, VsrD(i), MADD_FLGS, 0, 0) VSX_MADD(xvmsubdp, 2, float64, VsrD(i), MSUB_FLGS, 0, 0) @@ -2222,55 +2223,93 @@ VSX_MADD(xvnmaddsp, 4, float32, VsrW(i), NMADD_FLGS, 0, 0) VSX_MADD(xvnmsubsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0) /* - * VSX_SCALAR_CMP_DP - VSX scalar floating point compare double precision + * VSX_MADDQ - VSX floating point quad-precision muliply/add * op - instruction mnemonic + * maddflgs - flags for the float*muladd routine that control the + * various forms (madd, msub, nmadd, nmsub) + * ro - round to odd + */ +#define VSX_MADDQ(op, maddflgs, ro) \ +void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *s1, ppc_vsr_t *s2,\ + ppc_vsr_t *s3) \ +{ \ + ppc_vsr_t t = *xt; \ + \ + helper_reset_fpstatus(env); \ + \ + float_status tstat = env->fp_status; \ + set_float_exception_flags(0, &tstat); \ + if (ro) { \ + tstat.float_rounding_mode = float_round_to_odd; \ + } \ + t.f128 = float128_muladd(s1->f128, s3->f128, s2->f128, maddflgs, &tstat); \ + env->fp_status.float_exception_flags |= tstat.float_exception_flags; \ + \ + if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \ + float_invalid_op_madd(env, tstat.float_exception_flags, \ + false, GETPC()); \ + } \ + \ + helper_compute_fprf_float128(env, t.f128); \ + *xt = t; \ + do_float_check_status(env, GETPC()); \ +} + +VSX_MADDQ(XSMADDQP, MADD_FLGS, 0) +VSX_MADDQ(XSMADDQPO, MADD_FLGS, 1) +VSX_MADDQ(XSMSUBQP, MSUB_FLGS, 0) +VSX_MADDQ(XSMSUBQPO, MSUB_FLGS, 1) +VSX_MADDQ(XSNMADDQP, NMADD_FLGS, 0) +VSX_MADDQ(XSNMADDQPO, NMADD_FLGS, 1) +VSX_MADDQ(XSNMSUBQP, NMSUB_FLGS, 0) +VSX_MADDQ(XSNMSUBQPO, NMSUB_FLGS, 0) + +/* + * VSX_SCALAR_CMP - VSX scalar floating point compare + * op - instruction mnemonic + * tp - type * cmp - comparison operation - * exp - expected result of comparison + * fld - vsr_t field * svxvc - set VXVC bit */ -#define VSX_SCALAR_CMP_DP(op, cmp, exp, svxvc) \ -void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \ - ppc_vsr_t *xa, ppc_vsr_t *xb) \ +#define VSX_SCALAR_CMP(op, tp, cmp, fld, svxvc) \ + void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \ + ppc_vsr_t *xa, ppc_vsr_t *xb) \ { \ - ppc_vsr_t t = *xt; \ - bool vxsnan_flag = false, vxvc_flag = false, vex_flag = false; \ + int flags; \ + bool r, vxvc; \ \ - if (float64_is_signaling_nan(xa->VsrD(0), &env->fp_status) || \ - float64_is_signaling_nan(xb->VsrD(0), &env->fp_status)) { \ - vxsnan_flag = true; \ - if (fpscr_ve == 0 && svxvc) { \ - vxvc_flag = true; \ - } \ - } else if (svxvc) { \ - vxvc_flag = float64_is_quiet_nan(xa->VsrD(0), &env->fp_status) || \ - float64_is_quiet_nan(xb->VsrD(0), &env->fp_status); \ - } \ - if (vxsnan_flag) { \ - float_invalid_op_vxsnan(env, GETPC()); \ - } \ - if (vxvc_flag) { \ - float_invalid_op_vxvc(env, 0, GETPC()); \ + helper_reset_fpstatus(env); \ + \ + if (svxvc) { \ + r = tp##_##cmp(xb->fld, xa->fld, &env->fp_status); \ + } else { \ + r = tp##_##cmp##_quiet(xb->fld, xa->fld, &env->fp_status); \ } \ - vex_flag = fpscr_ve && (vxvc_flag || vxsnan_flag); \ \ - if (!vex_flag) { \ - if (float64_##cmp(xb->VsrD(0), xa->VsrD(0), \ - &env->fp_status) == exp) { \ - t.VsrD(0) = -1; \ - t.VsrD(1) = 0; \ - } else { \ - t.VsrD(0) = 0; \ - t.VsrD(1) = 0; \ + flags = get_float_exception_flags(&env->fp_status); \ + if (unlikely(flags & float_flag_invalid)) { \ + vxvc = svxvc; \ + if (flags & float_flag_invalid_snan) { \ + float_invalid_op_vxsnan(env, GETPC()); \ + vxvc &= fpscr_ve == 0; \ + } \ + if (vxvc) { \ + float_invalid_op_vxvc(env, 0, GETPC()); \ } \ } \ - *xt = t; \ + \ + memset(xt, 0, sizeof(*xt)); \ + memset(&xt->fld, -r, sizeof(xt->fld)); \ do_float_check_status(env, GETPC()); \ } -VSX_SCALAR_CMP_DP(xscmpeqdp, eq, 1, 0) -VSX_SCALAR_CMP_DP(xscmpgedp, le, 1, 1) -VSX_SCALAR_CMP_DP(xscmpgtdp, lt, 1, 1) -VSX_SCALAR_CMP_DP(xscmpnedp, eq, 0, 0) +VSX_SCALAR_CMP(XSCMPEQDP, float64, eq, VsrD(0), 0) +VSX_SCALAR_CMP(XSCMPGEDP, float64, le, VsrD(0), 1) +VSX_SCALAR_CMP(XSCMPGTDP, float64, lt, VsrD(0), 1) +VSX_SCALAR_CMP(XSCMPEQQP, float128, eq, f128, 0) +VSX_SCALAR_CMP(XSCMPGEQP, float128, le, f128, 1) +VSX_SCALAR_CMP(XSCMPGTQP, float128, lt, f128, 1) void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode, ppc_vsr_t *xa, ppc_vsr_t *xb) @@ -2494,40 +2533,35 @@ VSX_MAX_MIN(xsmindp, minnum, 1, float64, VsrD(0)) VSX_MAX_MIN(xvmindp, minnum, 2, float64, VsrD(i)) VSX_MAX_MIN(xvminsp, minnum, 4, float32, VsrW(i)) -#define VSX_MAX_MINC(name, max) \ +#define VSX_MAX_MINC(name, max, tp, fld) \ void helper_##name(CPUPPCState *env, \ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb) \ { \ ppc_vsr_t t = { }; \ - bool vxsnan_flag = false, vex_flag = false; \ + bool first; \ \ - if (unlikely(float64_is_any_nan(xa->VsrD(0)) || \ - float64_is_any_nan(xb->VsrD(0)))) { \ - if (float64_is_signaling_nan(xa->VsrD(0), &env->fp_status) || \ - float64_is_signaling_nan(xb->VsrD(0), &env->fp_status)) { \ - vxsnan_flag = true; \ - } \ - t.VsrD(0) = xb->VsrD(0); \ - } else if ((max && \ - !float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status)) || \ - (!max && \ - float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status))) { \ - t.VsrD(0) = xa->VsrD(0); \ + if (max) { \ + first = tp##_le_quiet(xb->fld, xa->fld, &env->fp_status); \ } else { \ - t.VsrD(0) = xb->VsrD(0); \ + first = tp##_lt_quiet(xa->fld, xb->fld, &env->fp_status); \ } \ \ - vex_flag = fpscr_ve & vxsnan_flag; \ - if (vxsnan_flag) { \ - float_invalid_op_vxsnan(env, GETPC()); \ - } \ - if (!vex_flag) { \ - *xt = t; \ + if (first) { \ + t.fld = xa->fld; \ + } else { \ + t.fld = xb->fld; \ + if (env->fp_status.float_exception_flags & float_flag_invalid_snan) { \ + float_invalid_op_vxsnan(env, GETPC()); \ + } \ } \ -} \ + \ + *xt = t; \ +} -VSX_MAX_MINC(xsmaxcdp, 1); -VSX_MAX_MINC(xsmincdp, 0); +VSX_MAX_MINC(XSMAXCDP, true, float64, VsrD(0)); +VSX_MAX_MINC(XSMINCDP, false, float64, VsrD(0)); +VSX_MAX_MINC(XSMAXCQP, true, float128, f128); +VSX_MAX_MINC(XSMINCQP, false, float128, f128); #define VSX_MAX_MINJ(name, max) \ void helper_##name(CPUPPCState *env, \ @@ -2581,8 +2615,8 @@ void helper_##name(CPUPPCState *env, \ } \ } \ -VSX_MAX_MINJ(xsmaxjdp, 1); -VSX_MAX_MINJ(xsminjdp, 0); +VSX_MAX_MINJ(XSMAXJDP, 1); +VSX_MAX_MINJ(XSMINJDP, 0); /* * VSX_CMP - VSX floating point compare @@ -2751,6 +2785,24 @@ VSX_CVT_FP_TO_FP_HP(xscvhpdp, 1, float16, float64, VsrH(3), VsrD(0), 1) VSX_CVT_FP_TO_FP_HP(xvcvsphp, 4, float32, float16, VsrW(i), VsrH(2 * i + 1), 0) VSX_CVT_FP_TO_FP_HP(xvcvhpsp, 4, float16, float32, VsrH(2 * i + 1), VsrW(i), 0) +void helper_XVCVSPBF16(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) +{ + ppc_vsr_t t = { }; + int i, status; + + for (i = 0; i < 4; i++) { + t.VsrH(2 * i + 1) = float32_to_bfloat16(xb->VsrW(i), &env->fp_status); + } + + status = get_float_exception_flags(&env->fp_status); + if (unlikely(status & float_flag_invalid_snan)) { + float_invalid_op_vxsnan(env, GETPC()); + } + + *xt = t; + do_float_check_status(env, GETPC()); +} + void helper_XSCVQPDP(CPUPPCState *env, uint32_t ro, ppc_vsr_t *xt, ppc_vsr_t *xb) { @@ -3055,27 +3107,6 @@ uint64_t helper_xsrsp(CPUPPCState *env, uint64_t xb) return xt; } -#define VSX_XXPERM(op, indexed) \ -void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \ - ppc_vsr_t *xa, ppc_vsr_t *pcv) \ -{ \ - ppc_vsr_t t = *xt; \ - int i, idx; \ - \ - for (i = 0; i < 16; i++) { \ - idx = pcv->VsrB(i) & 0x1F; \ - if (indexed) { \ - idx = 31 - idx; \ - } \ - t.VsrB(i) = (idx <= 15) ? xa->VsrB(idx) \ - : xt->VsrB(idx - 16); \ - } \ - *xt = t; \ -} - -VSX_XXPERM(xxperm, 0) -VSX_XXPERM(xxpermr, 1) - void helper_xvxsigsp(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) { ppc_vsr_t t = { }; diff --git a/target/ppc/helper.h b/target/ppc/helper.h index ae7d503fcf..57da11c77e 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -142,46 +142,13 @@ DEF_HELPER_3(vabsduw, void, avr, avr, avr) DEF_HELPER_3(vavgsb, void, avr, avr, avr) DEF_HELPER_3(vavgsh, void, avr, avr, avr) DEF_HELPER_3(vavgsw, void, avr, avr, avr) -DEF_HELPER_4(vcmpequb, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequh, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequw, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequd, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpneb, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpneh, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnew, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnezb, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnezh, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnezw, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtub, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtuh, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtuw, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtud, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsb, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsh, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsw, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsd, void, env, avr, avr, avr) DEF_HELPER_4(vcmpeqfp, void, env, avr, avr, avr) DEF_HELPER_4(vcmpgefp, void, env, avr, avr, avr) DEF_HELPER_4(vcmpgtfp, void, env, avr, avr, avr) DEF_HELPER_4(vcmpbfp, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequb_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequh_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequw_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpequd_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpneb_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpneh_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnew_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnezb_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnezh_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpnezw_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtub_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtuh_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtuw_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtud_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsb_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsh_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsw_dot, void, env, avr, avr, avr) -DEF_HELPER_4(vcmpgtsd_dot, void, env, avr, avr, avr) +DEF_HELPER_FLAGS_4(VCMPNEZB, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VCMPNEZH, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VCMPNEZW, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) DEF_HELPER_4(vcmpeqfp_dot, void, env, avr, avr, avr) DEF_HELPER_4(vcmpgefp_dot, void, env, avr, avr, avr) DEF_HELPER_4(vcmpgtfp_dot, void, env, avr, avr, avr) @@ -192,22 +159,18 @@ DEF_HELPER_3(vmrglw, void, avr, avr, avr) DEF_HELPER_3(vmrghb, void, avr, avr, avr) DEF_HELPER_3(vmrghh, void, avr, avr, avr) DEF_HELPER_3(vmrghw, void, avr, avr, avr) -DEF_HELPER_3(vmulesb, void, avr, avr, avr) -DEF_HELPER_3(vmulesh, void, avr, avr, avr) -DEF_HELPER_3(vmulesw, void, avr, avr, avr) -DEF_HELPER_3(vmuleub, void, avr, avr, avr) -DEF_HELPER_3(vmuleuh, void, avr, avr, avr) -DEF_HELPER_3(vmuleuw, void, avr, avr, avr) -DEF_HELPER_3(vmulosb, void, avr, avr, avr) -DEF_HELPER_3(vmulosh, void, avr, avr, avr) -DEF_HELPER_3(vmulosw, void, avr, avr, avr) -DEF_HELPER_3(vmuloub, void, avr, avr, avr) -DEF_HELPER_3(vmulouh, void, avr, avr, avr) -DEF_HELPER_3(vmulouw, void, avr, avr, avr) -DEF_HELPER_3(vmulhsw, void, avr, avr, avr) -DEF_HELPER_3(vmulhuw, void, avr, avr, avr) -DEF_HELPER_3(vmulhsd, void, avr, avr, avr) -DEF_HELPER_3(vmulhud, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULESB, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULESH, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULESW, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULEUB, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULEUH, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULEUW, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULOSB, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULOSH, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULOSW, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULOUB, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULOUH, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_3(VMULOUW, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_3(vslo, void, avr, avr, avr) DEF_HELPER_3(vsro, void, avr, avr, avr) DEF_HELPER_3(vsrv, void, avr, avr, avr) @@ -246,11 +209,10 @@ DEF_HELPER_4(VINSBLX, void, env, avr, i64, tl) DEF_HELPER_4(VINSHLX, void, env, avr, i64, tl) DEF_HELPER_4(VINSWLX, void, env, avr, i64, tl) DEF_HELPER_4(VINSDLX, void, env, avr, i64, tl) -DEF_HELPER_2(vextsb2w, void, avr, avr) -DEF_HELPER_2(vextsh2w, void, avr, avr) -DEF_HELPER_2(vextsb2d, void, avr, avr) -DEF_HELPER_2(vextsh2d, void, avr, avr) -DEF_HELPER_2(vextsw2d, void, avr, avr) +DEF_HELPER_FLAGS_2(VSTRIBL, TCG_CALL_NO_RWG, i32, avr, avr) +DEF_HELPER_FLAGS_2(VSTRIBR, TCG_CALL_NO_RWG, i32, avr, avr) +DEF_HELPER_FLAGS_2(VSTRIHL, TCG_CALL_NO_RWG, i32, avr, avr) +DEF_HELPER_FLAGS_2(VSTRIHR, TCG_CALL_NO_RWG, i32, avr, avr) DEF_HELPER_2(vnegw, void, avr, avr) DEF_HELPER_2(vnegd, void, avr, avr) DEF_HELPER_2(vupkhpx, void, avr, avr) @@ -263,9 +225,8 @@ DEF_HELPER_2(vupklsh, void, avr, avr) DEF_HELPER_2(vupklsw, void, avr, avr) DEF_HELPER_5(vmsumubm, void, env, avr, avr, avr, avr) DEF_HELPER_5(vmsummbm, void, env, avr, avr, avr, avr) -DEF_HELPER_5(vsel, void, env, avr, avr, avr, avr) -DEF_HELPER_5(vperm, void, env, avr, avr, avr, avr) -DEF_HELPER_5(vpermr, void, env, avr, avr, avr, avr) +DEF_HELPER_FLAGS_4(VPERM, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) +DEF_HELPER_FLAGS_4(VPERMR, TCG_CALL_NO_RWG, void, avr, avr, avr, avr) DEF_HELPER_4(vpkshss, void, env, avr, avr, avr) DEF_HELPER_4(vpkshus, void, env, avr, avr, avr) DEF_HELPER_4(vpkswss, void, env, avr, avr, avr) @@ -311,10 +272,10 @@ DEF_HELPER_4(vmaxfp, void, env, avr, avr, avr) DEF_HELPER_4(vminfp, void, env, avr, avr, avr) DEF_HELPER_3(vrefp, void, env, avr, avr) DEF_HELPER_3(vrsqrtefp, void, env, avr, avr) -DEF_HELPER_3(vrlwmi, void, avr, avr, avr) -DEF_HELPER_3(vrldmi, void, avr, avr, avr) -DEF_HELPER_3(vrldnm, void, avr, avr, avr) -DEF_HELPER_3(vrlwnm, void, avr, avr, avr) +DEF_HELPER_FLAGS_4(VRLWMI, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VRLDMI, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VRLDNM, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VRLWNM, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) DEF_HELPER_5(vmaddfp, void, env, avr, avr, avr, avr) DEF_HELPER_5(vnmsubfp, void, env, avr, avr, avr, avr) DEF_HELPER_3(vexptefp, void, env, avr, avr) @@ -394,14 +355,16 @@ DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr) DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr) DEF_HELPER_4(xstdivdp, void, env, i32, vsr, vsr) DEF_HELPER_3(xstsqrtdp, void, env, i32, vsr) -DEF_HELPER_5(xsmadddp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_5(xsmsubdp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_5(xsnmadddp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_5(xsnmsubdp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_4(xscmpeqdp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xscmpgtdp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xscmpgedp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xscmpnedp, void, env, vsr, vsr, vsr) +DEF_HELPER_5(XSMADDDP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSMSUBDP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMADDDP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMSUBDP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_4(XSCMPEQDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSCMPGTDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSCMPGEDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSCMPEQQP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSCMPGTQP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSCMPGEQP, void, env, vsr, vsr, vsr) DEF_HELPER_4(xscmpexpdp, void, env, i32, vsr, vsr) DEF_HELPER_4(xscmpexpqp, void, env, i32, vsr, vsr) DEF_HELPER_4(xscmpodp, void, env, i32, vsr, vsr) @@ -410,10 +373,12 @@ DEF_HELPER_4(xscmpoqp, void, env, i32, vsr, vsr) DEF_HELPER_4(xscmpuqp, void, env, i32, vsr, vsr) DEF_HELPER_4(xsmaxdp, void, env, vsr, vsr, vsr) DEF_HELPER_4(xsmindp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xsmaxcdp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xsmincdp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xsmaxjdp, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xsminjdp, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSMAXCDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSMINCDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSMAXJDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSMINJDP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSMAXCQP, void, env, vsr, vsr, vsr) +DEF_HELPER_4(XSMINCQP, void, env, vsr, vsr, vsr) DEF_HELPER_3(xscvdphp, void, env, vsr, vsr) DEF_HELPER_4(xscvdpqp, void, env, i32, vsr, vsr) DEF_HELPER_3(xscvdpsp, void, env, vsr, vsr) @@ -457,10 +422,19 @@ DEF_HELPER_3(xsresp, void, env, vsr, vsr) DEF_HELPER_2(xsrsp, i64, env, i64) DEF_HELPER_3(xssqrtsp, void, env, vsr, vsr) DEF_HELPER_3(xsrsqrtesp, void, env, vsr, vsr) -DEF_HELPER_5(xsmaddsp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_5(xsmsubsp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_5(xsnmaddsp, void, env, vsr, vsr, vsr, vsr) -DEF_HELPER_5(xsnmsubsp, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSMADDSP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSMSUBSP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMADDSP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMSUBSP, void, env, vsr, vsr, vsr, vsr) + +DEF_HELPER_5(XSMADDQP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSMADDQPO, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSMSUBQP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSMSUBQPO, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMADDQP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMADDQPO, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMSUBQP, void, env, vsr, vsr, vsr, vsr) +DEF_HELPER_5(XSNMSUBQPO, void, env, vsr, vsr, vsr, vsr) DEF_HELPER_4(xvadddp, void, env, vsr, vsr, vsr) DEF_HELPER_4(xvsubdp, void, env, vsr, vsr, vsr) @@ -518,6 +492,7 @@ DEF_HELPER_FLAGS_4(xvcmpnesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr) DEF_HELPER_3(xvcvspdp, void, env, vsr, vsr) DEF_HELPER_3(xvcvsphp, void, env, vsr, vsr) DEF_HELPER_3(xvcvhpsp, void, env, vsr, vsr) +DEF_HELPER_3(XVCVSPBF16, void, env, vsr, vsr) DEF_HELPER_3(xvcvspsxds, void, env, vsr, vsr) DEF_HELPER_3(xvcvspsxws, void, env, vsr, vsr) DEF_HELPER_3(xvcvspuxds, void, env, vsr, vsr) @@ -533,11 +508,27 @@ DEF_HELPER_3(xvrspic, void, env, vsr, vsr) DEF_HELPER_3(xvrspim, void, env, vsr, vsr) DEF_HELPER_3(xvrspip, void, env, vsr, vsr) DEF_HELPER_3(xvrspiz, void, env, vsr, vsr) -DEF_HELPER_4(xxperm, void, env, vsr, vsr, vsr) -DEF_HELPER_4(xxpermr, void, env, vsr, vsr, vsr) +DEF_HELPER_FLAGS_2(XXGENPCVBM_be_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVBM_be_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVBM_le_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVBM_le_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVHM_be_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVHM_be_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVHM_le_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVHM_le_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVWM_be_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVWM_be_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVWM_le_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVWM_le_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVDM_be_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVDM_be_comp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVDM_le_exp, TCG_CALL_NO_RWG, void, vsr, avr) +DEF_HELPER_FLAGS_2(XXGENPCVDM_le_comp, TCG_CALL_NO_RWG, void, vsr, avr) DEF_HELPER_4(xxextractuw, void, env, vsr, vsr, i32) +DEF_HELPER_FLAGS_5(XXPERMX, TCG_CALL_NO_RWG, void, vsr, vsr, vsr, vsr, tl) DEF_HELPER_4(xxinsertw, void, env, vsr, vsr, i32) DEF_HELPER_3(xvxsigsp, void, env, vsr, vsr) +DEF_HELPER_FLAGS_5(XXEVAL, TCG_CALL_NO_RWG, void, vsr, vsr, vsr, vsr, i32) DEF_HELPER_5(XXBLENDVB, void, vsr, vsr, vsr, vsr, i32) DEF_HELPER_5(XXBLENDVH, void, vsr, vsr, vsr, vsr, i32) DEF_HELPER_5(XXBLENDVW, void, vsr, vsr, vsr, vsr, i32) diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode index 2a9c91a423..ac2d3da9a7 100644 --- a/target/ppc/insn32.decode +++ b/target/ppc/insn32.decode @@ -51,12 +51,27 @@ &VA vrt vra vrb rc @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 + &VN vrt vra vrb sh @VN ...... vrt:5 vra:5 vrb:5 .. sh:3 ...... &VN &VX vrt vra vrb @VX ...... vrt:5 vra:5 vrb:5 .......... . &VX +&VX_bf bf vra vrb +@VX_bf ...... bf:3 .. vra:5 vrb:5 ........... &VX_bf + +&VX_mp rt mp:bool vrb +@VX_mp ...... rt:5 .... mp:1 vrb:5 ........... &VX_mp + +&VX_n rt vrb n +@VX_n ...... rt:5 .. n:3 vrb:5 ........... &VX_n + +&VX_tb_rc vrt vrb rc:bool +@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 @@ -104,6 +119,9 @@ @X_bfl ...... bf:3 - l:1 ra:5 rb:5 ..........- &X_bfl %x_xt 0:1 21:5 +&X_imm5 xt imm:uint8_t vrb +@X_imm5 ...... ..... imm:5 vrb:5 .......... . &X_imm5 xt=%x_xt + &X_imm8 xt imm:uint8_t @X_imm8 ...... ..... .. imm:8 .......... . &X_imm8 xt=%x_xt @@ -133,12 +151,25 @@ %xx_xt 0:1 21:5 %xx_xb 1:1 11:5 %xx_xa 2:1 16:5 -&XX2 xt xb uim:uint8_t -@XX2 ...... ..... ... uim:2 ..... ......... .. &XX2 xt=%xx_xt xb=%xx_xb +%xx_xc 3:1 6:5 +&XX2 xt xb +@XX2 ...... ..... ..... ..... ......... .. &XX2 xt=%xx_xt xb=%xx_xb + +&XX2_uim2 xt xb uim:uint8_t +@XX2_uim2 ...... ..... ... uim:2 ..... ......... .. &XX2_uim2 xt=%xx_xt xb=%xx_xb + +&XX2_bf_xb bf xb +@XX2_bf_xb ...... bf:3 .. ..... ..... ......... . . &XX2_bf_xb xb=%xx_xb &XX3 xt xa xb @XX3 ...... ..... ..... ..... ........ ... &XX3 xt=%xx_xt xa=%xx_xa xb=%xx_xb +&XX3_dm xt xa xb dm +@XX3_dm ...... ..... ..... ..... . dm:2 ..... ... &XX3_dm xt=%xx_xt xa=%xx_xa xb=%xx_xb + +&XX4 xt xa xb xc +@XX4 ...... ..... ..... ..... ..... .. .... &XX4 xt=%xx_xt xa=%xx_xa xb=%xx_xb xc=%xx_xc + &Z22_bf_fra bf fra dm @Z22_bf_fra ...... bf:3 .. fra:5 dm:6 ......... . &Z22_bf_fra @@ -373,8 +404,41 @@ DSCLIQ 111111 ..... ..... ...... 001000010 . @Z22_tap_sh_rc DSCRI 111011 ..... ..... ...... 001100010 . @Z22_ta_sh_rc DSCRIQ 111111 ..... ..... ...... 001100010 . @Z22_tap_sh_rc +## Vector Integer Instructions + +VCMPEQUB 000100 ..... ..... ..... . 0000000110 @VC +VCMPEQUH 000100 ..... ..... ..... . 0001000110 @VC +VCMPEQUW 000100 ..... ..... ..... . 0010000110 @VC +VCMPEQUD 000100 ..... ..... ..... . 0011000111 @VC +VCMPEQUQ 000100 ..... ..... ..... . 0111000111 @VC + +VCMPGTSB 000100 ..... ..... ..... . 1100000110 @VC +VCMPGTSH 000100 ..... ..... ..... . 1101000110 @VC +VCMPGTSW 000100 ..... ..... ..... . 1110000110 @VC +VCMPGTSD 000100 ..... ..... ..... . 1111000111 @VC +VCMPGTSQ 000100 ..... ..... ..... . 1110000111 @VC + +VCMPGTUB 000100 ..... ..... ..... . 1000000110 @VC +VCMPGTUH 000100 ..... ..... ..... . 1001000110 @VC +VCMPGTUW 000100 ..... ..... ..... . 1010000110 @VC +VCMPGTUD 000100 ..... ..... ..... . 1011000111 @VC +VCMPGTUQ 000100 ..... ..... ..... . 1010000111 @VC + +VCMPNEB 000100 ..... ..... ..... . 0000000111 @VC +VCMPNEH 000100 ..... ..... ..... . 0001000111 @VC +VCMPNEW 000100 ..... ..... ..... . 0010000111 @VC + +VCMPNEZB 000100 ..... ..... ..... . 0100000111 @VC +VCMPNEZH 000100 ..... ..... ..... . 0101000111 @VC +VCMPNEZW 000100 ..... ..... ..... . 0110000111 @VC + +VCMPSQ 000100 ... -- ..... ..... 00101000001 @VX_bf +VCMPUQ 000100 ... -- ..... ..... 00100000001 @VX_bf + ## Vector Bit Manipulation Instruction +VGNB 000100 ..... -- ... ..... 10011001100 @VX_n + VCFUGED 000100 ..... ..... ..... 10101001101 @VX VCLZDM 000100 ..... ..... ..... 11110000100 @VX VCTZDM 000100 ..... ..... ..... 11111000100 @VX @@ -419,6 +483,54 @@ VINSWVRX 000100 ..... ..... ..... 00110001111 @VX VSLDBI 000100 ..... ..... ..... 00 ... 010110 @VN VSRDBI 000100 ..... ..... ..... 01 ... 010110 @VN +VPERM 000100 ..... ..... ..... ..... 101011 @VA +VPERMR 000100 ..... ..... ..... ..... 111011 @VA + +VSEL 000100 ..... ..... ..... ..... 101010 @VA + +## Vector Integer Shift Instruction + +VSLB 000100 ..... ..... ..... 00100000100 @VX +VSLH 000100 ..... ..... ..... 00101000100 @VX +VSLW 000100 ..... ..... ..... 00110000100 @VX +VSLD 000100 ..... ..... ..... 10111000100 @VX +VSLQ 000100 ..... ..... ..... 00100000101 @VX + +VSRB 000100 ..... ..... ..... 01000000100 @VX +VSRH 000100 ..... ..... ..... 01001000100 @VX +VSRW 000100 ..... ..... ..... 01010000100 @VX +VSRD 000100 ..... ..... ..... 11011000100 @VX +VSRQ 000100 ..... ..... ..... 01000000101 @VX + +VSRAB 000100 ..... ..... ..... 01100000100 @VX +VSRAH 000100 ..... ..... ..... 01101000100 @VX +VSRAW 000100 ..... ..... ..... 01110000100 @VX +VSRAD 000100 ..... ..... ..... 01111000100 @VX +VSRAQ 000100 ..... ..... ..... 01100000101 @VX + +VRLB 000100 ..... ..... ..... 00000000100 @VX +VRLH 000100 ..... ..... ..... 00001000100 @VX +VRLW 000100 ..... ..... ..... 00010000100 @VX +VRLD 000100 ..... ..... ..... 00011000100 @VX +VRLQ 000100 ..... ..... ..... 00000000101 @VX + +VRLWMI 000100 ..... ..... ..... 00010000101 @VX +VRLDMI 000100 ..... ..... ..... 00011000101 @VX +VRLQMI 000100 ..... ..... ..... 00001000101 @VX + +VRLWNM 000100 ..... ..... ..... 00110000101 @VX +VRLDNM 000100 ..... ..... ..... 00111000101 @VX +VRLQNM 000100 ..... ..... ..... 00101000101 @VX + +## Vector Integer Arithmetic Instructions + +VEXTSB2W 000100 ..... 10000 ..... 11000000010 @VX_tb +VEXTSH2W 000100 ..... 10001 ..... 11000000010 @VX_tb +VEXTSB2D 000100 ..... 11000 ..... 11000000010 @VX_tb +VEXTSH2D 000100 ..... 11001 ..... 11000000010 @VX_tb +VEXTSW2D 000100 ..... 11010 ..... 11000000010 @VX_tb +VEXTSD2Q 000100 ..... 11011 ..... 11000000010 @VX_tb + ## Vector Mask Manipulation Instructions MTVSRBM 000100 ..... 10000 ..... 11001000010 @VX_tb @@ -440,8 +552,60 @@ VEXTRACTWM 000100 ..... 01010 ..... 11001000010 @VX_tb VEXTRACTDM 000100 ..... 01011 ..... 11001000010 @VX_tb VEXTRACTQM 000100 ..... 01100 ..... 11001000010 @VX_tb +VCNTMBB 000100 ..... 1100 . ..... 11001000010 @VX_mp +VCNTMBH 000100 ..... 1101 . ..... 11001000010 @VX_mp +VCNTMBW 000100 ..... 1110 . ..... 11001000010 @VX_mp +VCNTMBD 000100 ..... 1111 . ..... 11001000010 @VX_mp + +## Vector Multiply Instruction + +VMULESB 000100 ..... ..... ..... 01100001000 @VX +VMULOSB 000100 ..... ..... ..... 00100001000 @VX +VMULEUB 000100 ..... ..... ..... 01000001000 @VX +VMULOUB 000100 ..... ..... ..... 00000001000 @VX + +VMULESH 000100 ..... ..... ..... 01101001000 @VX +VMULOSH 000100 ..... ..... ..... 00101001000 @VX +VMULEUH 000100 ..... ..... ..... 01001001000 @VX +VMULOUH 000100 ..... ..... ..... 00001001000 @VX + +VMULESW 000100 ..... ..... ..... 01110001000 @VX +VMULOSW 000100 ..... ..... ..... 00110001000 @VX +VMULEUW 000100 ..... ..... ..... 01010001000 @VX +VMULOUW 000100 ..... ..... ..... 00010001000 @VX + +VMULESD 000100 ..... ..... ..... 01111001000 @VX +VMULOSD 000100 ..... ..... ..... 00111001000 @VX +VMULEUD 000100 ..... ..... ..... 01011001000 @VX +VMULOUD 000100 ..... ..... ..... 00011001000 @VX + +VMULHSW 000100 ..... ..... ..... 01110001001 @VX +VMULHUW 000100 ..... ..... ..... 01010001001 @VX +VMULHSD 000100 ..... ..... ..... 01111001001 @VX +VMULHUD 000100 ..... ..... ..... 01011001001 @VX +VMULLD 000100 ..... ..... ..... 00111001001 @VX + +## Vector Multiply-Sum Instructions + +VMSUMCUD 000100 ..... ..... ..... ..... 010111 @VA +VMSUMUDM 000100 ..... ..... ..... ..... 100011 @VA + +## Vector String Instructions + +VSTRIBL 000100 ..... 00000 ..... . 0000001101 @VX_tb_rc +VSTRIBR 000100 ..... 00001 ..... . 0000001101 @VX_tb_rc +VSTRIHL 000100 ..... 00010 ..... . 0000001101 @VX_tb_rc +VSTRIHR 000100 ..... 00011 ..... . 0000001101 @VX_tb_rc + +VCLRLB 000100 ..... ..... ..... 00110001101 @VX +VCLRRB 000100 ..... ..... ..... 00111001101 @VX + # VSX Load/Store Instructions +LXSD 111001 ..... ..... .............. 10 @DS +STXSD 111101 ..... ..... .............. 10 @DS +LXSSP 111001 ..... ..... .............. 11 @DS +STXSSP 111101 ..... ..... .............. 11 @DS LXV 111101 ..... ..... ............ . 001 @DQ_TSX STXV 111101 ..... ..... ............ . 101 @DQ_TSX LXVP 000110 ..... ..... ............ 0000 @DQ_TSXP @@ -450,11 +614,60 @@ LXVX 011111 ..... ..... ..... 0100 - 01100 . @X_TSX STXVX 011111 ..... ..... ..... 0110001100 . @X_TSX LXVPX 011111 ..... ..... ..... 0101001101 - @X_TSXP STXVPX 011111 ..... ..... ..... 0111001101 - @X_TSXP +LXVRBX 011111 ..... ..... ..... 0000001101 . @X_TSX +LXVRHX 011111 ..... ..... ..... 0000101101 . @X_TSX +LXVRWX 011111 ..... ..... ..... 0001001101 . @X_TSX +LXVRDX 011111 ..... ..... ..... 0001101101 . @X_TSX +STXVRBX 011111 ..... ..... ..... 0010001101 . @X_TSX +STXVRHX 011111 ..... ..... ..... 0010101101 . @X_TSX +STXVRWX 011111 ..... ..... ..... 0011001101 . @X_TSX +STXVRDX 011111 ..... ..... ..... 0011101101 . @X_TSX + +## VSX Scalar Multiply-Add Instructions + +XSMADDADP 111100 ..... ..... ..... 00100001 . . . @XX3 +XSMADDMDP 111100 ..... ..... ..... 00101001 . . . @XX3 +XSMADDASP 111100 ..... ..... ..... 00000001 . . . @XX3 +XSMADDMSP 111100 ..... ..... ..... 00001001 . . . @XX3 +XSMADDQP 111111 ..... ..... ..... 0110000100 . @X_rc + +XSMSUBADP 111100 ..... ..... ..... 00110001 . . . @XX3 +XSMSUBMDP 111100 ..... ..... ..... 00111001 . . . @XX3 +XSMSUBASP 111100 ..... ..... ..... 00010001 . . . @XX3 +XSMSUBMSP 111100 ..... ..... ..... 00011001 . . . @XX3 +XSMSUBQP 111111 ..... ..... ..... 0110100100 . @X_rc + +XSNMADDASP 111100 ..... ..... ..... 10000001 . . . @XX3 +XSNMADDMSP 111100 ..... ..... ..... 10001001 . . . @XX3 +XSNMADDADP 111100 ..... ..... ..... 10100001 . . . @XX3 +XSNMADDMDP 111100 ..... ..... ..... 10101001 . . . @XX3 +XSNMADDQP 111111 ..... ..... ..... 0111000100 . @X_rc + +XSNMSUBASP 111100 ..... ..... ..... 10010001 . . . @XX3 +XSNMSUBMSP 111100 ..... ..... ..... 10011001 . . . @XX3 +XSNMSUBADP 111100 ..... ..... ..... 10110001 . . . @XX3 +XSNMSUBMDP 111100 ..... ..... ..... 10111001 . . . @XX3 +XSNMSUBQP 111111 ..... ..... ..... 0111100100 . @X_rc ## VSX splat instruction XXSPLTIB 111100 ..... 00 ........ 0101101000 . @X_imm8 -XXSPLTW 111100 ..... ---.. ..... 010100100 . . @XX2 +XXSPLTW 111100 ..... ---.. ..... 010100100 . . @XX2_uim2 + +## VSX Permute Instructions + +XXPERM 111100 ..... ..... ..... 00011010 ... @XX3 +XXPERMR 111100 ..... ..... ..... 00111010 ... @XX3 +XXPERMDI 111100 ..... ..... ..... 0 .. 01010 ... @XX3_dm + +XXSEL 111100 ..... ..... ..... ..... 11 .... @XX4 + +## VSX Vector Generate PCV + +XXGENPCVBM 111100 ..... ..... ..... 1110010100 . @X_imm5 +XXGENPCVHM 111100 ..... ..... ..... 1110010101 . @X_imm5 +XXGENPCVWM 111100 ..... ..... ..... 1110110100 . @X_imm5 +XXGENPCVDM 111100 ..... ..... ..... 1110110101 . @X_imm5 ## VSX Vector Load Special Value Instruction @@ -466,10 +679,25 @@ XSMAXCDP 111100 ..... ..... ..... 10000000 ... @XX3 XSMINCDP 111100 ..... ..... ..... 10001000 ... @XX3 XSMAXJDP 111100 ..... ..... ..... 10010000 ... @XX3 XSMINJDP 111100 ..... ..... ..... 10011000 ... @XX3 +XSMAXCQP 111111 ..... ..... ..... 1010100100 - @X +XSMINCQP 111111 ..... ..... ..... 1011100100 - @X + +XSCMPEQDP 111100 ..... ..... ..... 00000011 ... @XX3 +XSCMPGEDP 111100 ..... ..... ..... 00010011 ... @XX3 +XSCMPGTDP 111100 ..... ..... ..... 00001011 ... @XX3 +XSCMPEQQP 111111 ..... ..... ..... 0001000100 - @X +XSCMPGEQP 111111 ..... ..... ..... 0011000100 - @X +XSCMPGTQP 111111 ..... ..... ..... 0011100100 - @X ## VSX Binary Floating-Point Convert Instructions XSCVQPDP 111111 ..... 10100 ..... 1101000100 . @X_tb_rc +XVCVBF16SPN 111100 ..... 10000 ..... 111011011 .. @XX2 +XVCVSPBF16 111100 ..... 10001 ..... 111011011 .. @XX2 + +## VSX Vector Test Least-Significant Bit by Byte Instruction + +XVTLSBB 111100 ... -- 00010 ..... 111011011 . - @XX2_bf_xb ### rfebb &XL_s s:uint8_t diff --git a/target/ppc/insn64.decode b/target/ppc/insn64.decode index 39e610913d..691e8fe6c0 100644 --- a/target/ppc/insn64.decode +++ b/target/ppc/insn64.decode @@ -32,6 +32,10 @@ ...... ..... ra:5 ................ \ &PLS_D si=%pls_si rt=%rt_tsxp +@8LS_D ...... .. . .. r:1 .. .................. \ + ...... rt:5 ra:5 ................ \ + &PLS_D si=%pls_si + # Format 8RR:D %8rr_si 32:s16 0:16 %8rr_xt 16:1 21:5 @@ -44,15 +48,25 @@ ...... ..... .... . ................ \ &8RR_D si=%8rr_si xt=%8rr_xt -# Format XX4 -&XX4 xt xa xb xc -%xx4_xt 0:1 21:5 -%xx4_xa 2:1 16:5 -%xx4_xb 1:1 11:5 -%xx4_xc 3:1 6:5 -@XX4 ........ ........ ........ ........ \ +# Format 8RR:XX4 +%8rr_xx_xt 0:1 21:5 +%8rr_xx_xa 2:1 16:5 +%8rr_xx_xb 1:1 11:5 +%8rr_xx_xc 3:1 6:5 +&8RR_XX4 xt xa xb xc +@8RR_XX4 ........ ........ ........ ........ \ + ...... ..... ..... ..... ..... .. .... \ + &8RR_XX4 xt=%8rr_xx_xt xa=%8rr_xx_xa xb=%8rr_xx_xb xc=%8rr_xx_xc + +&8RR_XX4_imm xt xa xb xc imm +@8RR_XX4_imm ........ ........ ........ imm:8 \ ...... ..... ..... ..... ..... .. .... \ - &XX4 xt=%xx4_xt xa=%xx4_xa xb=%xx4_xb xc=%xx4_xc + &8RR_XX4_imm xt=%8rr_xx_xt xa=%8rr_xx_xa xb=%8rr_xx_xb xc=%8rr_xx_xc + +&8RR_XX4_uim3 xt xa xb xc uim3 +@8RR_XX4_uim3 ...... .. .... .. ............... uim3:3 \ + ...... ..... ..... ..... ..... .. .... \ + &8RR_XX4_uim3 xt=%8rr_xx_xt xa=%8rr_xx_xa xb=%8rr_xx_xb xc=%8rr_xx_xc ### Fixed-Point Load Instructions @@ -170,6 +184,18 @@ PSTFD 000001 10 0--.-- .................. \ ### VSX instructions +PLXSD 000001 00 0--.-- .................. \ + 101010 ..... ..... ................ @8LS_D + +PSTXSD 000001 00 0--.-- .................. \ + 101110 ..... ..... ................ @8LS_D + +PLXSSP 000001 00 0--.-- .................. \ + 101011 ..... ..... ................ @8LS_D + +PSTXSSP 000001 00 0--.-- .................. \ + 101111 ..... ..... ................ @8LS_D + PLXV 000001 00 0--.-- .................. \ 11001 ...... ..... ................ @8LS_D_TSX PSTXV 000001 00 0--.-- .................. \ @@ -179,6 +205,9 @@ PLXVP 000001 00 0--.-- .................. \ PSTXVP 000001 00 0--.-- .................. \ 111110 ..... ..... ................ @8LS_D_TSXP +XXEVAL 000001 01 0000 -- ---------- ........ \ + 100010 ..... ..... ..... ..... 01 .... @8RR_XX4_imm + XXSPLTIDP 000001 01 0000 -- -- ................ \ 100000 ..... 0010 . ................ @8RR_D XXSPLTIW 000001 01 0000 -- -- ................ \ @@ -187,10 +216,13 @@ XXSPLTI32DX 000001 01 0000 -- -- ................ \ 100000 ..... 000 .. ................ @8RR_D_IX XXBLENDVD 000001 01 0000 -- ------------------ \ - 100001 ..... ..... ..... ..... 11 .... @XX4 + 100001 ..... ..... ..... ..... 11 .... @8RR_XX4 XXBLENDVW 000001 01 0000 -- ------------------ \ - 100001 ..... ..... ..... ..... 10 .... @XX4 + 100001 ..... ..... ..... ..... 10 .... @8RR_XX4 XXBLENDVH 000001 01 0000 -- ------------------ \ - 100001 ..... ..... ..... ..... 01 .... @XX4 + 100001 ..... ..... ..... ..... 01 .... @8RR_XX4 XXBLENDVB 000001 01 0000 -- ------------------ \ - 100001 ..... ..... ..... ..... 00 .... @XX4 + 100001 ..... ..... ..... ..... 00 .... @8RR_XX4 + +XXPERMX 000001 01 0000 -- --------------- ... \ + 100010 ..... ..... ..... ..... 00 .... @8RR_XX4_uim3 diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index d1b12788b2..b2b17bb1ca 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -28,6 +28,7 @@ #include "fpu/softfloat.h" #include "qapi/error.h" #include "qemu/guest-random.h" +#include "tcg/tcg-gvec-desc.h" #include "helper_regs.h" /*****************************************************************************/ @@ -662,100 +663,18 @@ VCF(ux, uint32_to_float32, u32) VCF(sx, int32_to_float32, s32) #undef VCF -#define VCMP_DO(suffix, compare, element, record) \ - void helper_vcmp##suffix(CPUPPCState *env, ppc_avr_t *r, \ - ppc_avr_t *a, ppc_avr_t *b) \ - { \ - uint64_t ones = (uint64_t)-1; \ - uint64_t all = ones; \ - uint64_t none = 0; \ - int i; \ - \ - for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ - uint64_t result = (a->element[i] compare b->element[i] ? \ - ones : 0x0); \ - switch (sizeof(a->element[0])) { \ - case 8: \ - r->u64[i] = result; \ - break; \ - case 4: \ - r->u32[i] = result; \ - break; \ - case 2: \ - r->u16[i] = result; \ - break; \ - case 1: \ - r->u8[i] = result; \ - break; \ - } \ - all &= result; \ - none |= result; \ - } \ - if (record) { \ - env->crf[6] = ((all != 0) << 3) | ((none == 0) << 1); \ - } \ - } -#define VCMP(suffix, compare, element) \ - VCMP_DO(suffix, compare, element, 0) \ - VCMP_DO(suffix##_dot, compare, element, 1) -VCMP(equb, ==, u8) -VCMP(equh, ==, u16) -VCMP(equw, ==, u32) -VCMP(equd, ==, u64) -VCMP(gtub, >, u8) -VCMP(gtuh, >, u16) -VCMP(gtuw, >, u32) -VCMP(gtud, >, u64) -VCMP(gtsb, >, s8) -VCMP(gtsh, >, s16) -VCMP(gtsw, >, s32) -VCMP(gtsd, >, s64) -#undef VCMP_DO -#undef VCMP - -#define VCMPNE_DO(suffix, element, etype, cmpzero, record) \ -void helper_vcmpne##suffix(CPUPPCState *env, ppc_avr_t *r, \ - ppc_avr_t *a, ppc_avr_t *b) \ -{ \ - etype ones = (etype)-1; \ - etype all = ones; \ - etype result, none = 0; \ - int i; \ - \ - for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ - if (cmpzero) { \ - result = ((a->element[i] == 0) \ - || (b->element[i] == 0) \ - || (a->element[i] != b->element[i]) ? \ - ones : 0x0); \ - } else { \ - result = (a->element[i] != b->element[i]) ? ones : 0x0; \ - } \ - r->element[i] = result; \ - all &= result; \ - none |= result; \ - } \ - if (record) { \ - env->crf[6] = ((all != 0) << 3) | ((none == 0) << 1); \ - } \ +#define VCMPNEZ(NAME, ELEM) \ +void helper_##NAME(ppc_vsr_t *t, ppc_vsr_t *a, ppc_vsr_t *b, uint32_t desc) \ +{ \ + for (int i = 0; i < ARRAY_SIZE(t->ELEM); i++) { \ + t->ELEM[i] = ((a->ELEM[i] == 0) || (b->ELEM[i] == 0) || \ + (a->ELEM[i] != b->ELEM[i])) ? -1 : 0; \ + } \ } - -/* - * VCMPNEZ - Vector compare not equal to zero - * suffix - instruction mnemonic suffix (b: byte, h: halfword, w: word) - * element - element type to access from vector - */ -#define VCMPNE(suffix, element, etype, cmpzero) \ - VCMPNE_DO(suffix, element, etype, cmpzero, 0) \ - VCMPNE_DO(suffix##_dot, element, etype, cmpzero, 1) -VCMPNE(zb, u8, uint8_t, 1) -VCMPNE(zh, u16, uint16_t, 1) -VCMPNE(zw, u32, uint32_t, 1) -VCMPNE(b, u8, uint8_t, 0) -VCMPNE(h, u16, uint16_t, 0) -VCMPNE(w, u32, uint32_t, 0) -#undef VCMPNE_DO -#undef VCMPNE +VCMPNEZ(VCMPNEZB, u8) +VCMPNEZ(VCMPNEZH, u16) +VCMPNEZ(VCMPNEZW, u32) +#undef VCMPNEZ #define VCMPFP_DO(suffix, compare, order, record) \ void helper_vcmp##suffix(CPUPPCState *env, ppc_avr_t *r, \ @@ -1063,7 +982,7 @@ void helper_vmsumuhs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, } #define VMUL_DO_EVN(name, mul_element, mul_access, prod_access, cast) \ - void helper_v##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \ + void helper_V##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \ { \ int i; \ \ @@ -1074,7 +993,7 @@ void helper_vmsumuhs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, } #define VMUL_DO_ODD(name, mul_element, mul_access, prod_access, cast) \ - void helper_v##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \ + void helper_V##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \ { \ int i; \ \ @@ -1085,55 +1004,39 @@ void helper_vmsumuhs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, } #define VMUL(suffix, mul_element, mul_access, prod_access, cast) \ - VMUL_DO_EVN(mule##suffix, mul_element, mul_access, prod_access, cast) \ - VMUL_DO_ODD(mulo##suffix, mul_element, mul_access, prod_access, cast) -VMUL(sb, s8, VsrSB, VsrSH, int16_t) -VMUL(sh, s16, VsrSH, VsrSW, int32_t) -VMUL(sw, s32, VsrSW, VsrSD, int64_t) -VMUL(ub, u8, VsrB, VsrH, uint16_t) -VMUL(uh, u16, VsrH, VsrW, uint32_t) -VMUL(uw, u32, VsrW, VsrD, uint64_t) + VMUL_DO_EVN(MULE##suffix, mul_element, mul_access, prod_access, cast) \ + VMUL_DO_ODD(MULO##suffix, mul_element, mul_access, prod_access, cast) +VMUL(SB, s8, VsrSB, VsrSH, int16_t) +VMUL(SH, s16, VsrSH, VsrSW, int32_t) +VMUL(SW, s32, VsrSW, VsrSD, int64_t) +VMUL(UB, u8, VsrB, VsrH, uint16_t) +VMUL(UH, u16, VsrH, VsrW, uint32_t) +VMUL(UW, u32, VsrW, VsrD, uint64_t) #undef VMUL_DO_EVN #undef VMUL_DO_ODD #undef VMUL -void helper_vmulhsw(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) -{ - int i; - - for (i = 0; i < 4; i++) { - r->s32[i] = (int32_t)(((int64_t)a->s32[i] * (int64_t)b->s32[i]) >> 32); - } -} - -void helper_vmulhuw(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) +void helper_XXPERMX(ppc_vsr_t *t, ppc_vsr_t *s0, ppc_vsr_t *s1, ppc_vsr_t *pcv, + target_ulong uim) { - int i; + int i, idx; + ppc_vsr_t tmp = { .u64 = {0, 0} }; - for (i = 0; i < 4; i++) { - r->u32[i] = (uint32_t)(((uint64_t)a->u32[i] * - (uint64_t)b->u32[i]) >> 32); + for (i = 0; i < ARRAY_SIZE(t->u8); i++) { + if ((pcv->VsrB(i) >> 5) == uim) { + idx = pcv->VsrB(i) & 0x1f; + if (idx < ARRAY_SIZE(t->u8)) { + tmp.VsrB(i) = s0->VsrB(idx); + } else { + tmp.VsrB(i) = s1->VsrB(idx - ARRAY_SIZE(t->u8)); + } + } } -} -void helper_vmulhsd(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) -{ - uint64_t discard; - - muls64(&discard, &r->u64[0], a->s64[0], b->s64[0]); - muls64(&discard, &r->u64[1], a->s64[1], b->s64[1]); + *t = tmp; } -void helper_vmulhud(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) -{ - uint64_t discard; - - mulu64(&discard, &r->u64[0], a->u64[0], b->u64[0]); - mulu64(&discard, &r->u64[1], a->u64[1], b->u64[1]); -} - -void helper_vperm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, - ppc_avr_t *c) +void helper_VPERM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { ppc_avr_t result; int i; @@ -1151,8 +1054,7 @@ void helper_vperm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, *r = result; } -void helper_vpermr(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, - ppc_avr_t *c) +void helper_VPERMR(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { ppc_avr_t result; int i; @@ -1170,6 +1072,97 @@ void helper_vpermr(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, *r = result; } +#define XXGENPCV(NAME, SZ) \ +void glue(helper_, glue(NAME, _be_exp))(ppc_vsr_t *t, ppc_vsr_t *b) \ +{ \ + ppc_vsr_t tmp; \ + \ + /* Initialize tmp with the result of an all-zeros mask */ \ + tmp.VsrD(0) = 0x1011121314151617; \ + tmp.VsrD(1) = 0x18191A1B1C1D1E1F; \ + \ + /* Iterate over the most significant byte of each element */ \ + for (int i = 0, j = 0; i < ARRAY_SIZE(b->u8); i += SZ) { \ + if (b->VsrB(i) & 0x80) { \ + /* Update each byte of the element */ \ + for (int k = 0; k < SZ; k++) { \ + tmp.VsrB(i + k) = j + k; \ + } \ + j += SZ; \ + } \ + } \ + \ + *t = tmp; \ +} \ + \ +void glue(helper_, glue(NAME, _be_comp))(ppc_vsr_t *t, ppc_vsr_t *b)\ +{ \ + ppc_vsr_t tmp = { .u64 = { 0, 0 } }; \ + \ + /* Iterate over the most significant byte of each element */ \ + for (int i = 0, j = 0; i < ARRAY_SIZE(b->u8); i += SZ) { \ + if (b->VsrB(i) & 0x80) { \ + /* Update each byte of the element */ \ + for (int k = 0; k < SZ; k++) { \ + tmp.VsrB(j + k) = i + k; \ + } \ + j += SZ; \ + } \ + } \ + \ + *t = tmp; \ +} \ + \ +void glue(helper_, glue(NAME, _le_exp))(ppc_vsr_t *t, ppc_vsr_t *b) \ +{ \ + ppc_vsr_t tmp; \ + \ + /* Initialize tmp with the result of an all-zeros mask */ \ + tmp.VsrD(0) = 0x1F1E1D1C1B1A1918; \ + tmp.VsrD(1) = 0x1716151413121110; \ + \ + /* Iterate over the most significant byte of each element */ \ + for (int i = 0, j = 0; i < ARRAY_SIZE(b->u8); i += SZ) { \ + /* Reverse indexing of "i" */ \ + const int idx = ARRAY_SIZE(b->u8) - i - SZ; \ + if (b->VsrB(idx) & 0x80) { \ + /* Update each byte of the element */ \ + for (int k = 0, rk = SZ - 1; k < SZ; k++, rk--) { \ + tmp.VsrB(idx + rk) = j + k; \ + } \ + j += SZ; \ + } \ + } \ + \ + *t = tmp; \ +} \ + \ +void glue(helper_, glue(NAME, _le_comp))(ppc_vsr_t *t, ppc_vsr_t *b)\ +{ \ + ppc_vsr_t tmp = { .u64 = { 0, 0 } }; \ + \ + /* Iterate over the most significant byte of each element */ \ + for (int i = 0, j = 0; i < ARRAY_SIZE(b->u8); i += SZ) { \ + if (b->VsrB(ARRAY_SIZE(b->u8) - i - SZ) & 0x80) { \ + /* Update each byte of the element */ \ + for (int k = 0, rk = SZ - 1; k < SZ; k++, rk--) { \ + /* Reverse indexing of "j" */ \ + const int idx = ARRAY_SIZE(b->u8) - j - SZ; \ + tmp.VsrB(idx + rk) = i + k; \ + } \ + j += SZ; \ + } \ + } \ + \ + *t = tmp; \ +} + +XXGENPCV(XXGENPCVBM, 1) +XXGENPCV(XXGENPCVHM, 2) +XXGENPCV(XXGENPCVWM, 4) +XXGENPCV(XXGENPCVDM, 8) +#undef XXGENPCV + #if defined(HOST_WORDS_BIGENDIAN) #define VBPERMQ_INDEX(avr, i) ((avr)->u8[(i)]) #define VBPERMD_INDEX(i) (i) @@ -1392,40 +1385,33 @@ void helper_vrsqrtefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) } } -#define VRLMI(name, size, element, insert) \ -void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \ -{ \ - int i; \ - for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ - uint##size##_t src1 = a->element[i]; \ - uint##size##_t src2 = b->element[i]; \ - uint##size##_t src3 = r->element[i]; \ - uint##size##_t begin, end, shift, mask, rot_val; \ - \ - shift = extract##size(src2, 0, 6); \ - end = extract##size(src2, 8, 6); \ - begin = extract##size(src2, 16, 6); \ - rot_val = rol##size(src1, shift); \ - mask = mask_u##size(begin, end); \ - if (insert) { \ - r->element[i] = (rot_val & mask) | (src3 & ~mask); \ - } else { \ - r->element[i] = (rot_val & mask); \ - } \ - } \ +#define VRLMI(name, size, element, insert) \ +void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t desc) \ +{ \ + int i; \ + for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ + uint##size##_t src1 = a->element[i]; \ + uint##size##_t src2 = b->element[i]; \ + uint##size##_t src3 = r->element[i]; \ + uint##size##_t begin, end, shift, mask, rot_val; \ + \ + shift = extract##size(src2, 0, 6); \ + end = extract##size(src2, 8, 6); \ + begin = extract##size(src2, 16, 6); \ + rot_val = rol##size(src1, shift); \ + mask = mask_u##size(begin, end); \ + if (insert) { \ + r->element[i] = (rot_val & mask) | (src3 & ~mask); \ + } else { \ + r->element[i] = (rot_val & mask); \ + } \ + } \ } -VRLMI(vrldmi, 64, u64, 1); -VRLMI(vrlwmi, 32, u32, 1); -VRLMI(vrldnm, 64, u64, 0); -VRLMI(vrlwnm, 32, u32, 0); - -void helper_vsel(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, - ppc_avr_t *c) -{ - r->u64[0] = (a->u64[0] & ~c->u64[0]) | (b->u64[0] & c->u64[0]); - r->u64[1] = (a->u64[1] & ~c->u64[1]) | (b->u64[1] & c->u64[1]); -} +VRLMI(VRLDMI, 64, u64, 1); +VRLMI(VRLWMI, 32, u32, 1); +VRLMI(VRLDNM, 64, u64, 0); +VRLMI(VRLWNM, 32, u32, 0); void helper_vexptefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) { @@ -1619,6 +1605,34 @@ VEXTRACT(uw, u32) VEXTRACT(d, u64) #undef VEXTRACT +#define VSTRI(NAME, ELEM, NUM_ELEMS, LEFT) \ +uint32_t helper_##NAME(ppc_avr_t *t, ppc_avr_t *b) \ +{ \ + int i, idx, crf = 0; \ + \ + for (i = 0; i < NUM_ELEMS; i++) { \ + idx = LEFT ? i : NUM_ELEMS - i - 1; \ + if (b->Vsr##ELEM(idx)) { \ + t->Vsr##ELEM(idx) = b->Vsr##ELEM(idx); \ + } else { \ + crf = 0b0010; \ + break; \ + } \ + } \ + \ + for (; i < NUM_ELEMS; i++) { \ + idx = LEFT ? i : NUM_ELEMS - i - 1; \ + t->Vsr##ELEM(idx) = 0; \ + } \ + \ + return crf; \ +} +VSTRI(VSTRIBL, B, 16, true) +VSTRI(VSTRIBR, B, 16, false) +VSTRI(VSTRIHL, H, 8, true) +VSTRI(VSTRIHR, H, 8, false) +#undef VSTRI + void helper_xxextractuw(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb, uint32_t index) { @@ -1650,6 +1664,47 @@ void helper_xxinsertw(CPUPPCState *env, ppc_vsr_t *xt, *xt = t; } +void helper_XXEVAL(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c, + uint32_t desc) +{ + /* + * Instead of processing imm bit-by-bit, we'll skip the computation of + * conjunctions whose corresponding bit is unset. + */ + int bit, imm = simd_data(desc); + Int128 conj, disj = int128_zero(); + + /* Iterate over set bits from the least to the most significant bit */ + while (imm) { + /* + * Get the next bit to be processed with ctz64. Invert the result of + * ctz64 to match the indexing used by PowerISA. + */ + bit = 7 - ctzl(imm); + if (bit & 0x4) { + conj = a->s128; + } else { + conj = int128_not(a->s128); + } + if (bit & 0x2) { + conj = int128_and(conj, b->s128); + } else { + conj = int128_and(conj, int128_not(b->s128)); + } + if (bit & 0x1) { + conj = int128_and(conj, c->s128); + } else { + conj = int128_and(conj, int128_not(c->s128)); + } + disj = int128_or(disj, conj); + + /* Unset the least significant bit that is set */ + imm &= imm - 1; + } + + t->s128 = disj; +} + #define XXBLEND(name, sz) \ void glue(helper_XXBLENDV, name)(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b, \ ppc_avr_t *c, uint32_t desc) \ @@ -1665,21 +1720,6 @@ XXBLEND(W, 32) XXBLEND(D, 64) #undef XXBLEND -#define VEXT_SIGNED(name, element, cast) \ -void helper_##name(ppc_avr_t *r, ppc_avr_t *b) \ -{ \ - int i; \ - for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ - r->element[i] = (cast)b->element[i]; \ - } \ -} -VEXT_SIGNED(vextsb2w, s32, int8_t) -VEXT_SIGNED(vextsb2d, s64, int8_t) -VEXT_SIGNED(vextsh2w, s32, int16_t) -VEXT_SIGNED(vextsh2d, s64, int16_t) -VEXT_SIGNED(vextsw2d, s64, int32_t) -#undef VEXT_SIGNED - #define VNEG(name, element) \ void helper_##name(ppc_avr_t *r, ppc_avr_t *b) \ { \ diff --git a/target/ppc/machine.c b/target/ppc/machine.c index 1b63146ed1..e673944597 100644 --- a/target/ppc/machine.c +++ b/target/ppc/machine.c @@ -2,6 +2,7 @@ #include "cpu.h" #include "exec/exec-all.h" #include "sysemu/kvm.h" +#include "sysemu/tcg.h" #include "helper_regs.h" #include "mmu-hash64.h" #include "migration/cpu.h" @@ -20,7 +21,10 @@ static void post_load_update_msr(CPUPPCState *env) */ env->msr ^= env->msr_mask & ~((1ULL << MSR_TGPR) | MSR_HVB); ppc_store_msr(env, msr); - pmu_update_summaries(env); + + if (tcg_enabled()) { + pmu_update_summaries(env); + } } static int get_avr(QEMUFile *f, void *pv, size_t size, diff --git a/target/ppc/meson.build b/target/ppc/meson.build index a49a8911e0..79beaff147 100644 --- a/target/ppc/meson.build +++ b/target/ppc/meson.build @@ -16,6 +16,7 @@ ppc_ss.add(when: 'CONFIG_TCG', if_true: files( 'misc_helper.c', 'timebase_helper.c', 'translate.c', + 'power8-pmu.c', )) ppc_ss.add(libdecnumber) @@ -51,7 +52,6 @@ ppc_softmmu_ss.add(when: 'TARGET_PPC64', if_true: files( 'mmu-book3s-v3.c', 'mmu-hash64.c', 'mmu-radix64.c', - 'power8-pmu.c', )) target_arch += {'ppc': ppc_ss} diff --git a/target/ppc/power8-pmu.c b/target/ppc/power8-pmu.c index 236e8e66e9..beeab5c494 100644 --- a/target/ppc/power8-pmu.c +++ b/target/ppc/power8-pmu.c @@ -222,6 +222,20 @@ static void pmu_update_overflow_timers(CPUPPCState *env) } } +static void pmu_delete_timers(CPUPPCState *env) +{ + QEMUTimer *pmc_overflow_timer; + int sprn; + + for (sprn = SPR_POWER_PMC1; sprn <= SPR_POWER_PMC6; sprn++) { + pmc_overflow_timer = get_cyc_overflow_timer(env, sprn); + + if (pmc_overflow_timer) { + timer_del(pmc_overflow_timer); + } + } +} + void helper_store_mmcr0(CPUPPCState *env, target_ulong value) { bool hflags_pmcc0 = (value & MMCR0_PMCC0) != 0; @@ -271,12 +285,29 @@ static void fire_PMC_interrupt(PowerPCCPU *cpu) { CPUPPCState *env = &cpu->env; - if (!(env->spr[SPR_POWER_MMCR0] & MMCR0_EBE)) { - return; + pmu_update_cycles(env); + + if (env->spr[SPR_POWER_MMCR0] & MMCR0_FCECE) { + env->spr[SPR_POWER_MMCR0] &= ~MMCR0_FCECE; + env->spr[SPR_POWER_MMCR0] |= MMCR0_FC; + + /* Changing MMCR0_FC requires a new HFLAGS_INSN_CNT calc */ + pmu_update_summaries(env); + + /* + * Delete all pending timers if we need to freeze + * the PMC. We'll restart them when the PMC starts + * running again. + */ + pmu_delete_timers(env); + } + + if (env->spr[SPR_POWER_MMCR0] & MMCR0_PMAE) { + env->spr[SPR_POWER_MMCR0] &= ~MMCR0_PMAE; + env->spr[SPR_POWER_MMCR0] |= MMCR0_PMAO; } - /* PMC interrupt not implemented yet */ - return; + raise_ebb_perfm_exception(env); } /* This helper assumes that the PMC is running. */ diff --git a/target/ppc/power8-pmu.h b/target/ppc/power8-pmu.h index a839199561..256d90f523 100644 --- a/target/ppc/power8-pmu.h +++ b/target/ppc/power8-pmu.h @@ -13,11 +13,11 @@ #ifndef POWER8_PMU #define POWER8_PMU -void cpu_ppc_pmu_init(CPUPPCState *env); - #if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY) +void cpu_ppc_pmu_init(CPUPPCState *env); void pmu_update_summaries(CPUPPCState *env); #else +static inline void cpu_ppc_pmu_init(CPUPPCState *env) { } static inline void pmu_update_summaries(CPUPPCState *env) { } #endif diff --git a/target/ppc/translate.c b/target/ppc/translate.c index ecc5a104e0..408ae26173 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -6604,10 +6604,29 @@ static int times_16(DisasContext *ctx, int x) #define TRANS(NAME, FUNC, ...) \ static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ { return FUNC(ctx, a, __VA_ARGS__); } +#define TRANS_FLAGS(FLAGS, NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ + { \ + REQUIRE_INSNS_FLAGS(ctx, FLAGS); \ + return FUNC(ctx, a, __VA_ARGS__); \ + } +#define TRANS_FLAGS2(FLAGS2, NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ + { \ + REQUIRE_INSNS_FLAGS2(ctx, FLAGS2); \ + return FUNC(ctx, a, __VA_ARGS__); \ + } #define TRANS64(NAME, FUNC, ...) \ static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ { REQUIRE_64BIT(ctx); return FUNC(ctx, a, __VA_ARGS__); } +#define TRANS64_FLAGS2(FLAGS2, NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ + { \ + REQUIRE_64BIT(ctx); \ + REQUIRE_INSNS_FLAGS2(ctx, FLAGS2); \ + return FUNC(ctx, a, __VA_ARGS__); \ + } /* TODO: More TRANS* helpers for extra insn_flags checks. */ @@ -6649,49 +6668,24 @@ static bool resolve_PLS_D(DisasContext *ctx, arg_D *d, arg_PLS_D *a) #include "translate/branch-impl.c.inc" -/* Handles lfdp, lxsd, lxssp */ +/* Handles lfdp */ static void gen_dform39(DisasContext *ctx) { - switch (ctx->opcode & 0x3) { - case 0: /* lfdp */ + if ((ctx->opcode & 0x3) == 0) { if (ctx->insns_flags2 & PPC2_ISA205) { return gen_lfdp(ctx); } - break; - case 2: /* lxsd */ - if (ctx->insns_flags2 & PPC2_ISA300) { - return gen_lxsd(ctx); - } - break; - case 3: /* lxssp */ - if (ctx->insns_flags2 & PPC2_ISA300) { - return gen_lxssp(ctx); - } - break; } return gen_invalid(ctx); } -/* handles stfdp, lxv, stxsd, stxssp lxvx */ +/* Handles stfdp */ static void gen_dform3D(DisasContext *ctx) { - if ((ctx->opcode & 3) != 1) { /* DS-FORM */ - switch (ctx->opcode & 0x3) { - case 0: /* stfdp */ - if (ctx->insns_flags2 & PPC2_ISA205) { - return gen_stfdp(ctx); - } - break; - case 2: /* stxsd */ - if (ctx->insns_flags2 & PPC2_ISA300) { - return gen_stxsd(ctx); - } - break; - case 3: /* stxssp */ - if (ctx->insns_flags2 & PPC2_ISA300) { - return gen_stxssp(ctx); - } - break; + if ((ctx->opcode & 3) == 0) { /* DS-FORM */ + /* stfdp */ + if (ctx->insns_flags2 & PPC2_ISA205) { + return gen_stfdp(ctx); } } return gen_invalid(ctx); diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc index d5e02fd7f2..f91bee839d 100644 --- a/target/ppc/translate/vmx-impl.c.inc +++ b/target/ppc/translate/vmx-impl.c.inc @@ -798,45 +798,7 @@ static void trans_vclzd(DisasContext *ctx) tcg_temp_free_i64(avr); } -GEN_VXFORM(vmuloub, 4, 0); -GEN_VXFORM(vmulouh, 4, 1); -GEN_VXFORM(vmulouw, 4, 2); GEN_VXFORM_V(vmuluwm, MO_32, tcg_gen_gvec_mul, 4, 2); -GEN_VXFORM_DUAL(vmulouw, PPC_ALTIVEC, PPC_NONE, - vmuluwm, PPC_NONE, PPC2_ALTIVEC_207) -GEN_VXFORM(vmulosb, 4, 4); -GEN_VXFORM(vmulosh, 4, 5); -GEN_VXFORM(vmulosw, 4, 6); -GEN_VXFORM_V(vmulld, MO_64, tcg_gen_gvec_mul, 4, 7); -GEN_VXFORM(vmuleub, 4, 8); -GEN_VXFORM(vmuleuh, 4, 9); -GEN_VXFORM(vmuleuw, 4, 10); -GEN_VXFORM(vmulhuw, 4, 10); -GEN_VXFORM(vmulhud, 4, 11); -GEN_VXFORM_DUAL(vmuleuw, PPC_ALTIVEC, PPC_NONE, - vmulhuw, PPC_NONE, PPC2_ISA310); -GEN_VXFORM(vmulesb, 4, 12); -GEN_VXFORM(vmulesh, 4, 13); -GEN_VXFORM(vmulesw, 4, 14); -GEN_VXFORM(vmulhsw, 4, 14); -GEN_VXFORM_DUAL(vmulesw, PPC_ALTIVEC, PPC_NONE, - vmulhsw, PPC_NONE, PPC2_ISA310); -GEN_VXFORM(vmulhsd, 4, 15); -GEN_VXFORM_V(vslb, MO_8, tcg_gen_gvec_shlv, 2, 4); -GEN_VXFORM_V(vslh, MO_16, tcg_gen_gvec_shlv, 2, 5); -GEN_VXFORM_V(vslw, MO_32, tcg_gen_gvec_shlv, 2, 6); -GEN_VXFORM(vrlwnm, 2, 6); -GEN_VXFORM_DUAL(vslw, PPC_ALTIVEC, PPC_NONE, \ - vrlwnm, PPC_NONE, PPC2_ISA300) -GEN_VXFORM_V(vsld, MO_64, tcg_gen_gvec_shlv, 2, 23); -GEN_VXFORM_V(vsrb, MO_8, tcg_gen_gvec_shrv, 2, 8); -GEN_VXFORM_V(vsrh, MO_16, tcg_gen_gvec_shrv, 2, 9); -GEN_VXFORM_V(vsrw, MO_32, tcg_gen_gvec_shrv, 2, 10); -GEN_VXFORM_V(vsrd, MO_64, tcg_gen_gvec_shrv, 2, 27); -GEN_VXFORM_V(vsrab, MO_8, tcg_gen_gvec_sarv, 2, 12); -GEN_VXFORM_V(vsrah, MO_16, tcg_gen_gvec_sarv, 2, 13); -GEN_VXFORM_V(vsraw, MO_32, tcg_gen_gvec_sarv, 2, 14); -GEN_VXFORM_V(vsrad, MO_64, tcg_gen_gvec_sarv, 2, 15); GEN_VXFORM(vsrv, 2, 28); GEN_VXFORM(vslv, 2, 29); GEN_VXFORM(vslo, 6, 16); @@ -844,6 +806,387 @@ GEN_VXFORM(vsro, 6, 17); GEN_VXFORM(vaddcuw, 0, 6); GEN_VXFORM(vsubcuw, 0, 22); +static bool do_vector_gvec3_VX(DisasContext *ctx, arg_VX *a, int vece, + void (*gen_gvec)(unsigned, uint32_t, uint32_t, + uint32_t, uint32_t, uint32_t)) +{ + REQUIRE_VECTOR(ctx); + + gen_gvec(vece, avr_full_offset(a->vrt), avr_full_offset(a->vra), + avr_full_offset(a->vrb), 16, 16); + + return true; +} + +TRANS_FLAGS(ALTIVEC, VSLB, do_vector_gvec3_VX, MO_8, tcg_gen_gvec_shlv); +TRANS_FLAGS(ALTIVEC, VSLH, do_vector_gvec3_VX, MO_16, tcg_gen_gvec_shlv); +TRANS_FLAGS(ALTIVEC, VSLW, do_vector_gvec3_VX, MO_32, tcg_gen_gvec_shlv); +TRANS_FLAGS2(ALTIVEC_207, VSLD, do_vector_gvec3_VX, MO_64, tcg_gen_gvec_shlv); + +TRANS_FLAGS(ALTIVEC, VSRB, do_vector_gvec3_VX, MO_8, tcg_gen_gvec_shrv); +TRANS_FLAGS(ALTIVEC, VSRH, do_vector_gvec3_VX, MO_16, tcg_gen_gvec_shrv); +TRANS_FLAGS(ALTIVEC, VSRW, do_vector_gvec3_VX, MO_32, tcg_gen_gvec_shrv); +TRANS_FLAGS2(ALTIVEC_207, VSRD, do_vector_gvec3_VX, MO_64, tcg_gen_gvec_shrv); + +TRANS_FLAGS(ALTIVEC, VSRAB, do_vector_gvec3_VX, MO_8, tcg_gen_gvec_sarv); +TRANS_FLAGS(ALTIVEC, VSRAH, do_vector_gvec3_VX, MO_16, tcg_gen_gvec_sarv); +TRANS_FLAGS(ALTIVEC, VSRAW, do_vector_gvec3_VX, MO_32, tcg_gen_gvec_sarv); +TRANS_FLAGS2(ALTIVEC_207, VSRAD, do_vector_gvec3_VX, MO_64, tcg_gen_gvec_sarv); + +TRANS_FLAGS(ALTIVEC, VRLB, do_vector_gvec3_VX, MO_8, tcg_gen_gvec_rotlv) +TRANS_FLAGS(ALTIVEC, VRLH, do_vector_gvec3_VX, MO_16, tcg_gen_gvec_rotlv) +TRANS_FLAGS(ALTIVEC, VRLW, do_vector_gvec3_VX, MO_32, tcg_gen_gvec_rotlv) +TRANS_FLAGS2(ALTIVEC_207, VRLD, do_vector_gvec3_VX, MO_64, tcg_gen_gvec_rotlv) + +static TCGv_vec do_vrl_mask_vec(unsigned vece, TCGv_vec vrb) +{ + TCGv_vec t0 = tcg_temp_new_vec_matching(vrb), + t1 = tcg_temp_new_vec_matching(vrb), + t2 = tcg_temp_new_vec_matching(vrb), + ones = tcg_constant_vec_matching(vrb, vece, -1); + + /* Extract b and e */ + tcg_gen_dupi_vec(vece, t2, (8 << vece) - 1); + + tcg_gen_shri_vec(vece, t0, vrb, 16); + tcg_gen_and_vec(vece, t0, t0, t2); + + tcg_gen_shri_vec(vece, t1, vrb, 8); + tcg_gen_and_vec(vece, t1, t1, t2); + + /* Compare b and e to negate the mask where begin > end */ + tcg_gen_cmp_vec(TCG_COND_GT, vece, t2, t0, t1); + + /* Create the mask with (~0 >> b) ^ ((~0 >> e) >> 1) */ + tcg_gen_shrv_vec(vece, t0, ones, t0); + tcg_gen_shrv_vec(vece, t1, ones, t1); + tcg_gen_shri_vec(vece, t1, t1, 1); + tcg_gen_xor_vec(vece, t0, t0, t1); + + /* negate the mask */ + tcg_gen_xor_vec(vece, t0, t0, t2); + + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + + return t0; +} + +static void gen_vrlnm_vec(unsigned vece, TCGv_vec vrt, TCGv_vec vra, + TCGv_vec vrb) +{ + TCGv_vec mask, n = tcg_temp_new_vec_matching(vrt); + + /* Create the mask */ + mask = do_vrl_mask_vec(vece, vrb); + + /* Extract n */ + tcg_gen_dupi_vec(vece, n, (8 << vece) - 1); + tcg_gen_and_vec(vece, n, vrb, n); + + /* Rotate and mask */ + tcg_gen_rotlv_vec(vece, vrt, vra, n); + tcg_gen_and_vec(vece, vrt, vrt, mask); + + tcg_temp_free_vec(n); + tcg_temp_free_vec(mask); +} + +static bool do_vrlnm(DisasContext *ctx, arg_VX *a, int vece) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_cmp_vec, INDEX_op_rotlv_vec, INDEX_op_sari_vec, + INDEX_op_shli_vec, INDEX_op_shri_vec, INDEX_op_shrv_vec, 0 + }; + static const GVecGen3 ops[2] = { + { + .fniv = gen_vrlnm_vec, + .fno = gen_helper_VRLWNM, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 + }, + { + .fniv = gen_vrlnm_vec, + .fno = gen_helper_VRLDNM, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 + } + }; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VSX(ctx); + + tcg_gen_gvec_3(avr_full_offset(a->vrt), avr_full_offset(a->vra), + avr_full_offset(a->vrb), 16, 16, &ops[vece - 2]); + + return true; +} + +TRANS(VRLWNM, do_vrlnm, MO_32) +TRANS(VRLDNM, do_vrlnm, MO_64) + +static void gen_vrlmi_vec(unsigned vece, TCGv_vec vrt, TCGv_vec vra, + TCGv_vec vrb) +{ + TCGv_vec mask, n = tcg_temp_new_vec_matching(vrt), + tmp = tcg_temp_new_vec_matching(vrt); + + /* Create the mask */ + mask = do_vrl_mask_vec(vece, vrb); + + /* Extract n */ + tcg_gen_dupi_vec(vece, n, (8 << vece) - 1); + tcg_gen_and_vec(vece, n, vrb, n); + + /* Rotate and insert */ + tcg_gen_rotlv_vec(vece, tmp, vra, n); + tcg_gen_bitsel_vec(vece, vrt, mask, tmp, vrt); + + tcg_temp_free_vec(n); + tcg_temp_free_vec(tmp); + tcg_temp_free_vec(mask); +} + +static bool do_vrlmi(DisasContext *ctx, arg_VX *a, int vece) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_cmp_vec, INDEX_op_rotlv_vec, INDEX_op_sari_vec, + INDEX_op_shli_vec, INDEX_op_shri_vec, INDEX_op_shrv_vec, 0 + }; + static const GVecGen3 ops[2] = { + { + .fniv = gen_vrlmi_vec, + .fno = gen_helper_VRLWMI, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 + }, + { + .fniv = gen_vrlnm_vec, + .fno = gen_helper_VRLDMI, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 + } + }; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VSX(ctx); + + tcg_gen_gvec_3(avr_full_offset(a->vrt), avr_full_offset(a->vra), + avr_full_offset(a->vrb), 16, 16, &ops[vece - 2]); + + return true; +} + +TRANS(VRLWMI, do_vrlmi, MO_32) +TRANS(VRLDMI, do_vrlmi, MO_64) + +static bool do_vector_shift_quad(DisasContext *ctx, arg_VX *a, bool right, + bool alg) +{ + TCGv_i64 hi, lo, t0, t1, n, zero = tcg_constant_i64(0); + + REQUIRE_VECTOR(ctx); + + n = tcg_temp_new_i64(); + hi = tcg_temp_new_i64(); + lo = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + t1 = tcg_const_i64(0); + + get_avr64(lo, a->vra, false); + get_avr64(hi, a->vra, true); + + get_avr64(n, a->vrb, true); + + tcg_gen_andi_i64(t0, n, 64); + if (right) { + tcg_gen_movcond_i64(TCG_COND_NE, lo, t0, zero, hi, lo); + if (alg) { + tcg_gen_sari_i64(t1, lo, 63); + } + tcg_gen_movcond_i64(TCG_COND_NE, hi, t0, zero, t1, hi); + } else { + tcg_gen_movcond_i64(TCG_COND_NE, hi, t0, zero, lo, hi); + tcg_gen_movcond_i64(TCG_COND_NE, lo, t0, zero, zero, lo); + } + tcg_gen_andi_i64(n, n, 0x3F); + + if (right) { + if (alg) { + tcg_gen_sar_i64(t0, hi, n); + } else { + tcg_gen_shr_i64(t0, hi, n); + } + } else { + tcg_gen_shl_i64(t0, lo, n); + } + set_avr64(a->vrt, t0, right); + + if (right) { + tcg_gen_shr_i64(lo, lo, n); + } else { + tcg_gen_shl_i64(hi, hi, n); + } + tcg_gen_xori_i64(n, n, 63); + if (right) { + tcg_gen_shl_i64(hi, hi, n); + tcg_gen_shli_i64(hi, hi, 1); + } else { + tcg_gen_shr_i64(lo, lo, n); + tcg_gen_shri_i64(lo, lo, 1); + } + tcg_gen_or_i64(hi, hi, lo); + set_avr64(a->vrt, hi, !right); + + tcg_temp_free_i64(hi); + tcg_temp_free_i64(lo); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(n); + + return true; +} + +TRANS_FLAGS2(ISA310, VSLQ, do_vector_shift_quad, false, false); +TRANS_FLAGS2(ISA310, VSRQ, do_vector_shift_quad, true, false); +TRANS_FLAGS2(ISA310, VSRAQ, do_vector_shift_quad, true, true); + +static void do_vrlq_mask(TCGv_i64 mh, TCGv_i64 ml, TCGv_i64 b, TCGv_i64 e) +{ + TCGv_i64 th, tl, t0, t1, zero = tcg_constant_i64(0), + ones = tcg_constant_i64(-1); + + th = tcg_temp_new_i64(); + tl = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + + /* m = ~0 >> b */ + tcg_gen_andi_i64(t0, b, 64); + tcg_gen_movcond_i64(TCG_COND_NE, t1, t0, zero, zero, ones); + tcg_gen_andi_i64(t0, b, 0x3F); + tcg_gen_shr_i64(mh, t1, t0); + tcg_gen_shr_i64(ml, ones, t0); + tcg_gen_xori_i64(t0, t0, 63); + tcg_gen_shl_i64(t1, t1, t0); + tcg_gen_shli_i64(t1, t1, 1); + tcg_gen_or_i64(ml, t1, ml); + + /* t = ~0 >> e */ + tcg_gen_andi_i64(t0, e, 64); + tcg_gen_movcond_i64(TCG_COND_NE, t1, t0, zero, zero, ones); + tcg_gen_andi_i64(t0, e, 0x3F); + tcg_gen_shr_i64(th, t1, t0); + tcg_gen_shr_i64(tl, ones, t0); + tcg_gen_xori_i64(t0, t0, 63); + tcg_gen_shl_i64(t1, t1, t0); + tcg_gen_shli_i64(t1, t1, 1); + tcg_gen_or_i64(tl, t1, tl); + + /* t = t >> 1 */ + tcg_gen_shli_i64(t0, th, 63); + tcg_gen_shri_i64(tl, tl, 1); + tcg_gen_shri_i64(th, th, 1); + tcg_gen_or_i64(tl, t0, tl); + + /* m = m ^ t */ + tcg_gen_xor_i64(mh, mh, th); + tcg_gen_xor_i64(ml, ml, tl); + + /* Negate the mask if begin > end */ + tcg_gen_movcond_i64(TCG_COND_GT, t0, b, e, ones, zero); + + tcg_gen_xor_i64(mh, mh, t0); + tcg_gen_xor_i64(ml, ml, t0); + + tcg_temp_free_i64(th); + tcg_temp_free_i64(tl); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); +} + +static bool do_vector_rotl_quad(DisasContext *ctx, arg_VX *a, bool mask, + bool insert) +{ + TCGv_i64 ah, al, vrb, n, t0, t1, zero = tcg_constant_i64(0); + + REQUIRE_VECTOR(ctx); + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + + ah = tcg_temp_new_i64(); + al = tcg_temp_new_i64(); + vrb = tcg_temp_new_i64(); + n = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + + get_avr64(ah, a->vra, true); + get_avr64(al, a->vra, false); + get_avr64(vrb, a->vrb, true); + + tcg_gen_mov_i64(t0, ah); + tcg_gen_andi_i64(t1, vrb, 64); + tcg_gen_movcond_i64(TCG_COND_NE, ah, t1, zero, al, ah); + tcg_gen_movcond_i64(TCG_COND_NE, al, t1, zero, t0, al); + tcg_gen_andi_i64(n, vrb, 0x3F); + + tcg_gen_shl_i64(t0, ah, n); + tcg_gen_shl_i64(t1, al, n); + + tcg_gen_xori_i64(n, n, 63); + + tcg_gen_shr_i64(al, al, n); + tcg_gen_shri_i64(al, al, 1); + tcg_gen_or_i64(t0, al, t0); + + tcg_gen_shr_i64(ah, ah, n); + tcg_gen_shri_i64(ah, ah, 1); + tcg_gen_or_i64(t1, ah, t1); + + if (mask || insert) { + tcg_gen_shri_i64(n, vrb, 8); + tcg_gen_shri_i64(vrb, vrb, 16); + tcg_gen_andi_i64(n, n, 0x7f); + tcg_gen_andi_i64(vrb, vrb, 0x7f); + + do_vrlq_mask(ah, al, vrb, n); + + tcg_gen_and_i64(t0, t0, ah); + tcg_gen_and_i64(t1, t1, al); + + if (insert) { + get_avr64(n, a->vrt, true); + get_avr64(vrb, a->vrt, false); + tcg_gen_not_i64(ah, ah); + tcg_gen_not_i64(al, al); + tcg_gen_and_i64(n, n, ah); + tcg_gen_and_i64(vrb, vrb, al); + tcg_gen_or_i64(t0, t0, n); + tcg_gen_or_i64(t1, t1, vrb); + } + } + + set_avr64(a->vrt, t0, true); + set_avr64(a->vrt, t1, false); + + tcg_temp_free_i64(ah); + tcg_temp_free_i64(al); + tcg_temp_free_i64(vrb); + tcg_temp_free_i64(n); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + + return true; +} + +TRANS(VRLQ, do_vector_rotl_quad, false, false) +TRANS(VRLQNM, do_vector_rotl_quad, true, false) +TRANS(VRLQMI, do_vector_rotl_quad, false, true) + #define GEN_VXFORM_SAT(NAME, VECE, NORM, SAT, OPC2, OPC3) \ static void glue(glue(gen_, NAME), _vec)(unsigned vece, TCGv_vec t, \ TCGv_vec sat, TCGv_vec a, \ @@ -909,20 +1252,7 @@ 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_V(vrlb, MO_8, tcg_gen_gvec_rotlv, 2, 0); -GEN_VXFORM_V(vrlh, MO_16, tcg_gen_gvec_rotlv, 2, 1); -GEN_VXFORM_V(vrlw, MO_32, tcg_gen_gvec_rotlv, 2, 2); -GEN_VXFORM(vrlwmi, 2, 2); -GEN_VXFORM_DUAL(vrlw, PPC_ALTIVEC, PPC_NONE, \ - vrlwmi, PPC_NONE, PPC2_ISA300) -GEN_VXFORM_V(vrld, MO_64, tcg_gen_gvec_rotlv, 2, 3); -GEN_VXFORM(vrldmi, 2, 3); -GEN_VXFORM_DUAL(vrld, PPC_NONE, PPC2_ALTIVEC_207, \ - vrldmi, PPC_NONE, PPC2_ISA300) GEN_VXFORM_TRANS(vsl, 2, 7); -GEN_VXFORM(vrldnm, 2, 7); -GEN_VXFORM_DUAL(vsl, PPC_ALTIVEC, PPC_NONE, \ - vrldnm, PPC_NONE, PPC2_ISA300) GEN_VXFORM_TRANS(vsr, 2, 11); GEN_VXFORM_ENV(vpkuhum, 7, 0); GEN_VXFORM_ENV(vpkuwum, 7, 1); @@ -1008,41 +1338,252 @@ static void glue(gen_, name0##_##name1)(DisasContext *ctx) \ } \ } -GEN_VXRFORM(vcmpequb, 3, 0) -GEN_VXRFORM(vcmpequh, 3, 1) -GEN_VXRFORM(vcmpequw, 3, 2) -GEN_VXRFORM(vcmpequd, 3, 3) -GEN_VXRFORM(vcmpnezb, 3, 4) -GEN_VXRFORM(vcmpnezh, 3, 5) -GEN_VXRFORM(vcmpnezw, 3, 6) -GEN_VXRFORM(vcmpgtsb, 3, 12) -GEN_VXRFORM(vcmpgtsh, 3, 13) -GEN_VXRFORM(vcmpgtsw, 3, 14) -GEN_VXRFORM(vcmpgtsd, 3, 15) -GEN_VXRFORM(vcmpgtub, 3, 8) -GEN_VXRFORM(vcmpgtuh, 3, 9) -GEN_VXRFORM(vcmpgtuw, 3, 10) -GEN_VXRFORM(vcmpgtud, 3, 11) +static void do_vcmp_rc(int vrt) +{ + TCGv_i64 tmp, set, clr; + + tmp = tcg_temp_new_i64(); + set = tcg_temp_new_i64(); + clr = tcg_temp_new_i64(); + + get_avr64(tmp, vrt, true); + tcg_gen_mov_i64(set, tmp); + get_avr64(tmp, vrt, false); + tcg_gen_or_i64(clr, set, tmp); + tcg_gen_and_i64(set, set, tmp); + + tcg_gen_setcondi_i64(TCG_COND_EQ, clr, clr, 0); + tcg_gen_shli_i64(clr, clr, 1); + + tcg_gen_setcondi_i64(TCG_COND_EQ, set, set, -1); + tcg_gen_shli_i64(set, set, 3); + + tcg_gen_or_i64(tmp, set, clr); + tcg_gen_extrl_i64_i32(cpu_crf[6], tmp); + + tcg_temp_free_i64(tmp); + tcg_temp_free_i64(set); + tcg_temp_free_i64(clr); +} + +static bool do_vcmp(DisasContext *ctx, arg_VC *a, TCGCond cond, int vece) +{ + REQUIRE_VECTOR(ctx); + + tcg_gen_gvec_cmp(cond, vece, avr_full_offset(a->vrt), + avr_full_offset(a->vra), avr_full_offset(a->vrb), 16, 16); + + if (a->rc) { + do_vcmp_rc(a->vrt); + } + + return true; +} + +TRANS_FLAGS(ALTIVEC, VCMPEQUB, do_vcmp, TCG_COND_EQ, MO_8) +TRANS_FLAGS(ALTIVEC, VCMPEQUH, do_vcmp, TCG_COND_EQ, MO_16) +TRANS_FLAGS(ALTIVEC, VCMPEQUW, do_vcmp, TCG_COND_EQ, MO_32) +TRANS_FLAGS2(ALTIVEC_207, VCMPEQUD, do_vcmp, TCG_COND_EQ, MO_64) + +TRANS_FLAGS(ALTIVEC, VCMPGTSB, do_vcmp, TCG_COND_GT, MO_8) +TRANS_FLAGS(ALTIVEC, VCMPGTSH, do_vcmp, TCG_COND_GT, MO_16) +TRANS_FLAGS(ALTIVEC, VCMPGTSW, do_vcmp, TCG_COND_GT, MO_32) +TRANS_FLAGS2(ALTIVEC_207, VCMPGTSD, do_vcmp, TCG_COND_GT, MO_64) +TRANS_FLAGS(ALTIVEC, VCMPGTUB, do_vcmp, TCG_COND_GTU, MO_8) +TRANS_FLAGS(ALTIVEC, VCMPGTUH, do_vcmp, TCG_COND_GTU, MO_16) +TRANS_FLAGS(ALTIVEC, VCMPGTUW, do_vcmp, TCG_COND_GTU, MO_32) +TRANS_FLAGS2(ALTIVEC_207, VCMPGTUD, do_vcmp, TCG_COND_GTU, MO_64) + +TRANS_FLAGS2(ISA300, VCMPNEB, do_vcmp, TCG_COND_NE, MO_8) +TRANS_FLAGS2(ISA300, VCMPNEH, do_vcmp, TCG_COND_NE, MO_16) +TRANS_FLAGS2(ISA300, VCMPNEW, do_vcmp, TCG_COND_NE, MO_32) + +static void gen_vcmpnez_vec(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t0, t1, zero; + + t0 = tcg_temp_new_vec_matching(t); + t1 = tcg_temp_new_vec_matching(t); + zero = tcg_constant_vec_matching(t, vece, 0); + + tcg_gen_cmp_vec(TCG_COND_EQ, vece, t0, a, zero); + tcg_gen_cmp_vec(TCG_COND_EQ, vece, t1, b, zero); + tcg_gen_cmp_vec(TCG_COND_NE, vece, t, a, b); + + tcg_gen_or_vec(vece, t, t, t0); + tcg_gen_or_vec(vece, t, t, t1); + + tcg_temp_free_vec(t0); + tcg_temp_free_vec(t1); +} + +static bool do_vcmpnez(DisasContext *ctx, arg_VC *a, int vece) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_cmp_vec, 0 + }; + static const GVecGen3 ops[3] = { + { + .fniv = gen_vcmpnez_vec, + .fno = gen_helper_VCMPNEZB, + .opt_opc = vecop_list, + .vece = MO_8 + }, + { + .fniv = gen_vcmpnez_vec, + .fno = gen_helper_VCMPNEZH, + .opt_opc = vecop_list, + .vece = MO_16 + }, + { + .fniv = gen_vcmpnez_vec, + .fno = gen_helper_VCMPNEZW, + .opt_opc = vecop_list, + .vece = MO_32 + } + }; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VECTOR(ctx); + + tcg_gen_gvec_3(avr_full_offset(a->vrt), avr_full_offset(a->vra), + avr_full_offset(a->vrb), 16, 16, &ops[vece]); + + if (a->rc) { + do_vcmp_rc(a->vrt); + } + + return true; +} + +TRANS(VCMPNEZB, do_vcmpnez, MO_8) +TRANS(VCMPNEZH, do_vcmpnez, MO_16) +TRANS(VCMPNEZW, do_vcmpnez, MO_32) + +static bool trans_VCMPEQUQ(DisasContext *ctx, arg_VC *a) +{ + TCGv_i64 t0, t1, t2; + + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + t2 = tcg_temp_new_i64(); + + get_avr64(t0, a->vra, true); + get_avr64(t1, a->vrb, true); + tcg_gen_xor_i64(t2, t0, t1); + + get_avr64(t0, a->vra, false); + get_avr64(t1, a->vrb, false); + tcg_gen_xor_i64(t1, t0, t1); + + tcg_gen_or_i64(t1, t1, t2); + tcg_gen_setcondi_i64(TCG_COND_EQ, t1, t1, 0); + tcg_gen_neg_i64(t1, t1); + + set_avr64(a->vrt, t1, true); + set_avr64(a->vrt, t1, false); + + if (a->rc) { + tcg_gen_extrl_i64_i32(cpu_crf[6], t1); + tcg_gen_andi_i32(cpu_crf[6], cpu_crf[6], 0xa); + tcg_gen_xori_i32(cpu_crf[6], cpu_crf[6], 0x2); + } + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t2); + + return true; +} + +static bool do_vcmpgtq(DisasContext *ctx, arg_VC *a, bool sign) +{ + TCGv_i64 t0, t1, t2; + + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + t2 = tcg_temp_new_i64(); + + get_avr64(t0, a->vra, false); + get_avr64(t1, a->vrb, false); + tcg_gen_setcond_i64(TCG_COND_GTU, t2, t0, t1); + + get_avr64(t0, a->vra, true); + get_avr64(t1, a->vrb, true); + tcg_gen_movcond_i64(TCG_COND_EQ, t2, t0, t1, t2, tcg_constant_i64(0)); + tcg_gen_setcond_i64(sign ? TCG_COND_GT : TCG_COND_GTU, t1, t0, t1); + + tcg_gen_or_i64(t1, t1, t2); + tcg_gen_neg_i64(t1, t1); + + set_avr64(a->vrt, t1, true); + set_avr64(a->vrt, t1, false); + + if (a->rc) { + tcg_gen_extrl_i64_i32(cpu_crf[6], t1); + tcg_gen_andi_i32(cpu_crf[6], cpu_crf[6], 0xa); + tcg_gen_xori_i32(cpu_crf[6], cpu_crf[6], 0x2); + } + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t2); + + return true; +} + +TRANS(VCMPGTSQ, do_vcmpgtq, true) +TRANS(VCMPGTUQ, do_vcmpgtq, false) + +static bool do_vcmpq(DisasContext *ctx, arg_VX_bf *a, bool sign) +{ + TCGv_i64 vra, vrb; + TCGLabel *gt, *lt, *done; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + vra = tcg_temp_local_new_i64(); + vrb = tcg_temp_local_new_i64(); + gt = gen_new_label(); + lt = gen_new_label(); + done = gen_new_label(); + + get_avr64(vra, a->vra, true); + get_avr64(vrb, a->vrb, true); + tcg_gen_brcond_i64((sign ? TCG_COND_GT : TCG_COND_GTU), vra, vrb, gt); + tcg_gen_brcond_i64((sign ? TCG_COND_LT : TCG_COND_LTU), vra, vrb, lt); + + get_avr64(vra, a->vra, false); + get_avr64(vrb, a->vrb, false); + tcg_gen_brcond_i64(TCG_COND_GTU, vra, vrb, gt); + tcg_gen_brcond_i64(TCG_COND_LTU, vra, vrb, lt); + + tcg_gen_movi_i32(cpu_crf[a->bf], CRF_EQ); + tcg_gen_br(done); + + gen_set_label(gt); + tcg_gen_movi_i32(cpu_crf[a->bf], CRF_GT); + tcg_gen_br(done); + + gen_set_label(lt); + tcg_gen_movi_i32(cpu_crf[a->bf], CRF_LT); + tcg_gen_br(done); + + gen_set_label(done); + tcg_temp_free_i64(vra); + tcg_temp_free_i64(vrb); + + return true; +} + +TRANS(VCMPSQ, do_vcmpq, true) +TRANS(VCMPUQ, do_vcmpq, false) + GEN_VXRFORM(vcmpeqfp, 3, 3) GEN_VXRFORM(vcmpgefp, 3, 7) GEN_VXRFORM(vcmpgtfp, 3, 11) GEN_VXRFORM(vcmpbfp, 3, 15) -GEN_VXRFORM(vcmpneb, 3, 0) -GEN_VXRFORM(vcmpneh, 3, 1) -GEN_VXRFORM(vcmpnew, 3, 2) - -GEN_VXRFORM_DUAL(vcmpequb, PPC_ALTIVEC, PPC_NONE, \ - vcmpneb, PPC_NONE, PPC2_ISA300) -GEN_VXRFORM_DUAL(vcmpequh, PPC_ALTIVEC, PPC_NONE, \ - vcmpneh, PPC_NONE, PPC2_ISA300) -GEN_VXRFORM_DUAL(vcmpequw, PPC_ALTIVEC, PPC_NONE, \ - vcmpnew, PPC_NONE, PPC2_ISA300) -GEN_VXRFORM_DUAL(vcmpeqfp, PPC_ALTIVEC, PPC_NONE, \ - vcmpequd, PPC_NONE, PPC2_ALTIVEC_207) -GEN_VXRFORM_DUAL(vcmpbfp, PPC_ALTIVEC, PPC_NONE, \ - vcmpgtsd, PPC_NONE, PPC2_ALTIVEC_207) -GEN_VXRFORM_DUAL(vcmpgtfp, PPC_ALTIVEC, PPC_NONE, \ - vcmpgtud, PPC_NONE, PPC2_ALTIVEC_207) static void gen_vsplti(DisasContext *ctx, int vece) { @@ -1228,6 +1769,141 @@ GEN_VXFORM_DUAL(vsplth, PPC_ALTIVEC, PPC_NONE, GEN_VXFORM_DUAL(vspltw, PPC_ALTIVEC, PPC_NONE, vextractuw, PPC_NONE, PPC2_ISA300); +static bool trans_VGNB(DisasContext *ctx, arg_VX_n *a) +{ + /* + * Similar to do_vextractm, we'll use a sequence of mask-shift-or operations + * to gather the bits. The masks can be created with + * + * uint64_t mask(uint64_t n, uint64_t step) + * { + * uint64_t p = ((1UL << (1UL << step)) - 1UL) << ((n - 1UL) << step), + * plen = n << step, m = 0; + * for(int i = 0; i < 64/plen; i++) { + * m |= p; + * m = ror64(m, plen); + * } + * p >>= plen * DIV_ROUND_UP(64, plen) - 64; + * return m | p; + * } + * + * But since there are few values of N, we'll use a lookup table to avoid + * these calculations at runtime. + */ + static const uint64_t mask[6][5] = { + { + 0xAAAAAAAAAAAAAAAAULL, 0xccccccccccccccccULL, 0xf0f0f0f0f0f0f0f0ULL, + 0xff00ff00ff00ff00ULL, 0xffff0000ffff0000ULL + }, + { + 0x9249249249249249ULL, 0xC30C30C30C30C30CULL, 0xF00F00F00F00F00FULL, + 0xFF0000FF0000FF00ULL, 0xFFFF00000000FFFFULL + }, + { + /* For N >= 4, some mask operations can be elided */ + 0x8888888888888888ULL, 0, 0xf000f000f000f000ULL, 0, + 0xFFFF000000000000ULL + }, + { + 0x8421084210842108ULL, 0, 0xF0000F0000F0000FULL, 0, 0 + }, + { + 0x8208208208208208ULL, 0, 0xF00000F00000F000ULL, 0, 0 + }, + { + 0x8102040810204081ULL, 0, 0xF000000F000000F0ULL, 0, 0 + } + }; + uint64_t m; + int i, sh, nbits = DIV_ROUND_UP(64, a->n); + TCGv_i64 hi, lo, t0, t1; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + if (a->n < 2) { + /* + * "N can be any value between 2 and 7, inclusive." Otherwise, the + * result is undefined, so we don't need to change RT. Also, N > 7 is + * impossible since the immediate field is 3 bits only. + */ + return true; + } + + hi = tcg_temp_new_i64(); + lo = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + + get_avr64(hi, a->vrb, true); + get_avr64(lo, a->vrb, false); + + /* Align the lower doubleword so we can use the same mask */ + tcg_gen_shli_i64(lo, lo, a->n * nbits - 64); + + /* + * Starting from the most significant bit, gather every Nth bit with a + * sequence of mask-shift-or operation. E.g.: for N=3 + * AxxBxxCxxDxxExxFxxGxxHxxIxxJxxKxxLxxMxxNxxOxxPxxQxxRxxSxxTxxUxxV + * & rep(0b100) + * A..B..C..D..E..F..G..H..I..J..K..L..M..N..O..P..Q..R..S..T..U..V + * << 2 + * .B..C..D..E..F..G..H..I..J..K..L..M..N..O..P..Q..R..S..T..U..V.. + * | + * AB.BC.CD.DE.EF.FG.GH.HI.IJ.JK.KL.LM.MN.NO.OP.PQ.QR.RS.ST.TU.UV.V + * & rep(0b110000) + * AB....CD....EF....GH....IJ....KL....MN....OP....QR....ST....UV.. + * << 4 + * ..CD....EF....GH....IJ....KL....MN....OP....QR....ST....UV...... + * | + * ABCD..CDEF..EFGH..GHIJ..IJKL..KLMN..MNOP..OPQR..QRST..STUV..UV.. + * & rep(0b111100000000) + * ABCD........EFGH........IJKL........MNOP........QRST........UV.. + * << 8 + * ....EFGH........IJKL........MNOP........QRST........UV.......... + * | + * ABCDEFGH....EFGHIJKL....IJKLMNOP....MNOPQRST....QRSTUV......UV.. + * & rep(0b111111110000000000000000) + * ABCDEFGH................IJKLMNOP................QRSTUV.......... + * << 16 + * ........IJKLMNOP................QRSTUV.......................... + * | + * ABCDEFGHIJKLMNOP........IJKLMNOPQRSTUV..........QRSTUV.......... + * & rep(0b111111111111111100000000000000000000000000000000) + * ABCDEFGHIJKLMNOP................................QRSTUV.......... + * << 32 + * ................QRSTUV.......................................... + * | + * ABCDEFGHIJKLMNOPQRSTUV..........................QRSTUV.......... + */ + for (i = 0, sh = a->n - 1; i < 5; i++, sh <<= 1) { + m = mask[a->n - 2][i]; + if (m) { + tcg_gen_andi_i64(hi, hi, m); + tcg_gen_andi_i64(lo, lo, m); + } + if (sh < 64) { + tcg_gen_shli_i64(t0, hi, sh); + tcg_gen_shli_i64(t1, lo, sh); + tcg_gen_or_i64(hi, t0, hi); + tcg_gen_or_i64(lo, t1, lo); + } + } + + tcg_gen_andi_i64(hi, hi, ~(~0ULL >> nbits)); + tcg_gen_andi_i64(lo, lo, ~(~0ULL >> nbits)); + tcg_gen_shri_i64(lo, lo, nbits); + tcg_gen_or_i64(hi, hi, lo); + tcg_gen_trunc_i64_tl(cpu_gpr[a->rt], hi); + + tcg_temp_free_i64(hi); + tcg_temp_free_i64(lo); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + + return true; +} + static bool do_vextdx(DisasContext *ctx, arg_VA *a, int size, bool right, void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv)) { @@ -1722,6 +2398,124 @@ static bool trans_MTVSRBMI(DisasContext *ctx, arg_DX_b *a) return true; } +static bool do_vcntmb(DisasContext *ctx, arg_VX_mp *a, int vece) +{ + TCGv_i64 rt, vrb, mask; + rt = tcg_const_i64(0); + vrb = tcg_temp_new_i64(); + mask = tcg_constant_i64(dup_const(vece, 1ULL << ((8 << vece) - 1))); + + for (int i = 0; i < 2; i++) { + get_avr64(vrb, a->vrb, i); + if (a->mp) { + tcg_gen_and_i64(vrb, mask, vrb); + } else { + tcg_gen_andc_i64(vrb, mask, vrb); + } + tcg_gen_ctpop_i64(vrb, vrb); + tcg_gen_add_i64(rt, rt, vrb); + } + + tcg_gen_shli_i64(rt, rt, TARGET_LONG_BITS - 8 + vece); + tcg_gen_trunc_i64_tl(cpu_gpr[a->rt], rt); + + tcg_temp_free_i64(vrb); + tcg_temp_free_i64(rt); + + return true; +} + +TRANS(VCNTMBB, do_vcntmb, MO_8) +TRANS(VCNTMBH, do_vcntmb, MO_16) +TRANS(VCNTMBW, do_vcntmb, MO_32) +TRANS(VCNTMBD, do_vcntmb, MO_64) + +static bool do_vstri(DisasContext *ctx, arg_VX_tb_rc *a, + void (*gen_helper)(TCGv_i32, TCGv_ptr, TCGv_ptr)) +{ + TCGv_ptr vrt, vrb; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + vrt = gen_avr_ptr(a->vrt); + vrb = gen_avr_ptr(a->vrb); + + if (a->rc) { + gen_helper(cpu_crf[6], vrt, vrb); + } else { + TCGv_i32 discard = tcg_temp_new_i32(); + gen_helper(discard, vrt, vrb); + tcg_temp_free_i32(discard); + } + + tcg_temp_free_ptr(vrt); + tcg_temp_free_ptr(vrb); + + return true; +} + +TRANS(VSTRIBL, do_vstri, gen_helper_VSTRIBL) +TRANS(VSTRIBR, do_vstri, gen_helper_VSTRIBR) +TRANS(VSTRIHL, do_vstri, gen_helper_VSTRIHL) +TRANS(VSTRIHR, do_vstri, gen_helper_VSTRIHR) + +static bool do_vclrb(DisasContext *ctx, arg_VX *a, bool right) +{ + TCGv_i64 rb, mh, ml, tmp, + ones = tcg_constant_i64(-1), + zero = tcg_constant_i64(0); + + rb = tcg_temp_new_i64(); + mh = tcg_temp_new_i64(); + ml = tcg_temp_new_i64(); + tmp = tcg_temp_new_i64(); + + tcg_gen_extu_tl_i64(rb, cpu_gpr[a->vrb]); + tcg_gen_andi_i64(tmp, rb, 7); + tcg_gen_shli_i64(tmp, tmp, 3); + if (right) { + tcg_gen_shr_i64(tmp, ones, tmp); + } else { + tcg_gen_shl_i64(tmp, ones, tmp); + } + tcg_gen_not_i64(tmp, tmp); + + if (right) { + tcg_gen_movcond_i64(TCG_COND_LTU, mh, rb, tcg_constant_i64(8), + tmp, ones); + tcg_gen_movcond_i64(TCG_COND_LTU, ml, rb, tcg_constant_i64(8), + zero, tmp); + tcg_gen_movcond_i64(TCG_COND_LTU, ml, rb, tcg_constant_i64(16), + ml, ones); + } else { + tcg_gen_movcond_i64(TCG_COND_LTU, ml, rb, tcg_constant_i64(8), + tmp, ones); + tcg_gen_movcond_i64(TCG_COND_LTU, mh, rb, tcg_constant_i64(8), + zero, tmp); + tcg_gen_movcond_i64(TCG_COND_LTU, mh, rb, tcg_constant_i64(16), + mh, ones); + } + + get_avr64(tmp, a->vra, true); + tcg_gen_and_i64(tmp, tmp, mh); + set_avr64(a->vrt, tmp, true); + + get_avr64(tmp, a->vra, false); + tcg_gen_and_i64(tmp, tmp, ml); + set_avr64(a->vrt, tmp, false); + + tcg_temp_free_i64(rb); + tcg_temp_free_i64(mh); + tcg_temp_free_i64(ml); + tcg_temp_free_i64(tmp); + + return true; +} + +TRANS(VCLRLB, do_vclrb, false) +TRANS(VCLRRB, do_vclrb, true) + #define GEN_VAFORM_PAIRED(name0, name1, opc2) \ static void glue(gen_, name0##_##name1)(DisasContext *ctx) \ { \ @@ -1765,28 +2559,65 @@ static void gen_vmladduhm(DisasContext *ctx) tcg_temp_free_ptr(rd); } -static void gen_vpermr(DisasContext *ctx) +static bool trans_VPERM(DisasContext *ctx, arg_VA *a) { - TCGv_ptr ra, rb, rc, rd; - if (unlikely(!ctx->altivec_enabled)) { - gen_exception(ctx, POWERPC_EXCP_VPU); - return; - } - ra = gen_avr_ptr(rA(ctx->opcode)); - rb = gen_avr_ptr(rB(ctx->opcode)); - rc = gen_avr_ptr(rC(ctx->opcode)); - rd = gen_avr_ptr(rD(ctx->opcode)); - gen_helper_vpermr(cpu_env, rd, ra, rb, rc); - tcg_temp_free_ptr(ra); - tcg_temp_free_ptr(rb); - tcg_temp_free_ptr(rc); - tcg_temp_free_ptr(rd); + TCGv_ptr vrt, vra, vrb, vrc; + + REQUIRE_INSNS_FLAGS(ctx, ALTIVEC); + REQUIRE_VECTOR(ctx); + + vrt = gen_avr_ptr(a->vrt); + vra = gen_avr_ptr(a->vra); + vrb = gen_avr_ptr(a->vrb); + vrc = gen_avr_ptr(a->rc); + + gen_helper_VPERM(vrt, vra, vrb, vrc); + + tcg_temp_free_ptr(vrt); + tcg_temp_free_ptr(vra); + tcg_temp_free_ptr(vrb); + tcg_temp_free_ptr(vrc); + + return true; +} + +static bool trans_VPERMR(DisasContext *ctx, arg_VA *a) +{ + TCGv_ptr vrt, vra, vrb, vrc; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VECTOR(ctx); + + vrt = gen_avr_ptr(a->vrt); + vra = gen_avr_ptr(a->vra); + vrb = gen_avr_ptr(a->vrb); + vrc = gen_avr_ptr(a->rc); + + gen_helper_VPERMR(vrt, vra, vrb, vrc); + + tcg_temp_free_ptr(vrt); + tcg_temp_free_ptr(vra); + tcg_temp_free_ptr(vrb); + tcg_temp_free_ptr(vrc); + + return true; +} + +static bool trans_VSEL(DisasContext *ctx, arg_VA *a) +{ + REQUIRE_INSNS_FLAGS(ctx, ALTIVEC); + REQUIRE_VECTOR(ctx); + + tcg_gen_gvec_bitsel(MO_64, avr_full_offset(a->vrt), avr_full_offset(a->rc), + avr_full_offset(a->vrb), avr_full_offset(a->vra), + 16, 16); + + return true; } GEN_VAFORM_PAIRED(vmsumubm, vmsummbm, 18) GEN_VAFORM_PAIRED(vmsumuhm, vmsumuhs, 19) GEN_VAFORM_PAIRED(vmsumshm, vmsumshs, 20) -GEN_VAFORM_PAIRED(vsel, vperm, 21) GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23) GEN_VXFORM_NOA(vclzb, 1, 28) @@ -1795,11 +2626,77 @@ GEN_VXFORM_TRANS(vclzw, 1, 30) GEN_VXFORM_TRANS(vclzd, 1, 31) GEN_VXFORM_NOA_2(vnegw, 1, 24, 6) GEN_VXFORM_NOA_2(vnegd, 1, 24, 7) -GEN_VXFORM_NOA_2(vextsb2w, 1, 24, 16) -GEN_VXFORM_NOA_2(vextsh2w, 1, 24, 17) -GEN_VXFORM_NOA_2(vextsb2d, 1, 24, 24) -GEN_VXFORM_NOA_2(vextsh2d, 1, 24, 25) -GEN_VXFORM_NOA_2(vextsw2d, 1, 24, 26) + +static void gen_vexts_i64(TCGv_i64 t, TCGv_i64 b, int64_t s) +{ + tcg_gen_sextract_i64(t, b, 0, 64 - s); +} + +static void gen_vexts_i32(TCGv_i32 t, TCGv_i32 b, int32_t s) +{ + tcg_gen_sextract_i32(t, b, 0, 32 - s); +} + +static void gen_vexts_vec(unsigned vece, TCGv_vec t, TCGv_vec b, int64_t s) +{ + tcg_gen_shli_vec(vece, t, b, s); + tcg_gen_sari_vec(vece, t, t, s); +} + +static bool do_vexts(DisasContext *ctx, arg_VX_tb *a, unsigned vece, int64_t s) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, 0 + }; + + static const GVecGen2i op[2] = { + { + .fni4 = gen_vexts_i32, + .fniv = gen_vexts_vec, + .opt_opc = vecop_list, + .vece = MO_32 + }, + { + .fni8 = gen_vexts_i64, + .fniv = gen_vexts_vec, + .opt_opc = vecop_list, + .vece = MO_64 + }, + }; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VECTOR(ctx); + + tcg_gen_gvec_2i(avr_full_offset(a->vrt), avr_full_offset(a->vrb), + 16, 16, s, &op[vece - MO_32]); + + return true; +} + +TRANS(VEXTSB2W, do_vexts, MO_32, 24); +TRANS(VEXTSH2W, do_vexts, MO_32, 16); +TRANS(VEXTSB2D, do_vexts, MO_64, 56); +TRANS(VEXTSH2D, do_vexts, MO_64, 48); +TRANS(VEXTSW2D, do_vexts, MO_64, 32); + +static bool trans_VEXTSD2Q(DisasContext *ctx, arg_VX_tb *a) +{ + TCGv_i64 tmp; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + tmp = tcg_temp_new_i64(); + + get_avr64(tmp, a->vrb, false); + set_avr64(a->vrt, tmp, false); + tcg_gen_sari_i64(tmp, tmp, 63); + set_avr64(a->vrt, tmp, true); + + tcg_temp_free_i64(tmp); + return true; +} + GEN_VXFORM_NOA_2(vctzb, 1, 24, 28) GEN_VXFORM_NOA_2(vctzh, 1, 24, 29) GEN_VXFORM_NOA_2(vctzw, 1, 24, 30) @@ -2104,6 +3001,251 @@ static bool trans_VPEXTD(DisasContext *ctx, arg_VX *a) return true; } +static bool trans_VMSUMUDM(DisasContext *ctx, arg_VA *a) +{ + TCGv_i64 rl, rh, src1, src2; + int dw; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VECTOR(ctx); + + rh = tcg_temp_new_i64(); + rl = tcg_temp_new_i64(); + src1 = tcg_temp_new_i64(); + src2 = tcg_temp_new_i64(); + + get_avr64(rl, a->rc, false); + get_avr64(rh, a->rc, true); + + for (dw = 0; dw < 2; dw++) { + get_avr64(src1, a->vra, dw); + get_avr64(src2, a->vrb, dw); + tcg_gen_mulu2_i64(src1, src2, src1, src2); + tcg_gen_add2_i64(rl, rh, rl, rh, src1, src2); + } + + set_avr64(a->vrt, rl, false); + set_avr64(a->vrt, rh, true); + + tcg_temp_free_i64(rl); + tcg_temp_free_i64(rh); + tcg_temp_free_i64(src1); + tcg_temp_free_i64(src2); + + return true; +} + +static bool trans_VMSUMCUD(DisasContext *ctx, arg_VA *a) +{ + TCGv_i64 tmp0, tmp1, prod1h, prod1l, prod0h, prod0l, zero; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + tmp0 = tcg_temp_new_i64(); + tmp1 = tcg_temp_new_i64(); + prod1h = tcg_temp_new_i64(); + prod1l = tcg_temp_new_i64(); + prod0h = tcg_temp_new_i64(); + prod0l = tcg_temp_new_i64(); + zero = tcg_constant_i64(0); + + /* prod1 = vsr[vra+32].dw[1] * vsr[vrb+32].dw[1] */ + get_avr64(tmp0, a->vra, false); + get_avr64(tmp1, a->vrb, false); + tcg_gen_mulu2_i64(prod1l, prod1h, tmp0, tmp1); + + /* prod0 = vsr[vra+32].dw[0] * vsr[vrb+32].dw[0] */ + get_avr64(tmp0, a->vra, true); + get_avr64(tmp1, a->vrb, true); + tcg_gen_mulu2_i64(prod0l, prod0h, tmp0, tmp1); + + /* Sum lower 64-bits elements */ + get_avr64(tmp1, a->rc, false); + tcg_gen_add2_i64(tmp1, tmp0, tmp1, zero, prod1l, zero); + tcg_gen_add2_i64(tmp1, tmp0, tmp1, tmp0, prod0l, zero); + + /* + * Discard lower 64-bits, leaving the carry into bit 64. + * Then sum the higher 64-bit elements. + */ + get_avr64(tmp1, a->rc, true); + tcg_gen_add2_i64(tmp1, tmp0, tmp0, zero, tmp1, zero); + tcg_gen_add2_i64(tmp1, tmp0, tmp1, tmp0, prod1h, zero); + tcg_gen_add2_i64(tmp1, tmp0, tmp1, tmp0, prod0h, zero); + + /* Discard 64 more bits to complete the CHOP128(temp >> 128) */ + set_avr64(a->vrt, tmp0, false); + set_avr64(a->vrt, zero, true); + + tcg_temp_free_i64(tmp0); + tcg_temp_free_i64(tmp1); + tcg_temp_free_i64(prod1h); + tcg_temp_free_i64(prod1l); + tcg_temp_free_i64(prod0h); + tcg_temp_free_i64(prod0l); + + return true; +} + +static bool do_vx_helper(DisasContext *ctx, arg_VX *a, + void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr)) +{ + TCGv_ptr ra, rb, rd; + REQUIRE_VECTOR(ctx); + + ra = gen_avr_ptr(a->vra); + rb = gen_avr_ptr(a->vrb); + rd = gen_avr_ptr(a->vrt); + gen_helper(rd, ra, rb); + tcg_temp_free_ptr(ra); + tcg_temp_free_ptr(rb); + tcg_temp_free_ptr(rd); + + return true; +} + +static bool do_vx_vmuleo(DisasContext *ctx, arg_VX *a, bool even, + void (*gen_mul)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64)) +{ + TCGv_i64 vra, vrb, vrt0, vrt1; + REQUIRE_VECTOR(ctx); + + vra = tcg_temp_new_i64(); + vrb = tcg_temp_new_i64(); + vrt0 = tcg_temp_new_i64(); + vrt1 = tcg_temp_new_i64(); + + get_avr64(vra, a->vra, even); + get_avr64(vrb, a->vrb, even); + gen_mul(vrt0, vrt1, vra, vrb); + set_avr64(a->vrt, vrt0, false); + set_avr64(a->vrt, vrt1, true); + + tcg_temp_free_i64(vra); + tcg_temp_free_i64(vrb); + tcg_temp_free_i64(vrt0); + tcg_temp_free_i64(vrt1); + + return true; +} + +static bool trans_VMULLD(DisasContext *ctx, arg_VX *a) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + tcg_gen_gvec_mul(MO_64, avr_full_offset(a->vrt), avr_full_offset(a->vra), + avr_full_offset(a->vrb), 16, 16); + + return true; +} + +TRANS_FLAGS2(ALTIVEC_207, VMULESB, do_vx_helper, gen_helper_VMULESB) +TRANS_FLAGS2(ALTIVEC_207, VMULOSB, do_vx_helper, gen_helper_VMULOSB) +TRANS_FLAGS2(ALTIVEC_207, VMULEUB, do_vx_helper, gen_helper_VMULEUB) +TRANS_FLAGS2(ALTIVEC_207, VMULOUB, do_vx_helper, gen_helper_VMULOUB) +TRANS_FLAGS2(ALTIVEC_207, VMULESH, do_vx_helper, gen_helper_VMULESH) +TRANS_FLAGS2(ALTIVEC_207, VMULOSH, do_vx_helper, gen_helper_VMULOSH) +TRANS_FLAGS2(ALTIVEC_207, VMULEUH, do_vx_helper, gen_helper_VMULEUH) +TRANS_FLAGS2(ALTIVEC_207, VMULOUH, do_vx_helper, gen_helper_VMULOUH) +TRANS_FLAGS2(ALTIVEC_207, VMULESW, do_vx_helper, gen_helper_VMULESW) +TRANS_FLAGS2(ALTIVEC_207, VMULOSW, do_vx_helper, gen_helper_VMULOSW) +TRANS_FLAGS2(ALTIVEC_207, VMULEUW, do_vx_helper, gen_helper_VMULEUW) +TRANS_FLAGS2(ALTIVEC_207, VMULOUW, do_vx_helper, gen_helper_VMULOUW) +TRANS_FLAGS2(ISA310, VMULESD, do_vx_vmuleo, true , tcg_gen_muls2_i64) +TRANS_FLAGS2(ISA310, VMULOSD, do_vx_vmuleo, false, tcg_gen_muls2_i64) +TRANS_FLAGS2(ISA310, VMULEUD, do_vx_vmuleo, true , tcg_gen_mulu2_i64) +TRANS_FLAGS2(ISA310, VMULOUD, do_vx_vmuleo, false, tcg_gen_mulu2_i64) + +static void do_vx_vmulhw_i64(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b, bool sign) +{ + TCGv_i64 hh, lh, temp; + + uint64_t c; + hh = tcg_temp_new_i64(); + lh = tcg_temp_new_i64(); + temp = tcg_temp_new_i64(); + + c = 0xFFFFFFFF; + + if (sign) { + tcg_gen_ext32s_i64(lh, a); + tcg_gen_ext32s_i64(temp, b); + } else { + tcg_gen_andi_i64(lh, a, c); + tcg_gen_andi_i64(temp, b, c); + } + tcg_gen_mul_i64(lh, lh, temp); + + if (sign) { + tcg_gen_sari_i64(hh, a, 32); + tcg_gen_sari_i64(temp, b, 32); + } else { + tcg_gen_shri_i64(hh, a, 32); + tcg_gen_shri_i64(temp, b, 32); + } + tcg_gen_mul_i64(hh, hh, temp); + + tcg_gen_shri_i64(lh, lh, 32); + tcg_gen_andi_i64(hh, hh, c << 32); + tcg_gen_or_i64(t, hh, lh); + + tcg_temp_free_i64(hh); + tcg_temp_free_i64(lh); + tcg_temp_free_i64(temp); +} + +static void do_vx_vmulhd_i64(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b, bool sign) +{ + TCGv_i64 tlow; + + tlow = tcg_temp_new_i64(); + if (sign) { + tcg_gen_muls2_i64(tlow, t, a, b); + } else { + tcg_gen_mulu2_i64(tlow, t, a, b); + } + + tcg_temp_free_i64(tlow); +} + +static bool do_vx_mulh(DisasContext *ctx, arg_VX *a, bool sign, + void (*func)(TCGv_i64, TCGv_i64, TCGv_i64, bool)) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VECTOR(ctx); + + TCGv_i64 vra, vrb, vrt; + int i; + + vra = tcg_temp_new_i64(); + vrb = tcg_temp_new_i64(); + vrt = tcg_temp_new_i64(); + + for (i = 0; i < 2; i++) { + get_avr64(vra, a->vra, i); + get_avr64(vrb, a->vrb, i); + get_avr64(vrt, a->vrt, i); + + func(vrt, vra, vrb, sign); + + set_avr64(a->vrt, vrt, i); + } + + tcg_temp_free_i64(vra); + tcg_temp_free_i64(vrb); + tcg_temp_free_i64(vrt); + + return true; + +} + +TRANS(VMULHSW, do_vx_mulh, true , do_vx_vmulhw_i64) +TRANS(VMULHSD, do_vx_mulh, true , do_vx_vmulhd_i64) +TRANS(VMULHUW, do_vx_mulh, false, do_vx_vmulhw_i64) +TRANS(VMULHUD, do_vx_mulh, false, do_vx_vmulhd_i64) + #undef GEN_VR_LDX #undef GEN_VR_STX #undef GEN_VR_LVE diff --git a/target/ppc/translate/vmx-ops.c.inc b/target/ppc/translate/vmx-ops.c.inc index 25ee715b43..d960648d52 100644 --- a/target/ppc/translate/vmx-ops.c.inc +++ b/target/ppc/translate/vmx-ops.c.inc @@ -101,33 +101,7 @@ GEN_VXFORM_DUAL(vmrgow, vextuwlx, 6, 26, PPC_NONE, PPC2_ALTIVEC_207), GEN_VXFORM_300(vextubrx, 6, 28), GEN_VXFORM_300(vextuhrx, 6, 29), GEN_VXFORM_DUAL(vmrgew, vextuwrx, 6, 30, PPC_NONE, PPC2_ALTIVEC_207), -GEN_VXFORM(vmuloub, 4, 0), -GEN_VXFORM(vmulouh, 4, 1), -GEN_VXFORM_DUAL(vmulouw, vmuluwm, 4, 2, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM(vmulosb, 4, 4), -GEN_VXFORM(vmulosh, 4, 5), -GEN_VXFORM_207(vmulosw, 4, 6), -GEN_VXFORM_310(vmulld, 4, 7), -GEN_VXFORM(vmuleub, 4, 8), -GEN_VXFORM(vmuleuh, 4, 9), -GEN_VXFORM_DUAL(vmuleuw, vmulhuw, 4, 10, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_310(vmulhud, 4, 11), -GEN_VXFORM(vmulesb, 4, 12), -GEN_VXFORM(vmulesh, 4, 13), -GEN_VXFORM_DUAL(vmulesw, vmulhsw, 4, 14, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_310(vmulhsd, 4, 15), -GEN_VXFORM(vslb, 2, 4), -GEN_VXFORM(vslh, 2, 5), -GEN_VXFORM_DUAL(vslw, vrlwnm, 2, 6, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_207(vsld, 2, 23), -GEN_VXFORM(vsrb, 2, 8), -GEN_VXFORM(vsrh, 2, 9), -GEN_VXFORM(vsrw, 2, 10), -GEN_VXFORM_207(vsrd, 2, 27), -GEN_VXFORM(vsrab, 2, 12), -GEN_VXFORM(vsrah, 2, 13), -GEN_VXFORM(vsraw, 2, 14), -GEN_VXFORM_207(vsrad, 2, 15), +GEN_VXFORM_207(vmuluwm, 4, 2), GEN_VXFORM_300(vsrv, 2, 28), GEN_VXFORM_300(vslv, 2, 29), GEN_VXFORM(vslo, 6, 16), @@ -158,11 +132,7 @@ 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(vrlb, 2, 0), -GEN_VXFORM(vrlh, 2, 1), -GEN_VXFORM_DUAL(vrlw, vrlwmi, 2, 2, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_DUAL(vrld, vrldmi, 2, 3, PPC_NONE, PPC2_ALTIVEC_207), -GEN_VXFORM_DUAL(vsl, vrldnm, 2, 7, PPC_ALTIVEC, PPC_NONE), +GEN_VXFORM(vsl, 2, 7), GEN_VXFORM(vsr, 2, 11), GEN_VXFORM(vpkuhum, 7, 0), GEN_VXFORM(vpkuwum, 7, 1), @@ -198,22 +168,10 @@ GEN_HANDLER2_E(name, str, 0x4, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ISA300), GEN_VXRFORM1_300(name, name, #name, opc2, opc3) \ GEN_VXRFORM1_300(name##_dot, name##_, #name ".", opc2, (opc3 | (0x1 << 4))) -GEN_VXRFORM_300(vcmpnezb, 3, 4) -GEN_VXRFORM_300(vcmpnezh, 3, 5) -GEN_VXRFORM_300(vcmpnezw, 3, 6) -GEN_VXRFORM(vcmpgtsb, 3, 12) -GEN_VXRFORM(vcmpgtsh, 3, 13) -GEN_VXRFORM(vcmpgtsw, 3, 14) -GEN_VXRFORM(vcmpgtub, 3, 8) -GEN_VXRFORM(vcmpgtuh, 3, 9) -GEN_VXRFORM(vcmpgtuw, 3, 10) -GEN_VXRFORM_DUAL(vcmpeqfp, vcmpequd, 3, 3, PPC_ALTIVEC, PPC_NONE) +GEN_VXRFORM(vcmpeqfp, 3, 3) GEN_VXRFORM(vcmpgefp, 3, 7) -GEN_VXRFORM_DUAL(vcmpgtfp, vcmpgtud, 3, 11, PPC_ALTIVEC, PPC_NONE) -GEN_VXRFORM_DUAL(vcmpbfp, vcmpgtsd, 3, 15, PPC_ALTIVEC, PPC_NONE) -GEN_VXRFORM_DUAL(vcmpequb, vcmpneb, 3, 0, PPC_ALTIVEC, PPC_NONE) -GEN_VXRFORM_DUAL(vcmpequh, vcmpneh, 3, 1, PPC_ALTIVEC, PPC_NONE) -GEN_VXRFORM_DUAL(vcmpequw, vcmpnew, 3, 2, PPC_ALTIVEC, PPC_NONE) +GEN_VXRFORM(vcmpgtfp, 3, 11) +GEN_VXRFORM(vcmpbfp, 3, 15) #define GEN_VXFORM_DUAL_INV(name0, name1, opc2, opc3, inval0, inval1, type) \ GEN_OPCODE_DUAL(name0##_##name1, 0x04, opc2, opc3, inval0, inval1, type, \ @@ -230,18 +188,12 @@ GEN_VXFORM(vspltish, 6, 13), GEN_VXFORM(vspltisw, 6, 14), GEN_VXFORM_300_EO(vnegw, 0x01, 0x18, 0x06), GEN_VXFORM_300_EO(vnegd, 0x01, 0x18, 0x07), -GEN_VXFORM_300_EO(vextsb2w, 0x01, 0x18, 0x10), -GEN_VXFORM_300_EO(vextsh2w, 0x01, 0x18, 0x11), -GEN_VXFORM_300_EO(vextsb2d, 0x01, 0x18, 0x18), -GEN_VXFORM_300_EO(vextsh2d, 0x01, 0x18, 0x19), -GEN_VXFORM_300_EO(vextsw2d, 0x01, 0x18, 0x1A), GEN_VXFORM_300_EO(vctzb, 0x01, 0x18, 0x1C), GEN_VXFORM_300_EO(vctzh, 0x01, 0x18, 0x1D), GEN_VXFORM_300_EO(vctzw, 0x01, 0x18, 0x1E), GEN_VXFORM_300_EO(vctzd, 0x01, 0x18, 0x1F), GEN_VXFORM_300_EO(vclzlsbb, 0x01, 0x18, 0x0), GEN_VXFORM_300_EO(vctzlsbb, 0x01, 0x18, 0x1), -GEN_VXFORM_300(vpermr, 0x1D, 0xFF), #define GEN_VXFORM_NOA(name, opc2, opc3) \ GEN_HANDLER(name, 0x04, opc2, opc3, 0x001f0000, PPC_ALTIVEC) @@ -276,7 +228,6 @@ GEN_VAFORM_PAIRED(vmhaddshs, vmhraddshs, 16), GEN_VAFORM_PAIRED(vmsumubm, vmsummbm, 18), GEN_VAFORM_PAIRED(vmsumuhm, vmsumuhs, 19), GEN_VAFORM_PAIRED(vmsumshm, vmsumshs, 20), -GEN_VAFORM_PAIRED(vsel, vperm, 21), GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23), GEN_VXFORM_DUAL(vclzb, vpopcntb, 1, 28, PPC_NONE, PPC2_ALTIVEC_207), diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc index 128968b5e7..2ffeab5287 100644 --- a/target/ppc/translate/vsx-impl.c.inc +++ b/target/ppc/translate/vsx-impl.c.inc @@ -288,30 +288,6 @@ VSX_VECTOR_LOAD_STORE_LENGTH(stxvl) VSX_VECTOR_LOAD_STORE_LENGTH(stxvll) #endif -#define VSX_LOAD_SCALAR_DS(name, operation) \ -static void gen_##name(DisasContext *ctx) \ -{ \ - TCGv EA; \ - TCGv_i64 xth; \ - \ - if (unlikely(!ctx->altivec_enabled)) { \ - gen_exception(ctx, POWERPC_EXCP_VPU); \ - return; \ - } \ - xth = tcg_temp_new_i64(); \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - gen_addr_imm_index(ctx, EA, 0x03); \ - gen_qemu_##operation(ctx, xth, EA); \ - set_cpu_vsr(rD(ctx->opcode) + 32, xth, true); \ - /* NOTE: cpu_vsrl is undefined */ \ - tcg_temp_free(EA); \ - tcg_temp_free_i64(xth); \ -} - -VSX_LOAD_SCALAR_DS(lxsd, ld64_i64) -VSX_LOAD_SCALAR_DS(lxssp, ld32fs) - #define VSX_STORE_SCALAR(name, operation) \ static void gen_##name(DisasContext *ctx) \ { \ @@ -461,30 +437,6 @@ static void gen_stxvb16x(DisasContext *ctx) tcg_temp_free_i64(xsl); } -#define VSX_STORE_SCALAR_DS(name, operation) \ -static void gen_##name(DisasContext *ctx) \ -{ \ - TCGv EA; \ - TCGv_i64 xth; \ - \ - if (unlikely(!ctx->altivec_enabled)) { \ - gen_exception(ctx, POWERPC_EXCP_VPU); \ - return; \ - } \ - xth = tcg_temp_new_i64(); \ - get_cpu_vsr(xth, rD(ctx->opcode) + 32, true); \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - gen_addr_imm_index(ctx, EA, 0x03); \ - gen_qemu_##operation(ctx, xth, EA); \ - /* NOTE: cpu_vsrl is undefined */ \ - tcg_temp_free(EA); \ - tcg_temp_free_i64(xth); \ -} - -VSX_STORE_SCALAR_DS(stxsd, st64_i64) -VSX_STORE_SCALAR_DS(stxssp, st32fs) - static void gen_mfvsrwz(DisasContext *ctx) { if (xS(ctx->opcode) < 32) { @@ -665,45 +617,6 @@ static void gen_mtvsrws(DisasContext *ctx) #endif -static void gen_xxpermdi(DisasContext *ctx) -{ - TCGv_i64 xh, xl; - - if (unlikely(!ctx->vsx_enabled)) { - gen_exception(ctx, POWERPC_EXCP_VSXU); - return; - } - - xh = tcg_temp_new_i64(); - xl = tcg_temp_new_i64(); - - if (unlikely((xT(ctx->opcode) == xA(ctx->opcode)) || - (xT(ctx->opcode) == xB(ctx->opcode)))) { - get_cpu_vsr(xh, xA(ctx->opcode), (DM(ctx->opcode) & 2) == 0); - get_cpu_vsr(xl, xB(ctx->opcode), (DM(ctx->opcode) & 1) == 0); - - set_cpu_vsr(xT(ctx->opcode), xh, true); - set_cpu_vsr(xT(ctx->opcode), xl, false); - } else { - if ((DM(ctx->opcode) & 2) == 0) { - get_cpu_vsr(xh, xA(ctx->opcode), true); - set_cpu_vsr(xT(ctx->opcode), xh, true); - } else { - get_cpu_vsr(xh, xA(ctx->opcode), false); - set_cpu_vsr(xT(ctx->opcode), xh, true); - } - if ((DM(ctx->opcode) & 1) == 0) { - get_cpu_vsr(xl, xB(ctx->opcode), true); - set_cpu_vsr(xT(ctx->opcode), xl, false); - } else { - get_cpu_vsr(xl, xB(ctx->opcode), false); - set_cpu_vsr(xT(ctx->opcode), xl, false); - } - } - tcg_temp_free_i64(xh); - tcg_temp_free_i64(xl); -} - #define OP_ABS 1 #define OP_NABS 2 #define OP_NEG 3 @@ -1091,10 +1004,6 @@ GEN_VSX_HELPER_X2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX) GEN_VSX_HELPER_X2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX) GEN_VSX_HELPER_X2_AB(xstdivdp, 0x14, 0x07, 0, PPC2_VSX) GEN_VSX_HELPER_X1(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX) -GEN_VSX_HELPER_X3(xscmpeqdp, 0x0C, 0x00, 0, PPC2_ISA300) -GEN_VSX_HELPER_X3(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300) -GEN_VSX_HELPER_X3(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300) -GEN_VSX_HELPER_X3(xscmpnedp, 0x0C, 0x03, 0, PPC2_ISA300) GEN_VSX_HELPER_X2_AB(xscmpexpdp, 0x0C, 0x07, 0, PPC2_ISA300) GEN_VSX_HELPER_R2_AB(xscmpexpqp, 0x04, 0x05, 0, PPC2_ISA300) GEN_VSX_HELPER_X2_AB(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX) @@ -1200,8 +1109,216 @@ GEN_VSX_HELPER_X2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX) GEN_VSX_HELPER_X2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvtstdcsp, 0x14, 0x1A, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX) -GEN_VSX_HELPER_X3(xxperm, 0x08, 0x03, 0, PPC2_ISA300) -GEN_VSX_HELPER_X3(xxpermr, 0x08, 0x07, 0, PPC2_ISA300) + +static bool trans_XXPERM(DisasContext *ctx, arg_XX3 *a) +{ + TCGv_ptr xt, xa, xb; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VSX(ctx); + + xt = gen_vsr_ptr(a->xt); + xa = gen_vsr_ptr(a->xa); + xb = gen_vsr_ptr(a->xb); + + gen_helper_VPERM(xt, xa, xt, xb); + + tcg_temp_free_ptr(xt); + tcg_temp_free_ptr(xa); + tcg_temp_free_ptr(xb); + + return true; +} + +static bool trans_XXPERMR(DisasContext *ctx, arg_XX3 *a) +{ + TCGv_ptr xt, xa, xb; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VSX(ctx); + + xt = gen_vsr_ptr(a->xt); + xa = gen_vsr_ptr(a->xa); + xb = gen_vsr_ptr(a->xb); + + gen_helper_VPERMR(xt, xa, xt, xb); + + tcg_temp_free_ptr(xt); + tcg_temp_free_ptr(xa); + tcg_temp_free_ptr(xb); + + return true; +} + +static bool trans_XXPERMDI(DisasContext *ctx, arg_XX3_dm *a) +{ + TCGv_i64 t0, t1; + + REQUIRE_INSNS_FLAGS2(ctx, VSX); + REQUIRE_VSX(ctx); + + t0 = tcg_temp_new_i64(); + + if (unlikely(a->xt == a->xa || a->xt == a->xb)) { + t1 = tcg_temp_new_i64(); + + get_cpu_vsr(t0, a->xa, (a->dm & 2) == 0); + get_cpu_vsr(t1, a->xb, (a->dm & 1) == 0); + + set_cpu_vsr(a->xt, t0, true); + set_cpu_vsr(a->xt, t1, false); + + tcg_temp_free_i64(t1); + } else { + get_cpu_vsr(t0, a->xa, (a->dm & 2) == 0); + set_cpu_vsr(a->xt, t0, true); + + get_cpu_vsr(t0, a->xb, (a->dm & 1) == 0); + set_cpu_vsr(a->xt, t0, false); + } + + tcg_temp_free_i64(t0); + + return true; +} + +static bool trans_XXPERMX(DisasContext *ctx, arg_8RR_XX4_uim3 *a) +{ + TCGv_ptr xt, xa, xb, xc; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VSX(ctx); + + xt = gen_vsr_ptr(a->xt); + xa = gen_vsr_ptr(a->xa); + xb = gen_vsr_ptr(a->xb); + xc = gen_vsr_ptr(a->xc); + + gen_helper_XXPERMX(xt, xa, xb, xc, tcg_constant_tl(a->uim3)); + + tcg_temp_free_ptr(xt); + tcg_temp_free_ptr(xa); + tcg_temp_free_ptr(xb); + tcg_temp_free_ptr(xc); + + return true; +} + +#define XXGENPCV(NAME) \ +static bool trans_##NAME(DisasContext *ctx, arg_X_imm5 *a) \ +{ \ + TCGv_ptr xt, vrb; \ + \ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); \ + REQUIRE_VSX(ctx); \ + \ + if (a->imm & ~0x3) { \ + gen_invalid(ctx); \ + return true; \ + } \ + \ + xt = gen_vsr_ptr(a->xt); \ + vrb = gen_avr_ptr(a->vrb); \ + \ + switch (a->imm) { \ + case 0b00000: /* Big-Endian expansion */ \ + glue(gen_helper_, glue(NAME, _be_exp))(xt, vrb); \ + break; \ + case 0b00001: /* Big-Endian compression */ \ + glue(gen_helper_, glue(NAME, _be_comp))(xt, vrb); \ + break; \ + case 0b00010: /* Little-Endian expansion */ \ + glue(gen_helper_, glue(NAME, _le_exp))(xt, vrb); \ + break; \ + case 0b00011: /* Little-Endian compression */ \ + glue(gen_helper_, glue(NAME, _le_comp))(xt, vrb); \ + break; \ + } \ + \ + tcg_temp_free_ptr(xt); \ + tcg_temp_free_ptr(vrb); \ + \ + return true; \ +} + +XXGENPCV(XXGENPCVBM) +XXGENPCV(XXGENPCVHM) +XXGENPCV(XXGENPCVWM) +XXGENPCV(XXGENPCVDM) +#undef XXGENPCV + +static bool do_xsmadd(DisasContext *ctx, int tgt, int src1, int src2, int src3, + void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) +{ + TCGv_ptr t, s1, s2, s3; + + t = gen_vsr_ptr(tgt); + s1 = gen_vsr_ptr(src1); + s2 = gen_vsr_ptr(src2); + s3 = gen_vsr_ptr(src3); + + gen_helper(cpu_env, t, s1, s2, s3); + + tcg_temp_free_ptr(t); + tcg_temp_free_ptr(s1); + tcg_temp_free_ptr(s2); + tcg_temp_free_ptr(s3); + + return true; +} + +static bool do_xsmadd_XX3(DisasContext *ctx, arg_XX3 *a, bool type_a, + void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) +{ + REQUIRE_VSX(ctx); + + if (type_a) { + return do_xsmadd(ctx, a->xt, a->xa, a->xt, a->xb, gen_helper); + } + return do_xsmadd(ctx, a->xt, a->xa, a->xb, a->xt, gen_helper); +} + +TRANS_FLAGS2(VSX, XSMADDADP, do_xsmadd_XX3, true, gen_helper_XSMADDDP) +TRANS_FLAGS2(VSX, XSMADDMDP, do_xsmadd_XX3, false, gen_helper_XSMADDDP) +TRANS_FLAGS2(VSX, XSMSUBADP, do_xsmadd_XX3, true, gen_helper_XSMSUBDP) +TRANS_FLAGS2(VSX, XSMSUBMDP, do_xsmadd_XX3, false, gen_helper_XSMSUBDP) +TRANS_FLAGS2(VSX, XSNMADDADP, do_xsmadd_XX3, true, gen_helper_XSNMADDDP) +TRANS_FLAGS2(VSX, XSNMADDMDP, do_xsmadd_XX3, false, gen_helper_XSNMADDDP) +TRANS_FLAGS2(VSX, XSNMSUBADP, do_xsmadd_XX3, true, gen_helper_XSNMSUBDP) +TRANS_FLAGS2(VSX, XSNMSUBMDP, do_xsmadd_XX3, false, gen_helper_XSNMSUBDP) +TRANS_FLAGS2(VSX207, XSMADDASP, do_xsmadd_XX3, true, gen_helper_XSMADDSP) +TRANS_FLAGS2(VSX207, XSMADDMSP, do_xsmadd_XX3, false, gen_helper_XSMADDSP) +TRANS_FLAGS2(VSX207, XSMSUBASP, do_xsmadd_XX3, true, gen_helper_XSMSUBSP) +TRANS_FLAGS2(VSX207, XSMSUBMSP, do_xsmadd_XX3, false, gen_helper_XSMSUBSP) +TRANS_FLAGS2(VSX207, XSNMADDASP, do_xsmadd_XX3, true, gen_helper_XSNMADDSP) +TRANS_FLAGS2(VSX207, XSNMADDMSP, do_xsmadd_XX3, false, gen_helper_XSNMADDSP) +TRANS_FLAGS2(VSX207, XSNMSUBASP, do_xsmadd_XX3, true, gen_helper_XSNMSUBSP) +TRANS_FLAGS2(VSX207, XSNMSUBMSP, do_xsmadd_XX3, false, gen_helper_XSNMSUBSP) + +static bool do_xsmadd_X(DisasContext *ctx, arg_X_rc *a, + void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr), + void (*gen_helper_ro)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) +{ + int vrt, vra, vrb; + + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + REQUIRE_VSX(ctx); + + vrt = a->rt + 32; + vra = a->ra + 32; + vrb = a->rb + 32; + + if (a->rc) { + return do_xsmadd(ctx, vrt, vra, vrt, vrb, gen_helper_ro); + } + + return do_xsmadd(ctx, vrt, vra, vrt, vrb, gen_helper); +} + +TRANS(XSMADDQP, do_xsmadd_X, gen_helper_XSMADDQP, gen_helper_XSMADDQPO) +TRANS(XSMSUBQP, do_xsmadd_X, gen_helper_XSMSUBQP, gen_helper_XSMSUBQPO) +TRANS(XSNMADDQP, do_xsmadd_X, gen_helper_XSNMADDQP, gen_helper_XSNMADDQPO) +TRANS(XSNMSUBQP, do_xsmadd_X, gen_helper_XSNMSUBQP, gen_helper_XSNMSUBQPO) #define GEN_VSX_HELPER_VSX_MADD(name, op1, aop, mop, inval, type) \ static void gen_##name(DisasContext *ctx) \ @@ -1233,14 +1350,6 @@ static void gen_##name(DisasContext *ctx) \ tcg_temp_free_ptr(c); \ } -GEN_VSX_HELPER_VSX_MADD(xsmadddp, 0x04, 0x04, 0x05, 0, PPC2_VSX) -GEN_VSX_HELPER_VSX_MADD(xsmsubdp, 0x04, 0x06, 0x07, 0, PPC2_VSX) -GEN_VSX_HELPER_VSX_MADD(xsnmadddp, 0x04, 0x14, 0x15, 0, PPC2_VSX) -GEN_VSX_HELPER_VSX_MADD(xsnmsubdp, 0x04, 0x16, 0x17, 0, PPC2_VSX) -GEN_VSX_HELPER_VSX_MADD(xsmaddsp, 0x04, 0x00, 0x01, 0, PPC2_VSX207) -GEN_VSX_HELPER_VSX_MADD(xsmsubsp, 0x04, 0x02, 0x03, 0, PPC2_VSX207) -GEN_VSX_HELPER_VSX_MADD(xsnmaddsp, 0x04, 0x10, 0x11, 0, PPC2_VSX207) -GEN_VSX_HELPER_VSX_MADD(xsnmsubsp, 0x04, 0x12, 0x13, 0, PPC2_VSX207) GEN_VSX_HELPER_VSX_MADD(xvmadddp, 0x04, 0x0C, 0x0D, 0, PPC2_VSX) GEN_VSX_HELPER_VSX_MADD(xvmsubdp, 0x04, 0x0E, 0x0F, 0, PPC2_VSX) GEN_VSX_HELPER_VSX_MADD(xvnmadddp, 0x04, 0x1C, 0x1D, 0, PPC2_VSX) @@ -1422,22 +1531,18 @@ static void glue(gen_, name)(DisasContext *ctx) \ VSX_XXMRG(xxmrghw, 1) VSX_XXMRG(xxmrglw, 0) -static void gen_xxsel(DisasContext *ctx) +static bool trans_XXSEL(DisasContext *ctx, arg_XX4 *a) { - int rt = xT(ctx->opcode); - int ra = xA(ctx->opcode); - int rb = xB(ctx->opcode); - int rc = xC(ctx->opcode); + REQUIRE_INSNS_FLAGS2(ctx, VSX); + REQUIRE_VSX(ctx); - if (unlikely(!ctx->vsx_enabled)) { - gen_exception(ctx, POWERPC_EXCP_VSXU); - return; - } - tcg_gen_gvec_bitsel(MO_64, vsr_full_offset(rt), vsr_full_offset(rc), - vsr_full_offset(rb), vsr_full_offset(ra), 16, 16); + tcg_gen_gvec_bitsel(MO_64, vsr_full_offset(a->xt), vsr_full_offset(a->xc), + vsr_full_offset(a->xb), vsr_full_offset(a->xa), 16, 16); + + return true; } -static bool trans_XXSPLTW(DisasContext *ctx, arg_XX2 *a) +static bool trans_XXSPLTW(DisasContext *ctx, arg_XX2_uim2 *a) { int tofs, bofs; @@ -1547,6 +1652,46 @@ static bool trans_LXVKQ(DisasContext *ctx, arg_X_uim5 *a) return true; } +static bool trans_XVTLSBB(DisasContext *ctx, arg_XX2_bf_xb *a) +{ + TCGv_i64 xb, t0, t1, all_true, all_false, mask, zero; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VSX(ctx); + + xb = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + all_true = tcg_temp_new_i64(); + all_false = tcg_temp_new_i64(); + mask = tcg_constant_i64(dup_const(MO_8, 1)); + zero = tcg_constant_i64(0); + + get_cpu_vsr(xb, a->xb, true); + tcg_gen_and_i64(t0, mask, xb); + get_cpu_vsr(xb, a->xb, false); + tcg_gen_and_i64(t1, mask, xb); + + tcg_gen_or_i64(all_false, t0, t1); + tcg_gen_and_i64(all_true, t0, t1); + + tcg_gen_setcond_i64(TCG_COND_EQ, all_false, all_false, zero); + tcg_gen_shli_i64(all_false, all_false, 1); + tcg_gen_setcond_i64(TCG_COND_EQ, all_true, all_true, mask); + tcg_gen_shli_i64(all_true, all_true, 3); + + tcg_gen_or_i64(t0, all_false, all_true); + tcg_gen_extrl_i64_i32(cpu_crf[a->bf], t0); + + tcg_temp_free_i64(xb); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(all_true); + tcg_temp_free_i64(all_false); + + return true; +} + static void gen_xxsldwi(DisasContext *ctx) { TCGv_i64 xth, xtl; @@ -2072,12 +2217,6 @@ static bool do_lstxv(DisasContext *ctx, int ra, TCGv displ, static bool do_lstxv_D(DisasContext *ctx, arg_D *a, bool store, bool paired) { - if (paired) { - REQUIRE_INSNS_FLAGS2(ctx, ISA310); - } else { - REQUIRE_INSNS_FLAGS2(ctx, ISA300); - } - if (paired || a->rt >= 32) { REQUIRE_VSX(ctx); } else { @@ -2091,7 +2230,6 @@ static bool do_lstxv_PLS_D(DisasContext *ctx, arg_PLS_D *a, bool store, bool paired) { arg_D d; - REQUIRE_INSNS_FLAGS2(ctx, ISA310); REQUIRE_VSX(ctx); if (!resolve_PLS_D(ctx, &d, a)) { @@ -2103,12 +2241,6 @@ static bool do_lstxv_PLS_D(DisasContext *ctx, arg_PLS_D *a, static bool do_lstxv_X(DisasContext *ctx, arg_X *a, bool store, bool paired) { - if (paired) { - REQUIRE_INSNS_FLAGS2(ctx, ISA310); - } else { - REQUIRE_INSNS_FLAGS2(ctx, ISA300); - } - if (paired || a->rt >= 32) { REQUIRE_VSX(ctx); } else { @@ -2118,18 +2250,373 @@ static bool do_lstxv_X(DisasContext *ctx, arg_X *a, bool store, bool paired) return do_lstxv(ctx, a->ra, cpu_gpr[a->rb], a->rt, store, paired); } -TRANS(STXV, do_lstxv_D, true, false) -TRANS(LXV, do_lstxv_D, false, false) -TRANS(STXVP, do_lstxv_D, true, true) -TRANS(LXVP, do_lstxv_D, false, true) -TRANS(STXVX, do_lstxv_X, true, false) -TRANS(LXVX, do_lstxv_X, false, false) -TRANS(STXVPX, do_lstxv_X, true, true) -TRANS(LXVPX, do_lstxv_X, false, true) -TRANS64(PSTXV, do_lstxv_PLS_D, true, false) -TRANS64(PLXV, do_lstxv_PLS_D, false, false) -TRANS64(PSTXVP, do_lstxv_PLS_D, true, true) -TRANS64(PLXVP, do_lstxv_PLS_D, false, true) +static bool do_lstxsd(DisasContext *ctx, int rt, int ra, TCGv displ, bool store) +{ + TCGv ea; + TCGv_i64 xt; + MemOp mop; + + if (store) { + REQUIRE_VECTOR(ctx); + } else { + REQUIRE_VSX(ctx); + } + + xt = tcg_temp_new_i64(); + mop = DEF_MEMOP(MO_UQ); + + gen_set_access_type(ctx, ACCESS_INT); + ea = do_ea_calc(ctx, ra, displ); + + if (store) { + get_cpu_vsr(xt, rt + 32, true); + tcg_gen_qemu_st_i64(xt, ea, ctx->mem_idx, mop); + } else { + tcg_gen_qemu_ld_i64(xt, ea, ctx->mem_idx, mop); + set_cpu_vsr(rt + 32, xt, true); + set_cpu_vsr(rt + 32, tcg_constant_i64(0), false); + } + + tcg_temp_free(ea); + tcg_temp_free_i64(xt); + + return true; +} + +static bool do_lstxsd_DS(DisasContext *ctx, arg_D *a, bool store) +{ + return do_lstxsd(ctx, a->rt, a->ra, tcg_constant_tl(a->si), store); +} + +static bool do_plstxsd_PLS_D(DisasContext *ctx, arg_PLS_D *a, bool store) +{ + arg_D d; + + if (!resolve_PLS_D(ctx, &d, a)) { + return true; + } + + return do_lstxsd(ctx, d.rt, d.ra, tcg_constant_tl(d.si), store); +} + +static bool do_lstxssp(DisasContext *ctx, int rt, int ra, TCGv displ, bool store) +{ + TCGv ea; + TCGv_i64 xt; + + REQUIRE_VECTOR(ctx); + + xt = tcg_temp_new_i64(); + + gen_set_access_type(ctx, ACCESS_INT); + ea = do_ea_calc(ctx, ra, displ); + + if (store) { + get_cpu_vsr(xt, rt + 32, true); + gen_qemu_st32fs(ctx, xt, ea); + } else { + gen_qemu_ld32fs(ctx, xt, ea); + set_cpu_vsr(rt + 32, xt, true); + set_cpu_vsr(rt + 32, tcg_constant_i64(0), false); + } + + tcg_temp_free(ea); + tcg_temp_free_i64(xt); + + return true; +} + +static bool do_lstxssp_DS(DisasContext *ctx, arg_D *a, bool store) +{ + return do_lstxssp(ctx, a->rt, a->ra, tcg_constant_tl(a->si), store); +} + +static bool do_plstxssp_PLS_D(DisasContext *ctx, arg_PLS_D *a, bool store) +{ + arg_D d; + + if (!resolve_PLS_D(ctx, &d, a)) { + return true; + } + + return do_lstxssp(ctx, d.rt, d.ra, tcg_constant_tl(d.si), store); +} + +TRANS_FLAGS2(ISA300, LXSD, do_lstxsd_DS, false) +TRANS_FLAGS2(ISA300, STXSD, do_lstxsd_DS, true) +TRANS_FLAGS2(ISA300, LXSSP, do_lstxssp_DS, false) +TRANS_FLAGS2(ISA300, STXSSP, do_lstxssp_DS, true) +TRANS_FLAGS2(ISA300, STXV, do_lstxv_D, true, false) +TRANS_FLAGS2(ISA300, LXV, do_lstxv_D, false, false) +TRANS_FLAGS2(ISA310, STXVP, do_lstxv_D, true, true) +TRANS_FLAGS2(ISA310, LXVP, do_lstxv_D, false, true) +TRANS_FLAGS2(ISA300, STXVX, do_lstxv_X, true, false) +TRANS_FLAGS2(ISA300, LXVX, do_lstxv_X, false, false) +TRANS_FLAGS2(ISA310, STXVPX, do_lstxv_X, true, true) +TRANS_FLAGS2(ISA310, LXVPX, do_lstxv_X, false, true) +TRANS64_FLAGS2(ISA310, PLXSD, do_plstxsd_PLS_D, false) +TRANS64_FLAGS2(ISA310, PSTXSD, do_plstxsd_PLS_D, true) +TRANS64_FLAGS2(ISA310, PLXSSP, do_plstxssp_PLS_D, false) +TRANS64_FLAGS2(ISA310, PSTXSSP, do_plstxssp_PLS_D, true) +TRANS64_FLAGS2(ISA310, PSTXV, do_lstxv_PLS_D, true, false) +TRANS64_FLAGS2(ISA310, PLXV, do_lstxv_PLS_D, false, false) +TRANS64_FLAGS2(ISA310, PSTXVP, do_lstxv_PLS_D, true, true) +TRANS64_FLAGS2(ISA310, PLXVP, do_lstxv_PLS_D, false, true) + +static bool do_lstrm(DisasContext *ctx, arg_X *a, MemOp mop, bool store) +{ + TCGv ea; + TCGv_i64 xt; + + REQUIRE_VSX(ctx); + + xt = tcg_temp_new_i64(); + + gen_set_access_type(ctx, ACCESS_INT); + ea = do_ea_calc(ctx, a->ra , cpu_gpr[a->rb]); + + if (store) { + get_cpu_vsr(xt, a->rt, false); + tcg_gen_qemu_st_i64(xt, ea, ctx->mem_idx, mop); + } else { + tcg_gen_qemu_ld_i64(xt, ea, ctx->mem_idx, mop); + set_cpu_vsr(a->rt, xt, false); + set_cpu_vsr(a->rt, tcg_constant_i64(0), true); + } + + tcg_temp_free(ea); + tcg_temp_free_i64(xt); + return true; +} + +TRANS_FLAGS2(ISA310, LXVRBX, do_lstrm, DEF_MEMOP(MO_UB), false) +TRANS_FLAGS2(ISA310, LXVRHX, do_lstrm, DEF_MEMOP(MO_UW), false) +TRANS_FLAGS2(ISA310, LXVRWX, do_lstrm, DEF_MEMOP(MO_UL), false) +TRANS_FLAGS2(ISA310, LXVRDX, do_lstrm, DEF_MEMOP(MO_UQ), false) +TRANS_FLAGS2(ISA310, STXVRBX, do_lstrm, DEF_MEMOP(MO_UB), true) +TRANS_FLAGS2(ISA310, STXVRHX, do_lstrm, DEF_MEMOP(MO_UW), true) +TRANS_FLAGS2(ISA310, STXVRWX, do_lstrm, DEF_MEMOP(MO_UL), true) +TRANS_FLAGS2(ISA310, STXVRDX, do_lstrm, DEF_MEMOP(MO_UQ), true) + +static void gen_xxeval_i64(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b, TCGv_i64 c, + int64_t imm) +{ + /* + * Instead of processing imm bit-by-bit, we'll skip the computation of + * conjunctions whose corresponding bit is unset. + */ + int bit; + TCGv_i64 conj, disj; + + conj = tcg_temp_new_i64(); + disj = tcg_const_i64(0); + + /* Iterate over set bits from the least to the most significant bit */ + while (imm) { + /* + * Get the next bit to be processed with ctz64. Invert the result of + * ctz64 to match the indexing used by PowerISA. + */ + bit = 7 - ctz64(imm); + if (bit & 0x4) { + tcg_gen_mov_i64(conj, a); + } else { + tcg_gen_not_i64(conj, a); + } + if (bit & 0x2) { + tcg_gen_and_i64(conj, conj, b); + } else { + tcg_gen_andc_i64(conj, conj, b); + } + if (bit & 0x1) { + tcg_gen_and_i64(conj, conj, c); + } else { + tcg_gen_andc_i64(conj, conj, c); + } + tcg_gen_or_i64(disj, disj, conj); + + /* Unset the least significant bit that is set */ + imm &= imm - 1; + } + + tcg_gen_mov_i64(t, disj); + + tcg_temp_free_i64(conj); + tcg_temp_free_i64(disj); +} + +static void gen_xxeval_vec(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b, + TCGv_vec c, int64_t imm) +{ + /* + * Instead of processing imm bit-by-bit, we'll skip the computation of + * conjunctions whose corresponding bit is unset. + */ + int bit; + TCGv_vec disj, conj; + + disj = tcg_const_zeros_vec_matching(t); + conj = tcg_temp_new_vec_matching(t); + + /* Iterate over set bits from the least to the most significant bit */ + while (imm) { + /* + * Get the next bit to be processed with ctz64. Invert the result of + * ctz64 to match the indexing used by PowerISA. + */ + bit = 7 - ctz64(imm); + if (bit & 0x4) { + tcg_gen_mov_vec(conj, a); + } else { + tcg_gen_not_vec(vece, conj, a); + } + if (bit & 0x2) { + tcg_gen_and_vec(vece, conj, conj, b); + } else { + tcg_gen_andc_vec(vece, conj, conj, b); + } + if (bit & 0x1) { + tcg_gen_and_vec(vece, conj, conj, c); + } else { + tcg_gen_andc_vec(vece, conj, conj, c); + } + tcg_gen_or_vec(vece, disj, disj, conj); + + /* Unset the least significant bit that is set */ + imm &= imm - 1; + } + + tcg_gen_mov_vec(t, disj); + + tcg_temp_free_vec(disj); + tcg_temp_free_vec(conj); +} + +static bool trans_XXEVAL(DisasContext *ctx, arg_8RR_XX4_imm *a) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_andc_vec, 0 + }; + static const GVecGen4i op = { + .fniv = gen_xxeval_vec, + .fno = gen_helper_XXEVAL, + .fni8 = gen_xxeval_i64, + .opt_opc = vecop_list, + .vece = MO_64 + }; + int xt = vsr_full_offset(a->xt), xa = vsr_full_offset(a->xa), + xb = vsr_full_offset(a->xb), xc = vsr_full_offset(a->xc); + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VSX(ctx); + + /* Equivalent functions that can be implemented with a single gen_gvec */ + switch (a->imm) { + case 0b00000000: /* true */ + set_cpu_vsr(a->xt, tcg_constant_i64(0), true); + set_cpu_vsr(a->xt, tcg_constant_i64(0), false); + break; + case 0b00000011: /* and(B,A) */ + tcg_gen_gvec_and(MO_64, xt, xb, xa, 16, 16); + break; + case 0b00000101: /* and(C,A) */ + tcg_gen_gvec_and(MO_64, xt, xc, xa, 16, 16); + break; + case 0b00001111: /* A */ + tcg_gen_gvec_mov(MO_64, xt, xa, 16, 16); + break; + case 0b00010001: /* and(C,B) */ + tcg_gen_gvec_and(MO_64, xt, xc, xb, 16, 16); + break; + case 0b00011011: /* C?B:A */ + tcg_gen_gvec_bitsel(MO_64, xt, xc, xb, xa, 16, 16); + break; + case 0b00011101: /* B?C:A */ + tcg_gen_gvec_bitsel(MO_64, xt, xb, xc, xa, 16, 16); + break; + case 0b00100111: /* C?A:B */ + tcg_gen_gvec_bitsel(MO_64, xt, xc, xa, xb, 16, 16); + break; + case 0b00110011: /* B */ + tcg_gen_gvec_mov(MO_64, xt, xb, 16, 16); + break; + case 0b00110101: /* A?C:B */ + tcg_gen_gvec_bitsel(MO_64, xt, xa, xc, xb, 16, 16); + break; + case 0b00111100: /* xor(B,A) */ + tcg_gen_gvec_xor(MO_64, xt, xb, xa, 16, 16); + break; + case 0b00111111: /* or(B,A) */ + tcg_gen_gvec_or(MO_64, xt, xb, xa, 16, 16); + break; + case 0b01000111: /* B?A:C */ + tcg_gen_gvec_bitsel(MO_64, xt, xb, xa, xc, 16, 16); + break; + case 0b01010011: /* A?B:C */ + tcg_gen_gvec_bitsel(MO_64, xt, xa, xb, xc, 16, 16); + break; + case 0b01010101: /* C */ + tcg_gen_gvec_mov(MO_64, xt, xc, 16, 16); + break; + case 0b01011010: /* xor(C,A) */ + tcg_gen_gvec_xor(MO_64, xt, xc, xa, 16, 16); + break; + case 0b01011111: /* or(C,A) */ + tcg_gen_gvec_or(MO_64, xt, xc, xa, 16, 16); + break; + case 0b01100110: /* xor(C,B) */ + tcg_gen_gvec_xor(MO_64, xt, xc, xb, 16, 16); + break; + case 0b01110111: /* or(C,B) */ + tcg_gen_gvec_or(MO_64, xt, xc, xb, 16, 16); + break; + case 0b10001000: /* nor(C,B) */ + tcg_gen_gvec_nor(MO_64, xt, xc, xb, 16, 16); + break; + case 0b10011001: /* eqv(C,B) */ + tcg_gen_gvec_eqv(MO_64, xt, xc, xb, 16, 16); + break; + case 0b10100000: /* nor(C,A) */ + tcg_gen_gvec_nor(MO_64, xt, xc, xa, 16, 16); + break; + case 0b10100101: /* eqv(C,A) */ + tcg_gen_gvec_eqv(MO_64, xt, xc, xa, 16, 16); + break; + case 0b10101010: /* not(C) */ + tcg_gen_gvec_not(MO_64, xt, xc, 16, 16); + break; + case 0b11000000: /* nor(B,A) */ + tcg_gen_gvec_nor(MO_64, xt, xb, xa, 16, 16); + break; + case 0b11000011: /* eqv(B,A) */ + tcg_gen_gvec_eqv(MO_64, xt, xb, xa, 16, 16); + break; + case 0b11001100: /* not(B) */ + tcg_gen_gvec_not(MO_64, xt, xb, 16, 16); + break; + case 0b11101110: /* nand(C,B) */ + tcg_gen_gvec_nand(MO_64, xt, xc, xb, 16, 16); + break; + case 0b11110000: /* not(A) */ + tcg_gen_gvec_not(MO_64, xt, xa, 16, 16); + break; + case 0b11111010: /* nand(C,A) */ + tcg_gen_gvec_nand(MO_64, xt, xc, xa, 16, 16); + break; + case 0b11111100: /* nand(B,A) */ + tcg_gen_gvec_nand(MO_64, xt, xb, xa, 16, 16); + break; + case 0b11111111: /* true */ + set_cpu_vsr(a->xt, tcg_constant_i64(-1), true); + set_cpu_vsr(a->xt, tcg_constant_i64(-1), false); + break; + default: + /* Fallback to compute all conjunctions/disjunctions */ + tcg_gen_gvec_4i(xt, xa, xb, xc, 16, 16, a->imm, &op); + } + + return true; +} static void gen_xxblendv_vec(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b, TCGv_vec c) @@ -2140,7 +2627,7 @@ static void gen_xxblendv_vec(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b, tcg_temp_free_vec(tmp); } -static bool do_xxblendv(DisasContext *ctx, arg_XX4 *a, unsigned vece) +static bool do_xxblendv(DisasContext *ctx, arg_8RR_XX4 *a, unsigned vece) { static const TCGOpcode vecop_list[] = { INDEX_op_sari_vec, 0 @@ -2186,8 +2673,8 @@ TRANS(XXBLENDVH, do_xxblendv, MO_16) TRANS(XXBLENDVW, do_xxblendv, MO_32) TRANS(XXBLENDVD, do_xxblendv, MO_64) -static bool do_xsmaxmincjdp(DisasContext *ctx, arg_XX3 *a, - void (*helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) +static bool do_helper_XX3(DisasContext *ctx, arg_XX3 *a, + void (*helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) { TCGv_ptr xt, xa, xb; @@ -2207,10 +2694,75 @@ static bool do_xsmaxmincjdp(DisasContext *ctx, arg_XX3 *a, return true; } -TRANS(XSMAXCDP, do_xsmaxmincjdp, gen_helper_xsmaxcdp) -TRANS(XSMINCDP, do_xsmaxmincjdp, gen_helper_xsmincdp) -TRANS(XSMAXJDP, do_xsmaxmincjdp, gen_helper_xsmaxjdp) -TRANS(XSMINJDP, do_xsmaxmincjdp, gen_helper_xsminjdp) +TRANS(XSCMPEQDP, do_helper_XX3, gen_helper_XSCMPEQDP) +TRANS(XSCMPGEDP, do_helper_XX3, gen_helper_XSCMPGEDP) +TRANS(XSCMPGTDP, do_helper_XX3, gen_helper_XSCMPGTDP) +TRANS(XSMAXCDP, do_helper_XX3, gen_helper_XSMAXCDP) +TRANS(XSMINCDP, do_helper_XX3, gen_helper_XSMINCDP) +TRANS(XSMAXJDP, do_helper_XX3, gen_helper_XSMAXJDP) +TRANS(XSMINJDP, do_helper_XX3, gen_helper_XSMINJDP) + +static bool do_helper_X(arg_X *a, + void (*helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) +{ + TCGv_ptr rt, ra, rb; + + rt = gen_avr_ptr(a->rt); + ra = gen_avr_ptr(a->ra); + rb = gen_avr_ptr(a->rb); + + helper(cpu_env, rt, ra, rb); + + tcg_temp_free_ptr(rt); + tcg_temp_free_ptr(ra); + tcg_temp_free_ptr(rb); + + return true; +} + +static bool do_xscmpqp(DisasContext *ctx, arg_X *a, + void (*helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr)) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VSX(ctx); + + return do_helper_X(a, helper); +} + +TRANS(XSCMPEQQP, do_xscmpqp, gen_helper_XSCMPEQQP) +TRANS(XSCMPGEQP, do_xscmpqp, gen_helper_XSCMPGEQP) +TRANS(XSCMPGTQP, do_xscmpqp, gen_helper_XSCMPGTQP) +TRANS(XSMAXCQP, do_xscmpqp, gen_helper_XSMAXCQP) +TRANS(XSMINCQP, do_xscmpqp, gen_helper_XSMINCQP) + +static bool trans_XVCVSPBF16(DisasContext *ctx, arg_XX2 *a) +{ + TCGv_ptr xt, xb; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VSX(ctx); + + xt = gen_vsr_ptr(a->xt); + xb = gen_vsr_ptr(a->xb); + + gen_helper_XVCVSPBF16(cpu_env, xt, xb); + + tcg_temp_free_ptr(xt); + tcg_temp_free_ptr(xb); + + return true; +} + +static bool trans_XVCVBF16SPN(DisasContext *ctx, arg_XX2 *a) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_VSX(ctx); + + tcg_gen_gvec_shli(MO_32, vsr_full_offset(a->xt), vsr_full_offset(a->xb), + 16, 16, 16); + + return true; +} #undef GEN_XX2FORM #undef GEN_XX3FORM diff --git a/target/ppc/translate/vsx-ops.c.inc b/target/ppc/translate/vsx-ops.c.inc index c974324c4c..b8fd116728 100644 --- a/target/ppc/translate/vsx-ops.c.inc +++ b/target/ppc/translate/vsx-ops.c.inc @@ -186,18 +186,6 @@ GEN_XX2FORM(xssqrtdp, 0x16, 0x04, PPC2_VSX), GEN_XX2FORM(xsrsqrtedp, 0x14, 0x04, PPC2_VSX), GEN_XX3FORM(xstdivdp, 0x14, 0x07, PPC2_VSX), GEN_XX2FORM(xstsqrtdp, 0x14, 0x06, PPC2_VSX), -GEN_XX3FORM_NAME(xsmadddp, "xsmaddadp", 0x04, 0x04, PPC2_VSX), -GEN_XX3FORM_NAME(xsmadddp, "xsmaddmdp", 0x04, 0x05, PPC2_VSX), -GEN_XX3FORM_NAME(xsmsubdp, "xsmsubadp", 0x04, 0x06, PPC2_VSX), -GEN_XX3FORM_NAME(xsmsubdp, "xsmsubmdp", 0x04, 0x07, PPC2_VSX), -GEN_XX3FORM_NAME(xsnmadddp, "xsnmaddadp", 0x04, 0x14, PPC2_VSX), -GEN_XX3FORM_NAME(xsnmadddp, "xsnmaddmdp", 0x04, 0x15, PPC2_VSX), -GEN_XX3FORM_NAME(xsnmsubdp, "xsnmsubadp", 0x04, 0x16, PPC2_VSX), -GEN_XX3FORM_NAME(xsnmsubdp, "xsnmsubmdp", 0x04, 0x17, PPC2_VSX), -GEN_XX3FORM(xscmpeqdp, 0x0C, 0x00, PPC2_ISA300), -GEN_XX3FORM(xscmpgtdp, 0x0C, 0x01, PPC2_ISA300), -GEN_XX3FORM(xscmpgedp, 0x0C, 0x02, PPC2_ISA300), -GEN_XX3FORM(xscmpnedp, 0x0C, 0x03, PPC2_ISA300), GEN_XX3FORM(xscmpexpdp, 0x0C, 0x07, PPC2_ISA300), GEN_VSX_XFORM_300(xscmpexpqp, 0x04, 0x05, 0x00600001), GEN_XX2IFORM(xscmpodp, 0x0C, 0x05, PPC2_VSX), @@ -235,14 +223,6 @@ GEN_XX2FORM(xsresp, 0x14, 0x01, PPC2_VSX207), GEN_XX2FORM(xsrsp, 0x12, 0x11, PPC2_VSX207), GEN_XX2FORM(xssqrtsp, 0x16, 0x00, PPC2_VSX207), GEN_XX2FORM(xsrsqrtesp, 0x14, 0x00, PPC2_VSX207), -GEN_XX3FORM_NAME(xsmaddsp, "xsmaddasp", 0x04, 0x00, PPC2_VSX207), -GEN_XX3FORM_NAME(xsmaddsp, "xsmaddmsp", 0x04, 0x01, PPC2_VSX207), -GEN_XX3FORM_NAME(xsmsubsp, "xsmsubasp", 0x04, 0x02, PPC2_VSX207), -GEN_XX3FORM_NAME(xsmsubsp, "xsmsubmsp", 0x04, 0x03, PPC2_VSX207), -GEN_XX3FORM_NAME(xsnmaddsp, "xsnmaddasp", 0x04, 0x10, PPC2_VSX207), -GEN_XX3FORM_NAME(xsnmaddsp, "xsnmaddmsp", 0x04, 0x11, PPC2_VSX207), -GEN_XX3FORM_NAME(xsnmsubsp, "xsnmsubasp", 0x04, 0x12, PPC2_VSX207), -GEN_XX3FORM_NAME(xsnmsubsp, "xsnmsubmsp", 0x04, 0x13, PPC2_VSX207), GEN_XX2FORM(xscvsxdsp, 0x10, 0x13, PPC2_VSX207), GEN_XX2FORM(xscvuxdsp, 0x10, 0x12, PPC2_VSX207), @@ -341,53 +321,6 @@ VSX_LOGICAL(xxlnand, 0x8, 0x16, PPC2_VSX207), VSX_LOGICAL(xxlorc, 0x8, 0x15, PPC2_VSX207), GEN_XX3FORM(xxmrghw, 0x08, 0x02, PPC2_VSX), GEN_XX3FORM(xxmrglw, 0x08, 0x06, PPC2_VSX), -GEN_XX3FORM(xxperm, 0x08, 0x03, PPC2_ISA300), -GEN_XX3FORM(xxpermr, 0x08, 0x07, PPC2_ISA300), GEN_XX3FORM_DM(xxsldwi, 0x08, 0x00), GEN_XX2FORM_EXT(xxextractuw, 0x0A, 0x0A, PPC2_ISA300), GEN_XX2FORM_EXT(xxinsertw, 0x0A, 0x0B, PPC2_ISA300), - -#define GEN_XXSEL_ROW(opc3) \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x18, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x19, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x1A, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x1B, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x1C, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x1D, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x1E, opc3, 0, PPC_NONE, PPC2_VSX), \ -GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x1F, opc3, 0, PPC_NONE, PPC2_VSX), \ - -GEN_XXSEL_ROW(0x00) -GEN_XXSEL_ROW(0x01) -GEN_XXSEL_ROW(0x02) -GEN_XXSEL_ROW(0x03) -GEN_XXSEL_ROW(0x04) -GEN_XXSEL_ROW(0x05) -GEN_XXSEL_ROW(0x06) -GEN_XXSEL_ROW(0x07) -GEN_XXSEL_ROW(0x08) -GEN_XXSEL_ROW(0x09) -GEN_XXSEL_ROW(0x0A) -GEN_XXSEL_ROW(0x0B) -GEN_XXSEL_ROW(0x0C) -GEN_XXSEL_ROW(0x0D) -GEN_XXSEL_ROW(0x0E) -GEN_XXSEL_ROW(0x0F) -GEN_XXSEL_ROW(0x10) -GEN_XXSEL_ROW(0x11) -GEN_XXSEL_ROW(0x12) -GEN_XXSEL_ROW(0x13) -GEN_XXSEL_ROW(0x14) -GEN_XXSEL_ROW(0x15) -GEN_XXSEL_ROW(0x16) -GEN_XXSEL_ROW(0x17) -GEN_XXSEL_ROW(0x18) -GEN_XXSEL_ROW(0x19) -GEN_XXSEL_ROW(0x1A) -GEN_XXSEL_ROW(0x1B) -GEN_XXSEL_ROW(0x1C) -GEN_XXSEL_ROW(0x1D) -GEN_XXSEL_ROW(0x1E) -GEN_XXSEL_ROW(0x1F) - -GEN_XX3FORM_DM(xxpermdi, 0x08, 0x01), diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index dea24f23c4..69d22e08cb 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -3987,3 +3987,9 @@ void tcg_register_jit(const void *buf, size_t buf_size) tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame)); } #endif /* __ELF__ */ +#undef VMULEUB +#undef VMULEUH +#undef VMULEUW +#undef VMULOUB +#undef VMULOUH +#undef VMULOUW diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index ffe55e908f..079a761b04 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -836,6 +836,30 @@ static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs, tcg_temp_free_i32(t0); } +static void expand_4i_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t cofs, uint32_t oprsz, int32_t c, + void (*fni)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32, + int32_t)) +{ + TCGv_i32 t0 = tcg_temp_new_i32(); + TCGv_i32 t1 = tcg_temp_new_i32(); + TCGv_i32 t2 = tcg_temp_new_i32(); + TCGv_i32 t3 = tcg_temp_new_i32(); + uint32_t i; + + for (i = 0; i < oprsz; i += 4) { + tcg_gen_ld_i32(t1, cpu_env, aofs + i); + tcg_gen_ld_i32(t2, cpu_env, bofs + i); + tcg_gen_ld_i32(t3, cpu_env, cofs + i); + fni(t0, t1, t2, t3, c); + tcg_gen_st_i32(t0, cpu_env, dofs + i); + } + tcg_temp_free_i32(t3); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t1); + tcg_temp_free_i32(t0); +} + /* Expand OPSZ bytes worth of two-operand operations using i64 elements. */ static void expand_2_i64(uint32_t dofs, uint32_t aofs, uint32_t oprsz, bool load_dest, void (*fni)(TCGv_i64, TCGv_i64)) @@ -971,6 +995,30 @@ static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs, tcg_temp_free_i64(t0); } +static void expand_4i_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t cofs, uint32_t oprsz, int64_t c, + void (*fni)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, + int64_t)) +{ + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + uint32_t i; + + for (i = 0; i < oprsz; i += 8) { + tcg_gen_ld_i64(t1, cpu_env, aofs + i); + tcg_gen_ld_i64(t2, cpu_env, bofs + i); + tcg_gen_ld_i64(t3, cpu_env, cofs + i); + fni(t0, t1, t2, t3, c); + tcg_gen_st_i64(t0, cpu_env, dofs + i); + } + tcg_temp_free_i64(t3); + tcg_temp_free_i64(t2); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t0); +} + /* Expand OPSZ bytes worth of two-operand operations using host vectors. */ static void expand_2_vec(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t tysz, TCGType type, @@ -1121,6 +1169,35 @@ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_temp_free_vec(t0); } +/* + * Expand OPSZ bytes worth of four-vector operands and an immediate operand + * using host vectors. + */ +static void expand_4i_vec(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t cofs, uint32_t oprsz, + uint32_t tysz, TCGType type, int64_t c, + void (*fni)(unsigned, TCGv_vec, TCGv_vec, + TCGv_vec, TCGv_vec, int64_t)) +{ + TCGv_vec t0 = tcg_temp_new_vec(type); + TCGv_vec t1 = tcg_temp_new_vec(type); + TCGv_vec t2 = tcg_temp_new_vec(type); + TCGv_vec t3 = tcg_temp_new_vec(type); + uint32_t i; + + for (i = 0; i < oprsz; i += tysz) { + tcg_gen_ld_vec(t1, cpu_env, aofs + i); + tcg_gen_ld_vec(t2, cpu_env, bofs + i); + tcg_gen_ld_vec(t3, cpu_env, cofs + i); + fni(vece, t0, t1, t2, t3, c); + tcg_gen_st_vec(t0, cpu_env, dofs + i); + } + tcg_temp_free_vec(t3); + tcg_temp_free_vec(t2); + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t0); +} + /* Expand a vector two-operand operation. */ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz, const GVecGen2 *g) @@ -1533,6 +1610,75 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, } } +/* Expand a vector four-operand operation. */ +void tcg_gen_gvec_4i(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, + uint32_t oprsz, uint32_t maxsz, int64_t c, + const GVecGen4i *g) +{ + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); + TCGType type; + uint32_t some; + + check_size_align(oprsz, maxsz, dofs | aofs | bofs | cofs); + check_overlap_4(dofs, aofs, bofs, cofs, maxsz); + + type = 0; + if (g->fniv) { + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); + } + switch (type) { + case TCG_TYPE_V256: + /* + * Recall that ARM SVE allows vector sizes that are not a + * power of 2, but always a multiple of 16. The intent is + * that e.g. size == 80 would be expanded with 2x32 + 1x16. + */ + some = QEMU_ALIGN_DOWN(oprsz, 32); + expand_4i_vec(g->vece, dofs, aofs, bofs, cofs, some, + 32, TCG_TYPE_V256, c, g->fniv); + if (some == oprsz) { + break; + } + dofs += some; + aofs += some; + bofs += some; + cofs += some; + oprsz -= some; + maxsz -= some; + /* fallthru */ + case TCG_TYPE_V128: + expand_4i_vec(g->vece, dofs, aofs, bofs, cofs, oprsz, + 16, TCG_TYPE_V128, c, g->fniv); + break; + case TCG_TYPE_V64: + expand_4i_vec(g->vece, dofs, aofs, bofs, cofs, oprsz, + 8, TCG_TYPE_V64, c, g->fniv); + break; + + case 0: + if (g->fni8 && check_size_impl(oprsz, 8)) { + expand_4i_i64(dofs, aofs, bofs, cofs, oprsz, c, g->fni8); + } else if (g->fni4 && check_size_impl(oprsz, 4)) { + expand_4i_i32(dofs, aofs, bofs, cofs, oprsz, c, g->fni4); + } else { + assert(g->fno != NULL); + tcg_gen_gvec_4_ool(dofs, aofs, bofs, cofs, + oprsz, maxsz, c, g->fno); + oprsz = maxsz; + } + break; + + default: + g_assert_not_reached(); + } + tcg_swap_vecop_list(hold_list); + + if (oprsz < maxsz) { + expand_clr(dofs + oprsz, maxsz - oprsz); + } +} + /* * Expand specific vector operations. */ |