TCG patch queue, plus one target/sh4 patch that Yoshinori Sato asked me to process. r~ The following changes since commit efbf38d73e5dcc4d5f8b98c6e7a12be1f3b91745: Merge tag 'for-upstream' of git://repo.or.cz/qemu/kevin into staging (2022-10-03 15:06:07 -0400) are available in the Git repository at: https://gitlab.com/rth7680/qemu.git tags/pull-tcg-20221004 for you to fetch changes up to ab419fd8a035a65942de4e63effcd55ccbf1a9fe: target/sh4: Fix TB_FLAG_UNALIGN (2022-10-04 12:33:05 -0700) ---------------------------------------------------------------- Cache CPUClass for use in hot code paths. Add CPUTLBEntryFull, probe_access_full, tlb_set_page_full. Add generic support for TARGET_TB_PCREL. tcg/ppc: Optimize 26-bit jumps using STQ for POWER 2.07 target/sh4: Fix TB_FLAG_UNALIGN ---------------------------------------------------------------- Alex Bennée (3): cpu: cache CPUClass in CPUState for hot code paths hw/core/cpu-sysemu: used cached class in cpu_asidx_from_attrs cputlb: used cached CPUClass in our hot-paths Leandro Lupori (1): tcg/ppc: Optimize 26-bit jumps Richard Henderson (16): accel/tcg: Rename CPUIOTLBEntry to CPUTLBEntryFull accel/tcg: Drop addr member from SavedIOTLB accel/tcg: Suppress auto-invalidate in probe_access_internal accel/tcg: Introduce probe_access_full accel/tcg: Introduce tlb_set_page_full include/exec: Introduce TARGET_PAGE_ENTRY_EXTRA accel/tcg: Remove PageDesc code_bitmap accel/tcg: Use bool for page_find_alloc accel/tcg: Use DisasContextBase in plugin_gen_tb_start accel/tcg: Do not align tb->page_addr[0] accel/tcg: Inline tb_flush_jmp_cache include/hw/core: Create struct CPUJumpCache hw/core: Add CPUClass.get_pc accel/tcg: Introduce tb_pc and log_pc accel/tcg: Introduce TARGET_TB_PCREL target/sh4: Fix TB_FLAG_UNALIGN accel/tcg/internal.h | 10 ++ accel/tcg/tb-hash.h | 1 + accel/tcg/tb-jmp-cache.h | 65 ++++++++ include/exec/cpu-common.h | 1 + include/exec/cpu-defs.h | 48 ++++-- include/exec/exec-all.h | 75 ++++++++- include/exec/plugin-gen.h | 7 +- include/hw/core/cpu.h | 28 ++-- include/qemu/typedefs.h | 2 + include/tcg/tcg.h | 2 +- target/sh4/cpu.h | 56 ++++--- accel/stubs/tcg-stub.c | 4 + accel/tcg/cpu-exec.c | 80 +++++----- accel/tcg/cputlb.c | 259 ++++++++++++++++++-------------- accel/tcg/plugin-gen.c | 22 +-- accel/tcg/translate-all.c | 214 ++++++++++++-------------- accel/tcg/translator.c | 2 +- cpu.c | 9 +- hw/core/cpu-common.c | 3 +- hw/core/cpu-sysemu.c | 5 +- linux-user/sh4/signal.c | 6 +- plugins/core.c | 2 +- target/alpha/cpu.c | 9 ++ target/arm/cpu.c | 17 ++- target/arm/mte_helper.c | 14 +- target/arm/sve_helper.c | 4 +- target/arm/translate-a64.c | 2 +- target/avr/cpu.c | 10 +- target/cris/cpu.c | 8 + target/hexagon/cpu.c | 10 +- target/hppa/cpu.c | 12 +- target/i386/cpu.c | 9 ++ target/i386/tcg/tcg-cpu.c | 2 +- target/loongarch/cpu.c | 11 +- target/m68k/cpu.c | 8 + target/microblaze/cpu.c | 10 +- target/mips/cpu.c | 8 + target/mips/tcg/exception.c | 2 +- target/mips/tcg/sysemu/special_helper.c | 2 +- target/nios2/cpu.c | 9 ++ target/openrisc/cpu.c | 10 +- target/ppc/cpu_init.c | 8 + target/riscv/cpu.c | 17 ++- target/rx/cpu.c | 10 +- target/s390x/cpu.c | 8 + target/s390x/tcg/mem_helper.c | 4 - target/sh4/cpu.c | 18 ++- target/sh4/helper.c | 6 +- target/sh4/translate.c | 90 +++++------ target/sparc/cpu.c | 10 +- target/tricore/cpu.c | 11 +- target/xtensa/cpu.c | 8 + tcg/tcg.c | 8 +- trace/control-target.c | 2 +- tcg/ppc/tcg-target.c.inc | 119 +++++++++++---- 55 files changed, 915 insertions(+), 462 deletions(-) create mode 100644 accel/tcg/tb-jmp-cache.h From: Alex Bennée <alex.bennee@linaro.org> The class cast checkers are quite expensive and always on (unlike the dynamic case who's checks are gated by CONFIG_QOM_CAST_DEBUG). To avoid the overhead of repeatedly checking something which should never change we cache the CPUClass reference for use in the hot code paths. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220811151413.3350684-3-alex.bennee@linaro.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20220923084803.498337-3-clg@kaod.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/core/cpu.h | 9 +++++++++ cpu.c | 9 ++++----- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ typedef int (*WriteCoreDumpFunction)(const void *buf, size_t size, */ #define CPU(obj) ((CPUState *)(obj)) +/* + * The class checkers bring in CPU_GET_CLASS() which is potentially + * expensive given the eventual call to + * object_class_dynamic_cast_assert(). Because of this the CPUState + * has a cached value for the class in cs->cc which is set up in + * cpu_exec_realizefn() for use in hot code paths. + */ typedef struct CPUClass CPUClass; DECLARE_CLASS_CHECKERS(CPUClass, CPU, TYPE_CPU) @@ -XXX,XX +XXX,XX @@ struct qemu_work_item; struct CPUState { /*< private >*/ DeviceState parent_obj; + /* cache to avoid expensive CPU_GET_CLASS */ + CPUClass *cc; /*< public >*/ int nr_cores; diff --git a/cpu.c b/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/cpu.c +++ b/cpu.c @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_cpu_common = { void cpu_exec_realizefn(CPUState *cpu, Error **errp) { -#ifndef CONFIG_USER_ONLY - CPUClass *cc = CPU_GET_CLASS(cpu); -#endif + /* cache the cpu class for the hotpath */ + cpu->cc = CPU_GET_CLASS(cpu); cpu_list_add(cpu); if (!accel_cpu_realizefn(cpu, errp)) { @@ -XXX,XX +XXX,XX @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_register(NULL, cpu->cpu_index, &vmstate_cpu_common, cpu); } - if (cc->sysemu_ops->legacy_vmsd != NULL) { - vmstate_register(NULL, cpu->cpu_index, cc->sysemu_ops->legacy_vmsd, cpu); + if (cpu->cc->sysemu_ops->legacy_vmsd != NULL) { + vmstate_register(NULL, cpu->cpu_index, cpu->cc->sysemu_ops->legacy_vmsd, cpu); } #endif /* CONFIG_USER_ONLY */ } -- 2.34.1 From: Alex Bennée <alex.bennee@linaro.org> This is a heavily used function so lets avoid the cost of CPU_GET_CLASS. On the romulus-bmc run it has a modest effect: Before: 36.812 s ± 0.506 s After: 35.912 s ± 0.168 s Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220811151413.3350684-4-alex.bennee@linaro.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20220923084803.498337-4-clg@kaod.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- hw/core/cpu-sysemu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/hw/core/cpu-sysemu.c b/hw/core/cpu-sysemu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/cpu-sysemu.c +++ b/hw/core/cpu-sysemu.c @@ -XXX,XX +XXX,XX @@ hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) { - CPUClass *cc = CPU_GET_CLASS(cpu); int ret = 0; - if (cc->sysemu_ops->asidx_from_attrs) { - ret = cc->sysemu_ops->asidx_from_attrs(cpu, attrs); + if (cpu->cc->sysemu_ops->asidx_from_attrs) { + ret = cpu->cc->sysemu_ops->asidx_from_attrs(cpu, attrs); assert(ret < cpu->num_ases && ret >= 0); } return ret; -- 2.34.1 From: Alex Bennée <alex.bennee@linaro.org> Before: 35.912 s ± 0.168 s After: 35.565 s ± 0.087 s Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220811151413.3350684-5-alex.bennee@linaro.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20220923084803.498337-5-clg@kaod.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cputlb.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr, static void tlb_fill(CPUState *cpu, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) { - CPUClass *cc = CPU_GET_CLASS(cpu); bool ok; /* * This is not a probe, so only valid return is success; failure * should result in exception + longjmp to the cpu loop. */ - ok = cc->tcg_ops->tlb_fill(cpu, addr, size, - access_type, mmu_idx, false, retaddr); + ok = cpu->cc->tcg_ops->tlb_fill(cpu, addr, size, + access_type, mmu_idx, false, retaddr); assert(ok); } @@ -XXX,XX +XXX,XX @@ static inline void cpu_unaligned_access(CPUState *cpu, vaddr addr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) { - CPUClass *cc = CPU_GET_CLASS(cpu); - - cc->tcg_ops->do_unaligned_access(cpu, addr, access_type, mmu_idx, retaddr); + cpu->cc->tcg_ops->do_unaligned_access(cpu, addr, access_type, + mmu_idx, retaddr); } static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr, @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, if (!tlb_hit_page(tlb_addr, page_addr)) { if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) { CPUState *cs = env_cpu(env); - CPUClass *cc = CPU_GET_CLASS(cs); - if (!cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type, - mmu_idx, nonfault, retaddr)) { + if (!cs->cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type, + mmu_idx, nonfault, retaddr)) { /* Non-faulting page table read failed. */ *phost = NULL; return TLB_INVALID_MASK; -- 2.34.1 This structure will shortly contain more than just data for accessing MMIO. Rename the 'addr' member to 'xlat_section' to more clearly indicate its purpose. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 22 ++++---- accel/tcg/cputlb.c | 102 +++++++++++++++++++------------------ target/arm/mte_helper.c | 14 ++--- target/arm/sve_helper.c | 4 +- target/arm/translate-a64.c | 2 +- 5 files changed, 73 insertions(+), 71 deletions(-) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ typedef uint64_t target_ulong; # endif # endif +/* Minimalized TLB entry for use by TCG fast path. */ typedef struct CPUTLBEntry { /* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address bit TARGET_PAGE_BITS-1..4 : Nonzero for accesses that should not @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntry { QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS)); -/* The IOTLB is not accessed directly inline by generated TCG code, - * so the CPUIOTLBEntry layout is not as critical as that of the - * CPUTLBEntry. (This is also why we don't want to combine the two - * structs into one.) +/* + * The full TLB entry, which is not accessed by generated TCG code, + * so the layout is not as critical as that of CPUTLBEntry. This is + * also why we don't want to combine the two structs. */ -typedef struct CPUIOTLBEntry { +typedef struct CPUTLBEntryFull { /* - * @addr contains: + * @xlat_section contains: * - in the lower TARGET_PAGE_BITS, a physical section number * - with the lower TARGET_PAGE_BITS masked off, an offset which * must be added to the virtual address to obtain: @@ -XXX,XX +XXX,XX @@ typedef struct CPUIOTLBEntry { * number is PHYS_SECTION_NOTDIRTY or PHYS_SECTION_ROM) * + the offset within the target MemoryRegion (otherwise) */ - hwaddr addr; + hwaddr xlat_section; MemTxAttrs attrs; -} CPUIOTLBEntry; +} CPUTLBEntryFull; /* * Data elements that are per MMU mode, minus the bits accessed by @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBDesc { size_t vindex; /* The tlb victim table, in two parts. */ CPUTLBEntry vtable[CPU_VTLB_SIZE]; - CPUIOTLBEntry viotlb[CPU_VTLB_SIZE]; - /* The iotlb. */ - CPUIOTLBEntry *iotlb; + CPUTLBEntryFull vfulltlb[CPU_VTLB_SIZE]; + CPUTLBEntryFull *fulltlb; } CPUTLBDesc; /* diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast, } g_free(fast->table); - g_free(desc->iotlb); + g_free(desc->fulltlb); tlb_window_reset(desc, now, 0); /* desc->n_used_entries is cleared by the caller */ fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS; fast->table = g_try_new(CPUTLBEntry, new_size); - desc->iotlb = g_try_new(CPUIOTLBEntry, new_size); + desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size); /* * If the allocations fail, try smaller sizes. We just freed some @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast, * allocations to fail though, so we progressively reduce the allocation * size, aborting if we cannot even allocate the smallest TLB we support. */ - while (fast->table == NULL || desc->iotlb == NULL) { + while (fast->table == NULL || desc->fulltlb == NULL) { if (new_size == (1 << CPU_TLB_DYN_MIN_BITS)) { error_report("%s: %s", __func__, strerror(errno)); abort(); @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast, fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS; g_free(fast->table); - g_free(desc->iotlb); + g_free(desc->fulltlb); fast->table = g_try_new(CPUTLBEntry, new_size); - desc->iotlb = g_try_new(CPUIOTLBEntry, new_size); + desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size); } } @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_init(CPUTLBDesc *desc, CPUTLBDescFast *fast, int64_t now) desc->n_used_entries = 0; fast->mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS; fast->table = g_new(CPUTLBEntry, n_entries); - desc->iotlb = g_new(CPUIOTLBEntry, n_entries); + desc->fulltlb = g_new(CPUTLBEntryFull, n_entries); tlb_mmu_flush_locked(desc, fast); } @@ -XXX,XX +XXX,XX @@ void tlb_destroy(CPUState *cpu) CPUTLBDescFast *fast = &env_tlb(env)->f[i]; g_free(fast->table); - g_free(desc->iotlb); + g_free(desc->fulltlb); } } @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, /* Evict the old entry into the victim tlb. */ copy_tlb_helper_locked(tv, te); - desc->viotlb[vidx] = desc->iotlb[index]; + desc->vfulltlb[vidx] = desc->fulltlb[index]; tlb_n_used_entries_dec(env, mmu_idx); } @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, * subtract here is that of the page base, and not the same as the * vaddr we add back in io_readx()/io_writex()/get_page_addr_code(). */ - desc->iotlb[index].addr = iotlb - vaddr_page; - desc->iotlb[index].attrs = attrs; + desc->fulltlb[index].xlat_section = iotlb - vaddr_page; + desc->fulltlb[index].attrs = attrs; /* Now calculate the new entry */ tn.addend = addend - vaddr_page; @@ -XXX,XX +XXX,XX @@ static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr, } } -static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, +static uint64_t io_readx(CPUArchState *env, CPUTLBEntryFull *full, int mmu_idx, target_ulong addr, uintptr_t retaddr, MMUAccessType access_type, MemOp op) { @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, bool locked = false; MemTxResult r; - section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + section = iotlb_to_section(cpu, full->xlat_section, full->attrs); mr = section->mr; - mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + mr_offset = (full->xlat_section & TARGET_PAGE_MASK) + addr; cpu->mem_io_pc = retaddr; if (!cpu->can_do_io) { cpu_io_recompile(cpu, retaddr); @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, qemu_mutex_lock_iothread(); locked = true; } - r = memory_region_dispatch_read(mr, mr_offset, &val, op, iotlbentry->attrs); + r = memory_region_dispatch_read(mr, mr_offset, &val, op, full->attrs); if (r != MEMTX_OK) { hwaddr physaddr = mr_offset + section->offset_within_address_space - section->offset_within_region; cpu_transaction_failed(cpu, physaddr, addr, memop_size(op), access_type, - mmu_idx, iotlbentry->attrs, r, retaddr); + mmu_idx, full->attrs, r, retaddr); } if (locked) { qemu_mutex_unlock_iothread(); @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, } /* - * Save a potentially trashed IOTLB entry for later lookup by plugin. - * This is read by tlb_plugin_lookup if the iotlb entry doesn't match + * Save a potentially trashed CPUTLBEntryFull for later lookup by plugin. + * This is read by tlb_plugin_lookup if the fulltlb entry doesn't match * because of the side effect of io_writex changing memory layout. */ static void save_iotlb_data(CPUState *cs, hwaddr addr, @@ -XXX,XX +XXX,XX @@ static void save_iotlb_data(CPUState *cs, hwaddr addr, #endif } -static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, +static void io_writex(CPUArchState *env, CPUTLBEntryFull *full, int mmu_idx, uint64_t val, target_ulong addr, uintptr_t retaddr, MemOp op) { @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, bool locked = false; MemTxResult r; - section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + section = iotlb_to_section(cpu, full->xlat_section, full->attrs); mr = section->mr; - mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + mr_offset = (full->xlat_section & TARGET_PAGE_MASK) + addr; if (!cpu->can_do_io) { cpu_io_recompile(cpu, retaddr); } @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, * The memory_region_dispatch may trigger a flush/resize * so for plugins we save the iotlb_data just in case. */ - save_iotlb_data(cpu, iotlbentry->addr, section, mr_offset); + save_iotlb_data(cpu, full->xlat_section, section, mr_offset); if (!qemu_mutex_iothread_locked()) { qemu_mutex_lock_iothread(); locked = true; } - r = memory_region_dispatch_write(mr, mr_offset, val, op, iotlbentry->attrs); + r = memory_region_dispatch_write(mr, mr_offset, val, op, full->attrs); if (r != MEMTX_OK) { hwaddr physaddr = mr_offset + section->offset_within_address_space - section->offset_within_region; cpu_transaction_failed(cpu, physaddr, addr, memop_size(op), - MMU_DATA_STORE, mmu_idx, iotlbentry->attrs, r, + MMU_DATA_STORE, mmu_idx, full->attrs, r, retaddr); } if (locked) { @@ -XXX,XX +XXX,XX @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index, copy_tlb_helper_locked(vtlb, &tmptlb); qemu_spin_unlock(&env_tlb(env)->c.lock); - CPUIOTLBEntry tmpio, *io = &env_tlb(env)->d[mmu_idx].iotlb[index]; - CPUIOTLBEntry *vio = &env_tlb(env)->d[mmu_idx].viotlb[vidx]; - tmpio = *io; *io = *vio; *vio = tmpio; + CPUTLBEntryFull *f1 = &env_tlb(env)->d[mmu_idx].fulltlb[index]; + CPUTLBEntryFull *f2 = &env_tlb(env)->d[mmu_idx].vfulltlb[vidx]; + CPUTLBEntryFull tmpf; + tmpf = *f1; *f1 = *f2; *f2 = tmpf; return true; } } @@ -XXX,XX +XXX,XX @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index, (ADDR) & TARGET_PAGE_MASK) static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size, - CPUIOTLBEntry *iotlbentry, uintptr_t retaddr) + CPUTLBEntryFull *full, uintptr_t retaddr) { - ram_addr_t ram_addr = mem_vaddr + iotlbentry->addr; + ram_addr_t ram_addr = mem_vaddr + full->xlat_section; trace_memory_notdirty_write_access(mem_vaddr, ram_addr, size); @@ -XXX,XX +XXX,XX @@ int probe_access_flags(CPUArchState *env, target_ulong addr, /* Handle clean RAM pages. */ if (unlikely(flags & TLB_NOTDIRTY)) { uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; - notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr); + notdirty_write(env_cpu(env), addr, 1, full, retaddr); flags &= ~TLB_NOTDIRTY; } @@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) { uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; /* Handle watchpoints. */ if (flags & TLB_WATCHPOINT) { int wp_access = (access_type == MMU_DATA_STORE ? BP_MEM_WRITE : BP_MEM_READ); cpu_check_watchpoint(env_cpu(env), addr, size, - iotlbentry->attrs, wp_access, retaddr); + full->attrs, wp_access, retaddr); } /* Handle clean RAM pages. */ if (flags & TLB_NOTDIRTY) { - notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr); + notdirty_write(env_cpu(env), addr, 1, full, retaddr); } } @@ -XXX,XX +XXX,XX @@ tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr, * should have just filled the TLB. The one corner case is io_writex * which can cause TLB flushes and potential resizing of the TLBs * losing the information we need. In those cases we need to recover - * data from a copy of the iotlbentry. As long as this always occurs + * data from a copy of the CPUTLBEntryFull. As long as this always occurs * from the same thread (which a mem callback will be) this is safe. */ @@ -XXX,XX +XXX,XX @@ bool tlb_plugin_lookup(CPUState *cpu, target_ulong addr, int mmu_idx, if (likely(tlb_hit(tlb_addr, addr))) { /* We must have an iotlb entry for MMIO */ if (tlb_addr & TLB_MMIO) { - CPUIOTLBEntry *iotlbentry; - iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + CPUTLBEntryFull *full; + full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; data->is_io = true; - data->v.io.section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); - data->v.io.offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + data->v.io.section = + iotlb_to_section(cpu, full->xlat_section, full->attrs); + data->v.io.offset = (full->xlat_section & TARGET_PAGE_MASK) + addr; } else { data->is_io = false; data->v.ram.hostaddr = (void *)((uintptr_t)addr + tlbe->addend); @@ -XXX,XX +XXX,XX @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, if (unlikely(tlb_addr & TLB_NOTDIRTY)) { notdirty_write(env_cpu(env), addr, size, - &env_tlb(env)->d[mmu_idx].iotlb[index], retaddr); + &env_tlb(env)->d[mmu_idx].fulltlb[index], retaddr); } return hostaddr; @@ -XXX,XX +XXX,XX @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi, /* Handle anything that isn't just a straight memory access. */ if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) { - CPUIOTLBEntry *iotlbentry; + CPUTLBEntryFull *full; bool need_swap; /* For anything that is unaligned, recurse through full_load. */ @@ -XXX,XX +XXX,XX @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi, goto do_unaligned_access; } - iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; /* Handle watchpoints. */ if (unlikely(tlb_addr & TLB_WATCHPOINT)) { /* On watchpoint hit, this will longjmp out. */ cpu_check_watchpoint(env_cpu(env), addr, size, - iotlbentry->attrs, BP_MEM_READ, retaddr); + full->attrs, BP_MEM_READ, retaddr); } need_swap = size > 1 && (tlb_addr & TLB_BSWAP); /* Handle I/O access. */ if (likely(tlb_addr & TLB_MMIO)) { - return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, + return io_readx(env, full, mmu_idx, addr, retaddr, access_type, op ^ (need_swap * MO_BSWAP)); } @@ -XXX,XX +XXX,XX @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val, */ if (unlikely(tlb_addr & TLB_WATCHPOINT)) { cpu_check_watchpoint(env_cpu(env), addr, size - size2, - env_tlb(env)->d[mmu_idx].iotlb[index].attrs, + env_tlb(env)->d[mmu_idx].fulltlb[index].attrs, BP_MEM_WRITE, retaddr); } if (unlikely(tlb_addr2 & TLB_WATCHPOINT)) { cpu_check_watchpoint(env_cpu(env), page2, size2, - env_tlb(env)->d[mmu_idx].iotlb[index2].attrs, + env_tlb(env)->d[mmu_idx].fulltlb[index2].attrs, BP_MEM_WRITE, retaddr); } @@ -XXX,XX +XXX,XX @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, /* Handle anything that isn't just a straight memory access. */ if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) { - CPUIOTLBEntry *iotlbentry; + CPUTLBEntryFull *full; bool need_swap; /* For anything that is unaligned, recurse through byte stores. */ @@ -XXX,XX +XXX,XX @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, goto do_unaligned_access; } - iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; /* Handle watchpoints. */ if (unlikely(tlb_addr & TLB_WATCHPOINT)) { /* On watchpoint hit, this will longjmp out. */ cpu_check_watchpoint(env_cpu(env), addr, size, - iotlbentry->attrs, BP_MEM_WRITE, retaddr); + full->attrs, BP_MEM_WRITE, retaddr); } need_swap = size > 1 && (tlb_addr & TLB_BSWAP); /* Handle I/O access. */ if (tlb_addr & TLB_MMIO) { - io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr, + io_writex(env, full, mmu_idx, val, addr, retaddr, op ^ (need_swap * MO_BSWAP)); return; } @@ -XXX,XX +XXX,XX @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, /* Handle clean RAM pages. */ if (tlb_addr & TLB_NOTDIRTY) { - notdirty_write(env_cpu(env), addr, size, iotlbentry, retaddr); + notdirty_write(env_cpu(env), addr, size, full, retaddr); } haddr = (void *)((uintptr_t)addr + entry->addend); diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, return tags + index; #else uintptr_t index; - CPUIOTLBEntry *iotlbentry; + CPUTLBEntryFull *full; int in_page, flags; ram_addr_t ptr_ra; hwaddr ptr_paddr, tag_paddr, xlat; @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, assert(!(flags & TLB_INVALID_MASK)); /* - * Find the iotlbentry for ptr. This *must* be present in the TLB + * Find the CPUTLBEntryFull for ptr. This *must* be present in the TLB * because we just found the mapping. * TODO: Perhaps there should be a cputlb helper that returns a * matching tlb entry + iotlb entry. @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, g_assert(tlb_hit(comparator, ptr)); } # endif - iotlbentry = &env_tlb(env)->d[ptr_mmu_idx].iotlb[index]; + full = &env_tlb(env)->d[ptr_mmu_idx].fulltlb[index]; /* If the virtual page MemAttr != Tagged, access unchecked. */ - if (!arm_tlb_mte_tagged(&iotlbentry->attrs)) { + if (!arm_tlb_mte_tagged(&full->attrs)) { return NULL; } @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, int wp = ptr_access == MMU_DATA_LOAD ? BP_MEM_READ : BP_MEM_WRITE; assert(ra != 0); cpu_check_watchpoint(env_cpu(env), ptr, ptr_size, - iotlbentry->attrs, wp, ra); + full->attrs, wp, ra); } /* @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, tag_paddr = ptr_paddr >> (LOG2_TAG_GRANULE + 1); /* Look up the address in tag space. */ - tag_asi = iotlbentry->attrs.secure ? ARMASIdx_TagS : ARMASIdx_TagNS; + tag_asi = full->attrs.secure ? ARMASIdx_TagS : ARMASIdx_TagNS; tag_as = cpu_get_address_space(env_cpu(env), tag_asi); mr = address_space_translate(tag_as, tag_paddr, &xlat, NULL, tag_access == MMU_DATA_STORE, - iotlbentry->attrs); + full->attrs); /* * Note that @mr will never be NULL. If there is nothing in the address diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, g_assert(tlb_hit(comparator, addr)); # endif - CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; - info->attrs = iotlbentry->attrs; + CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; + info->attrs = full->attrs; } #endif diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool is_guarded_page(CPUARMState *env, DisasContext *s) * table entry even for that case. */ return (tlb_hit(entry->addr_code, addr) && - arm_tlb_bti_gp(&env_tlb(env)->d[mmu_idx].iotlb[index].attrs)); + arm_tlb_bti_gp(&env_tlb(env)->d[mmu_idx].fulltlb[index].attrs)); #endif } -- 2.34.1 This field is only written, not read; remove it. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/core/cpu.h | 1 - accel/tcg/cputlb.c | 7 +++---- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct CPUWatchpoint { * the memory regions get moved around by io_writex. */ typedef struct SavedIOTLB { - hwaddr addr; MemoryRegionSection *section; hwaddr mr_offset; } SavedIOTLB; diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUTLBEntryFull *full, * This is read by tlb_plugin_lookup if the fulltlb entry doesn't match * because of the side effect of io_writex changing memory layout. */ -static void save_iotlb_data(CPUState *cs, hwaddr addr, - MemoryRegionSection *section, hwaddr mr_offset) +static void save_iotlb_data(CPUState *cs, MemoryRegionSection *section, + hwaddr mr_offset) { #ifdef CONFIG_PLUGIN SavedIOTLB *saved = &cs->saved_iotlb; - saved->addr = addr; saved->section = section; saved->mr_offset = mr_offset; #endif @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUTLBEntryFull *full, * The memory_region_dispatch may trigger a flush/resize * so for plugins we save the iotlb_data just in case. */ - save_iotlb_data(cpu, full->xlat_section, section, mr_offset); + save_iotlb_data(cpu, section, mr_offset); if (!qemu_mutex_iothread_locked()) { qemu_mutex_lock_iothread(); -- 2.34.1 When PAGE_WRITE_INV is set when calling tlb_set_page, we immediately set TLB_INVALID_MASK in order to force tlb_fill to be called on the next lookup. Here in probe_access_internal, we have just called tlb_fill and eliminated true misses, thus the lookup must be valid. This allows us to remove a warning comment from s390x. There doesn't seem to be a reason to change the code though. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cputlb.c | 10 +++++++++- target/s390x/tcg/mem_helper.c | 4 ---- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, } tlb_addr = tlb_read_ofs(entry, elt_ofs); + flags = TLB_FLAGS_MASK; page_addr = addr & TARGET_PAGE_MASK; if (!tlb_hit_page(tlb_addr, page_addr)) { if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) { @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, /* TLB resize via tlb_fill may have moved the entry. */ entry = tlb_entry(env, mmu_idx, addr); + + /* + * With PAGE_WRITE_INV, we set TLB_INVALID_MASK immediately, + * to force the next access through tlb_fill. We've just + * called tlb_fill, so we know that this entry *is* valid. + */ + flags &= ~TLB_INVALID_MASK; } tlb_addr = tlb_read_ofs(entry, elt_ofs); } - flags = tlb_addr & TLB_FLAGS_MASK; + flags &= tlb_addr; /* Fold all "mmio-like" bits into TLB_MMIO. This is not RAM. */ if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) { diff --git a/target/s390x/tcg/mem_helper.c b/target/s390x/tcg/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/tcg/mem_helper.c +++ b/target/s390x/tcg/mem_helper.c @@ -XXX,XX +XXX,XX @@ static int s390_probe_access(CPUArchState *env, target_ulong addr, int size, #else int flags; - /* - * For !CONFIG_USER_ONLY, we cannot rely on TLB_INVALID_MASK or haddr==NULL - * to detect if there was an exception during tlb_fill(). - */ env->tlb_fill_exc = 0; flags = probe_access_flags(env, addr, access_type, mmu_idx, nonfault, phost, ra); -- 2.34.1 Add an interface to return the CPUTLBEntryFull struct that goes with the lookup. The result is not intended to be valid across multiple lookups, so the user must use the results immediately. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 15 +++++++++++++ include/qemu/typedefs.h | 1 + accel/tcg/cputlb.c | 47 +++++++++++++++++++++++++---------------- 3 files changed, 45 insertions(+), 18 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ int probe_access_flags(CPUArchState *env, target_ulong addr, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t retaddr); +#ifndef CONFIG_USER_ONLY +/** + * probe_access_full: + * Like probe_access_flags, except also return into @pfull. + * + * The CPUTLBEntryFull structure returned via @pfull is transient + * and must be consumed or copied immediately, before any further + * access or changes to TLB @mmu_idx. + */ +int probe_access_full(CPUArchState *env, target_ulong addr, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, + CPUTLBEntryFull **pfull, uintptr_t retaddr); +#endif + #define CODE_GEN_ALIGN 16 /* must be >= of the size of a icache line */ /* Estimated block size for TB allocation. */ diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -XXX,XX +XXX,XX @@ typedef struct ConfidentialGuestSupport ConfidentialGuestSupport; typedef struct CPUAddressSpace CPUAddressSpace; typedef struct CPUArchState CPUArchState; typedef struct CPUState CPUState; +typedef struct CPUTLBEntryFull CPUTLBEntryFull; typedef struct DeviceListener DeviceListener; typedef struct DeviceState DeviceState; typedef struct DirtyBitmapSnapshot DirtyBitmapSnapshot; diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size, static int probe_access_internal(CPUArchState *env, target_ulong addr, int fault_size, MMUAccessType access_type, int mmu_idx, bool nonfault, - void **phost, uintptr_t retaddr) + void **phost, CPUTLBEntryFull **pfull, + uintptr_t retaddr) { uintptr_t index = tlb_index(env, mmu_idx, addr); CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr); @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, mmu_idx, nonfault, retaddr)) { /* Non-faulting page table read failed. */ *phost = NULL; + *pfull = NULL; return TLB_INVALID_MASK; } /* TLB resize via tlb_fill may have moved the entry. */ + index = tlb_index(env, mmu_idx, addr); entry = tlb_entry(env, mmu_idx, addr); /* @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, } flags &= tlb_addr; + *pfull = &env_tlb(env)->d[mmu_idx].fulltlb[index]; + /* Fold all "mmio-like" bits into TLB_MMIO. This is not RAM. */ if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) { *phost = NULL; @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, return flags; } -int probe_access_flags(CPUArchState *env, target_ulong addr, - MMUAccessType access_type, int mmu_idx, - bool nonfault, void **phost, uintptr_t retaddr) +int probe_access_full(CPUArchState *env, target_ulong addr, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, CPUTLBEntryFull **pfull, + uintptr_t retaddr) { - int flags; - - flags = probe_access_internal(env, addr, 0, access_type, mmu_idx, - nonfault, phost, retaddr); + int flags = probe_access_internal(env, addr, 0, access_type, mmu_idx, + nonfault, phost, pfull, retaddr); /* Handle clean RAM pages. */ if (unlikely(flags & TLB_NOTDIRTY)) { - uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; - - notdirty_write(env_cpu(env), addr, 1, full, retaddr); + notdirty_write(env_cpu(env), addr, 1, *pfull, retaddr); flags &= ~TLB_NOTDIRTY; } return flags; } +int probe_access_flags(CPUArchState *env, target_ulong addr, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, uintptr_t retaddr) +{ + CPUTLBEntryFull *full; + + return probe_access_full(env, addr, access_type, mmu_idx, + nonfault, phost, &full, retaddr); +} + void *probe_access(CPUArchState *env, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) { + CPUTLBEntryFull *full; void *host; int flags; g_assert(-(addr | TARGET_PAGE_MASK) >= size); flags = probe_access_internal(env, addr, size, access_type, mmu_idx, - false, &host, retaddr); + false, &host, &full, retaddr); /* Per the interface, size == 0 merely faults the access. */ if (size == 0) { @@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, } if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) { - uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; - /* Handle watchpoints. */ if (flags & TLB_WATCHPOINT) { int wp_access = (access_type == MMU_DATA_STORE @@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, MMUAccessType access_type, int mmu_idx) { + CPUTLBEntryFull *full; void *host; int flags; flags = probe_access_internal(env, addr, 0, access_type, - mmu_idx, true, &host, 0); + mmu_idx, true, &host, &full, 0); /* No combination of flags are expected by the caller. */ return flags ? NULL : host; @@ -XXX,XX +XXX,XX @@ void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr, void **hostp) { + CPUTLBEntryFull *full; void *p; (void)probe_access_internal(env, addr, 1, MMU_INST_FETCH, - cpu_mmu_index(env, true), false, &p, 0); + cpu_mmu_index(env, true), false, &p, &full, 0); if (p == NULL) { return -1; } -- 2.34.1 Now that we have collected all of the page data into CPUTLBEntryFull, provide an interface to record that all in one go, instead of using 4 arguments. This interface allows CPUTLBEntryFull to be extended without having to change the number of arguments. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 14 +++++++++++ include/exec/exec-all.h | 22 ++++++++++++++++++ accel/tcg/cputlb.c | 51 ++++++++++++++++++++++++++--------------- 3 files changed, 69 insertions(+), 18 deletions(-) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntryFull { * + the offset within the target MemoryRegion (otherwise) */ hwaddr xlat_section; + + /* + * @phys_addr contains the physical address in the address space + * given by cpu_asidx_from_attrs(cpu, @attrs). + */ + hwaddr phys_addr; + + /* @attrs contains the memory transaction attributes for the page. */ MemTxAttrs attrs; + + /* @prot contains the complete protections for the page. */ + uint8_t prot; + + /* @lg_page_size contains the log2 of the page size. */ + uint8_t lg_page_size; } CPUTLBEntryFull; /* diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap, unsigned bits); +/** + * tlb_set_page_full: + * @cpu: CPU context + * @mmu_idx: mmu index of the tlb to modify + * @vaddr: virtual address of the entry to add + * @full: the details of the tlb entry + * + * Add an entry to @cpu tlb index @mmu_idx. All of the fields of + * @full must be filled, except for xlat_section, and constitute + * the complete description of the translated page. + * + * This is generally called by the target tlb_fill function after + * having performed a successful page table walk to find the physical + * address and attributes for the translation. + * + * At most one entry for a given virtual address is permitted. Only a + * single TARGET_PAGE_SIZE region is mapped; @full->lg_page_size is only + * used by tlb_flush_page. + */ +void tlb_set_page_full(CPUState *cpu, int mmu_idx, target_ulong vaddr, + CPUTLBEntryFull *full); + /** * tlb_set_page_with_attrs: * @cpu: CPU to add this TLB entry for diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tlb_add_large_page(CPUArchState *env, int mmu_idx, env_tlb(env)->d[mmu_idx].large_page_mask = lp_mask; } -/* Add a new TLB entry. At most one entry for a given virtual address +/* + * Add a new TLB entry. At most one entry for a given virtual address * is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the * supplied size is only used by tlb_flush_page. * * Called from TCG-generated code, which is under an RCU read-side * critical section. */ -void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, - hwaddr paddr, MemTxAttrs attrs, int prot, - int mmu_idx, target_ulong size) +void tlb_set_page_full(CPUState *cpu, int mmu_idx, + target_ulong vaddr, CPUTLBEntryFull *full) { CPUArchState *env = cpu->env_ptr; CPUTLB *tlb = env_tlb(env); @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, CPUTLBEntry *te, tn; hwaddr iotlb, xlat, sz, paddr_page; target_ulong vaddr_page; - int asidx = cpu_asidx_from_attrs(cpu, attrs); - int wp_flags; + int asidx, wp_flags, prot; bool is_ram, is_romd; assert_cpu_is_self(cpu); - if (size <= TARGET_PAGE_SIZE) { + if (full->lg_page_size <= TARGET_PAGE_BITS) { sz = TARGET_PAGE_SIZE; } else { - tlb_add_large_page(env, mmu_idx, vaddr, size); - sz = size; + sz = (hwaddr)1 << full->lg_page_size; + tlb_add_large_page(env, mmu_idx, vaddr, sz); } vaddr_page = vaddr & TARGET_PAGE_MASK; - paddr_page = paddr & TARGET_PAGE_MASK; + paddr_page = full->phys_addr & TARGET_PAGE_MASK; + prot = full->prot; + asidx = cpu_asidx_from_attrs(cpu, full->attrs); section = address_space_translate_for_iotlb(cpu, asidx, paddr_page, - &xlat, &sz, attrs, &prot); + &xlat, &sz, full->attrs, &prot); assert(sz >= TARGET_PAGE_SIZE); tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx " prot=%x idx=%d\n", - vaddr, paddr, prot, mmu_idx); + vaddr, full->phys_addr, prot, mmu_idx); address = vaddr_page; - if (size < TARGET_PAGE_SIZE) { + if (full->lg_page_size < TARGET_PAGE_BITS) { /* Repeat the MMU check and TLB fill on every access. */ address |= TLB_INVALID_MASK; } - if (attrs.byte_swap) { + if (full->attrs.byte_swap) { address |= TLB_BSWAP; } @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, * subtract here is that of the page base, and not the same as the * vaddr we add back in io_readx()/io_writex()/get_page_addr_code(). */ + desc->fulltlb[index] = *full; desc->fulltlb[index].xlat_section = iotlb - vaddr_page; - desc->fulltlb[index].attrs = attrs; + desc->fulltlb[index].phys_addr = paddr_page; + desc->fulltlb[index].prot = prot; /* Now calculate the new entry */ tn.addend = addend - vaddr_page; @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, qemu_spin_unlock(&tlb->c.lock); } -/* Add a new TLB entry, but without specifying the memory - * transaction attributes to be used. - */ +void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, + hwaddr paddr, MemTxAttrs attrs, int prot, + int mmu_idx, target_ulong size) +{ + CPUTLBEntryFull full = { + .phys_addr = paddr, + .attrs = attrs, + .prot = prot, + .lg_page_size = ctz64(size) + }; + + assert(is_power_of_2(size)); + tlb_set_page_full(cpu, mmu_idx, vaddr, &full); +} + void tlb_set_page(CPUState *cpu, target_ulong vaddr, hwaddr paddr, int prot, int mmu_idx, target_ulong size) -- 2.34.1 Allow the target to cache items from the guest page tables. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntryFull { /* @lg_page_size contains the log2 of the page size. */ uint8_t lg_page_size; + + /* + * Allow target-specific additions to this structure. + * This may be used to cache items from the guest cpu + * page tables for later use by the implementation. + */ +#ifdef TARGET_PAGE_ENTRY_EXTRA + TARGET_PAGE_ENTRY_EXTRA +#endif } CPUTLBEntryFull; /* -- 2.34.1 This bitmap is created and discarded immediately. We gain nothing by its existence. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220822232338.1727934-2-richard.henderson@linaro.org> --- accel/tcg/translate-all.c | 78 ++------------------------------------- 1 file changed, 4 insertions(+), 74 deletions(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ #define assert_memory_lock() tcg_debug_assert(have_mmap_lock()) #endif -#define SMC_BITMAP_USE_THRESHOLD 10 - typedef struct PageDesc { /* list of TBs intersecting this ram page */ uintptr_t first_tb; -#ifdef CONFIG_SOFTMMU - /* in order to optimize self modifying code, we count the number - of lookups we do to a given page to use a bitmap */ - unsigned long *code_bitmap; - unsigned int code_write_count; -#else +#ifdef CONFIG_USER_ONLY unsigned long flags; void *target_data; #endif -#ifndef CONFIG_USER_ONLY +#ifdef CONFIG_SOFTMMU QemuSpin lock; #endif } PageDesc; @@ -XXX,XX +XXX,XX @@ void tb_htable_init(void) qht_init(&tb_ctx.htable, tb_cmp, CODE_GEN_HTABLE_SIZE, mode); } -/* call with @p->lock held */ -static inline void invalidate_page_bitmap(PageDesc *p) -{ - assert_page_locked(p); -#ifdef CONFIG_SOFTMMU - g_free(p->code_bitmap); - p->code_bitmap = NULL; - p->code_write_count = 0; -#endif -} - /* Set to NULL all the 'first_tb' fields in all PageDescs. */ static void page_flush_tb_1(int level, void **lp) { @@ -XXX,XX +XXX,XX @@ static void page_flush_tb_1(int level, void **lp) for (i = 0; i < V_L2_SIZE; ++i) { page_lock(&pd[i]); pd[i].first_tb = (uintptr_t)NULL; - invalidate_page_bitmap(pd + i); page_unlock(&pd[i]); } } else { @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) if (rm_from_page_list) { p = page_find(tb->page_addr[0] >> TARGET_PAGE_BITS); tb_page_remove(p, tb); - invalidate_page_bitmap(p); if (tb->page_addr[1] != -1) { p = page_find(tb->page_addr[1] >> TARGET_PAGE_BITS); tb_page_remove(p, tb); - invalidate_page_bitmap(p); } } @@ -XXX,XX +XXX,XX @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr) } } -#ifdef CONFIG_SOFTMMU -/* call with @p->lock held */ -static void build_page_bitmap(PageDesc *p) -{ - int n, tb_start, tb_end; - TranslationBlock *tb; - - assert_page_locked(p); - p->code_bitmap = bitmap_new(TARGET_PAGE_SIZE); - - PAGE_FOR_EACH_TB(p, tb, n) { - /* NOTE: this is subtle as a TB may span two physical pages */ - if (n == 0) { - /* NOTE: tb_end may be after the end of the page, but - it is not a problem */ - tb_start = tb->pc & ~TARGET_PAGE_MASK; - tb_end = tb_start + tb->size; - if (tb_end > TARGET_PAGE_SIZE) { - tb_end = TARGET_PAGE_SIZE; - } - } else { - tb_start = 0; - tb_end = ((tb->pc + tb->size) & ~TARGET_PAGE_MASK); - } - bitmap_set(p->code_bitmap, tb_start, tb_end - tb_start); - } -} -#endif - /* add the tb in the target page and protect it if necessary * * Called with mmap_lock held for user-mode emulation. @@ -XXX,XX +XXX,XX @@ static inline void tb_page_add(PageDesc *p, TranslationBlock *tb, page_already_protected = p->first_tb != (uintptr_t)NULL; #endif p->first_tb = (uintptr_t)tb | n; - invalidate_page_bitmap(p); #if defined(CONFIG_USER_ONLY) /* translator_loop() must have made all TB pages non-writable */ @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, /* remove TB from the page(s) if we couldn't insert it */ if (unlikely(existing_tb)) { tb_page_remove(p, tb); - invalidate_page_bitmap(p); if (p2) { tb_page_remove(p2, tb); - invalidate_page_bitmap(p2); } tb = existing_tb; } @@ -XXX,XX +XXX,XX @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages, #if !defined(CONFIG_USER_ONLY) /* if no code remaining, no need to continue to use slow writes */ if (!p->first_tb) { - invalidate_page_bitmap(p); tlb_unprotect_code(start); } #endif @@ -XXX,XX +XXX,XX @@ void tb_invalidate_phys_page_fast(struct page_collection *pages, } assert_page_locked(p); - if (!p->code_bitmap && - ++p->code_write_count >= SMC_BITMAP_USE_THRESHOLD) { - build_page_bitmap(p); - } - if (p->code_bitmap) { - unsigned int nr; - unsigned long b; - - nr = start & ~TARGET_PAGE_MASK; - b = p->code_bitmap[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG - 1)); - if (b & ((1 << len) - 1)) { - goto do_invalidate; - } - } else { - do_invalidate: - tb_invalidate_phys_page_range__locked(pages, p, start, start + len, - retaddr); - } + tb_invalidate_phys_page_range__locked(pages, p, start, start + len, + retaddr); } #else /* Called with mmap_lock held. If pc is not 0 then it indicates the -- 2.34.1 Bool is more appropriate type for the alloc parameter. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/translate-all.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ void page_init(void) #endif } -static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc) +static PageDesc *page_find_alloc(tb_page_addr_t index, bool alloc) { PageDesc *pd; void **lp; @@ -XXX,XX +XXX,XX @@ static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc) static inline PageDesc *page_find(tb_page_addr_t index) { - return page_find_alloc(index, 0); + return page_find_alloc(index, false); } static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, - PageDesc **ret_p2, tb_page_addr_t phys2, int alloc); + PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc); /* In user-mode page locks aren't used; mmap_lock is enough */ #ifdef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static inline void page_unlock(PageDesc *pd) /* lock the page(s) of a TB in the correct acquisition order */ static inline void page_lock_tb(const TranslationBlock *tb) { - page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], 0); + page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], false); } static inline void page_unlock_tb(const TranslationBlock *tb) @@ -XXX,XX +XXX,XX @@ void page_collection_unlock(struct page_collection *set) #endif /* !CONFIG_USER_ONLY */ static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, - PageDesc **ret_p2, tb_page_addr_t phys2, int alloc) + PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc) { PageDesc *p1, *p2; tb_page_addr_t page1; @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, * Note that inserting into the hash table first isn't an option, since * we can only insert TBs that are fully initialized. */ - page_lock_pair(&p, phys_pc, &p2, phys_page2, 1); + page_lock_pair(&p, phys_pc, &p2, phys_page2, true); tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK); if (p2) { tb_page_add(p2, tb, 1, phys_page2); @@ -XXX,XX +XXX,XX @@ void page_set_flags(target_ulong start, target_ulong end, int flags) for (addr = start, len = end - start; len != 0; len -= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) { - PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, 1); + PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, true); /* If the write protection bit is set, then we invalidate the code inside. */ -- 2.34.1 Use the pc coming from db->pc_first rather than the TB. Use the cached host_addr rather than re-computing for the first page. We still need a separate lookup for the second page because it won't be computed for DisasContextBase until the translator actually performs a read from the page. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/plugin-gen.h | 7 ++++--- accel/tcg/plugin-gen.c | 22 +++++++++++----------- accel/tcg/translator.c | 2 +- 3 files changed, 16 insertions(+), 15 deletions(-) diff --git a/include/exec/plugin-gen.h b/include/exec/plugin-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/plugin-gen.h +++ b/include/exec/plugin-gen.h @@ -XXX,XX +XXX,XX @@ struct DisasContextBase; #ifdef CONFIG_PLUGIN -bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool supress); +bool plugin_gen_tb_start(CPUState *cpu, const struct DisasContextBase *db, + bool supress); void plugin_gen_tb_end(CPUState *cpu); void plugin_gen_insn_start(CPUState *cpu, const struct DisasContextBase *db); void plugin_gen_insn_end(void); @@ -XXX,XX +XXX,XX @@ static inline void plugin_insn_append(abi_ptr pc, const void *from, size_t size) #else /* !CONFIG_PLUGIN */ -static inline -bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool supress) +static inline bool +plugin_gen_tb_start(CPUState *cpu, const struct DisasContextBase *db, bool sup) { return false; } diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -XXX,XX +XXX,XX @@ static void plugin_gen_inject(const struct qemu_plugin_tb *plugin_tb) pr_ops(); } -bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_only) +bool plugin_gen_tb_start(CPUState *cpu, const DisasContextBase *db, + bool mem_only) { bool ret = false; @@ -XXX,XX +XXX,XX @@ bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_onl ret = true; - ptb->vaddr = tb->pc; + ptb->vaddr = db->pc_first; ptb->vaddr2 = -1; - get_page_addr_code_hostp(cpu->env_ptr, tb->pc, &ptb->haddr1); + ptb->haddr1 = db->host_addr[0]; ptb->haddr2 = NULL; ptb->mem_only = mem_only; @@ -XXX,XX +XXX,XX @@ void plugin_gen_insn_start(CPUState *cpu, const DisasContextBase *db) * Note that we skip this when haddr1 == NULL, e.g. when we're * fetching instructions from a region not backed by RAM. */ - if (likely(ptb->haddr1 != NULL && ptb->vaddr2 == -1) && - unlikely((db->pc_next & TARGET_PAGE_MASK) != - (db->pc_first & TARGET_PAGE_MASK))) { - get_page_addr_code_hostp(cpu->env_ptr, db->pc_next, - &ptb->haddr2); - ptb->vaddr2 = db->pc_next; - } - if (likely(ptb->vaddr2 == -1)) { + if (ptb->haddr1 == NULL) { + pinsn->haddr = NULL; + } else if (is_same_page(db, db->pc_next)) { pinsn->haddr = ptb->haddr1 + pinsn->vaddr - ptb->vaddr; } else { + if (ptb->vaddr2 == -1) { + ptb->vaddr2 = TARGET_PAGE_ALIGN(db->pc_first); + get_page_addr_code_hostp(cpu->env_ptr, ptb->vaddr2, &ptb->haddr2); + } pinsn->haddr = ptb->haddr2 + pinsn->vaddr - ptb->vaddr2; } } diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int max_insns, ops->tb_start(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ - plugin_enabled = plugin_gen_tb_start(cpu, tb, cflags & CF_MEMI_ONLY); + plugin_enabled = plugin_gen_tb_start(cpu, db, cflags & CF_MEMI_ONLY); while (true) { db->num_insns++; -- 2.34.1 Let tb->page_addr[0] contain the address of the first byte of the translated block, rather than the address of the page containing the start of the translated block. We need to recover this value anyway at various points, and it is easier to discard a page offset when it is not needed, which happens naturally via the existing find_page shift. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cpu-exec.c | 16 ++++++++-------- accel/tcg/cputlb.c | 3 ++- accel/tcg/translate-all.c | 9 +++++---- 3 files changed, 15 insertions(+), 13 deletions(-) diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ struct tb_desc { target_ulong pc; target_ulong cs_base; CPUArchState *env; - tb_page_addr_t phys_page1; + tb_page_addr_t page_addr0; uint32_t flags; uint32_t cflags; uint32_t trace_vcpu_dstate; @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) const struct tb_desc *desc = d; if (tb->pc == desc->pc && - tb->page_addr[0] == desc->phys_page1 && + tb->page_addr[0] == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && tb->trace_vcpu_dstate == desc->trace_vcpu_dstate && @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) if (tb->page_addr[1] == -1) { return true; } else { - tb_page_addr_t phys_page2; - target_ulong virt_page2; + tb_page_addr_t phys_page1; + target_ulong virt_page1; /* * We know that the first page matched, and an otherwise valid TB @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) * is different for the new TB. Therefore any exception raised * here by the faulting lookup is not premature. */ - virt_page2 = TARGET_PAGE_ALIGN(desc->pc); - phys_page2 = get_page_addr_code(desc->env, virt_page2); - if (tb->page_addr[1] == phys_page2) { + virt_page1 = TARGET_PAGE_ALIGN(desc->pc); + phys_page1 = get_page_addr_code(desc->env, virt_page1); + if (tb->page_addr[1] == phys_page1) { return true; } } @@ -XXX,XX +XXX,XX @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, if (phys_pc == -1) { return NULL; } - desc.phys_page1 = phys_pc & TARGET_PAGE_MASK; + desc.page_addr0 = phys_pc; h = tb_hash_func(phys_pc, pc, flags, cflags, *cpu->trace_dstate); return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp); } diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, can be detected */ void tlb_protect_code(ram_addr_t ram_addr) { - cpu_physical_memory_test_and_clear_dirty(ram_addr, TARGET_PAGE_SIZE, + cpu_physical_memory_test_and_clear_dirty(ram_addr & TARGET_PAGE_MASK, + TARGET_PAGE_SIZE, DIRTY_MEMORY_CODE); } diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) qemu_spin_unlock(&tb->jmp_lock); /* remove the TB from the hash list */ - phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK); + phys_pc = tb->page_addr[0]; h = tb_hash_func(phys_pc, tb->pc, tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, * we can only insert TBs that are fully initialized. */ page_lock_pair(&p, phys_pc, &p2, phys_page2, true); - tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK); + tb_page_add(p, tb, 0, phys_pc); if (p2) { tb_page_add(p2, tb, 1, phys_page2); } else { @@ -XXX,XX +XXX,XX @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages, if (n == 0) { /* NOTE: tb_end may be after the end of the page, but it is not a problem */ - tb_start = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK); + tb_start = tb->page_addr[0]; tb_end = tb_start + tb->size; } else { tb_start = tb->page_addr[1]; - tb_end = tb_start + ((tb->pc + tb->size) & ~TARGET_PAGE_MASK); + tb_end = tb_start + ((tb->page_addr[0] + tb->size) + & ~TARGET_PAGE_MASK); } if (!(tb_end <= start || tb_start >= end)) { #ifdef TARGET_HAS_PRECISE_SMC -- 2.34.1 This function has two users, who use it incompatibly. In tlb_flush_page_by_mmuidx_async_0, when flushing a single page, we need to flush exactly two pages. In tlb_flush_range_by_mmuidx_async_0, when flushing a range of pages, we need to flush N+1 pages. This avoids double-flushing of jmp cache pages in a range. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cputlb.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr) } } -static void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr) -{ - /* Discard jump cache entries for any tb which might potentially - overlap the flushed page. */ - tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE); - tb_jmp_cache_clear_page(cpu, addr); -} - /** * tlb_mmu_resize_locked() - perform TLB resize bookkeeping; resize if necessary * @desc: The CPUTLBDesc portion of the TLB @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_by_mmuidx_async_0(CPUState *cpu, } qemu_spin_unlock(&env_tlb(env)->c.lock); - tb_flush_jmp_cache(cpu, addr); + /* + * Discard jump cache entries for any tb which might potentially + * overlap the flushed page, which includes the previous. + */ + tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE); + tb_jmp_cache_clear_page(cpu, addr); } /** @@ -XXX,XX +XXX,XX @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, return; } - for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) { - tb_flush_jmp_cache(cpu, d.addr + i); + /* + * Discard jump cache entries for any tb which might potentially + * overlap the flushed pages, which includes the previous. + */ + d.addr -= TARGET_PAGE_SIZE; + for (target_ulong i = 0, n = d.len / TARGET_PAGE_SIZE + 1; i < n; i++) { + tb_jmp_cache_clear_page(cpu, d.addr); + d.addr += TARGET_PAGE_SIZE; } } -- 2.34.1 Wrap the bare TranslationBlock pointer into a structure. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/tb-hash.h | 1 + accel/tcg/tb-jmp-cache.h | 24 ++++++++++++++++++++++++ include/exec/cpu-common.h | 1 + include/hw/core/cpu.h | 15 +-------------- include/qemu/typedefs.h | 1 + accel/stubs/tcg-stub.c | 4 ++++ accel/tcg/cpu-exec.c | 10 +++++++--- accel/tcg/cputlb.c | 9 +++++---- accel/tcg/translate-all.c | 28 +++++++++++++++++++++++++--- hw/core/cpu-common.c | 3 +-- plugins/core.c | 2 +- trace/control-target.c | 2 +- 12 files changed, 72 insertions(+), 28 deletions(-) create mode 100644 accel/tcg/tb-jmp-cache.h diff --git a/accel/tcg/tb-hash.h b/accel/tcg/tb-hash.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tb-hash.h +++ b/accel/tcg/tb-hash.h @@ -XXX,XX +XXX,XX @@ #include "exec/cpu-defs.h" #include "exec/exec-all.h" #include "qemu/xxhash.h" +#include "tb-jmp-cache.h" #ifdef CONFIG_SOFTMMU diff --git a/accel/tcg/tb-jmp-cache.h b/accel/tcg/tb-jmp-cache.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/tcg/tb-jmp-cache.h @@ -XXX,XX +XXX,XX @@ +/* + * The per-CPU TranslationBlock jump cache. + * + * Copyright (c) 2003 Fabrice Bellard + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ACCEL_TCG_TB_JMP_CACHE_H +#define ACCEL_TCG_TB_JMP_CACHE_H + +#define TB_JMP_CACHE_BITS 12 +#define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) + +/* + * Accessed in parallel; all accesses to 'tb' must be atomic. + */ +struct CPUJumpCache { + struct { + TranslationBlock *tb; + } array[TB_JMP_CACHE_SIZE]; +}; + +#endif /* ACCEL_TCG_TB_JMP_CACHE_H */ diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -XXX,XX +XXX,XX @@ void cpu_list_unlock(void); unsigned int cpu_list_generation_id_get(void); void tcg_flush_softmmu_tlb(CPUState *cs); +void tcg_flush_jmp_cache(CPUState *cs); void tcg_iommu_init_notifier_list(CPUState *cpu); void tcg_iommu_free_notifier_list(CPUState *cpu); diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct kvm_run; struct hax_vcpu_state; struct hvf_vcpu_state; -#define TB_JMP_CACHE_BITS 12 -#define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) - /* work queue */ /* The union type allows passing of 64 bit target pointers on 32 bit @@ -XXX,XX +XXX,XX @@ struct CPUState { CPUArchState *env_ptr; IcountDecr *icount_decr_ptr; - /* Accessed in parallel; all accesses must be atomic */ - TranslationBlock *tb_jmp_cache[TB_JMP_CACHE_SIZE]; + CPUJumpCache *tb_jmp_cache; struct GDBRegisterState *gdb_regs; int gdb_num_regs; @@ -XXX,XX +XXX,XX @@ extern CPUTailQ cpus; extern __thread CPUState *current_cpu; -static inline void cpu_tb_jmp_cache_clear(CPUState *cpu) -{ - unsigned int i; - - for (i = 0; i < TB_JMP_CACHE_SIZE; i++) { - qatomic_set(&cpu->tb_jmp_cache[i], NULL); - } -} - /** * qemu_tcg_mttcg_enabled: * Check whether we are running MultiThread TCG or not. diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -XXX,XX +XXX,XX @@ typedef struct CoMutex CoMutex; typedef struct ConfidentialGuestSupport ConfidentialGuestSupport; typedef struct CPUAddressSpace CPUAddressSpace; typedef struct CPUArchState CPUArchState; +typedef struct CPUJumpCache CPUJumpCache; typedef struct CPUState CPUState; typedef struct CPUTLBEntryFull CPUTLBEntryFull; typedef struct DeviceListener DeviceListener; diff --git a/accel/stubs/tcg-stub.c b/accel/stubs/tcg-stub.c index XXXXXXX..XXXXXXX 100644 --- a/accel/stubs/tcg-stub.c +++ b/accel/stubs/tcg-stub.c @@ -XXX,XX +XXX,XX @@ void tlb_set_dirty(CPUState *cpu, target_ulong vaddr) { } +void tcg_flush_jmp_cache(CPUState *cpu) +{ +} + int probe_access_flags(CPUArchState *env, target_ulong addr, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t retaddr) diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/replay.h" #include "sysemu/tcg.h" #include "exec/helper-proto.h" +#include "tb-jmp-cache.h" #include "tb-hash.h" #include "tb-context.h" #include "internal.h" @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, tcg_debug_assert(!(cflags & CF_INVALID)); hash = tb_jmp_cache_hash_func(pc); - tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]); + tb = qatomic_rcu_read(&cpu->tb_jmp_cache->array[hash].tb); if (likely(tb && tb->pc == pc && @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, if (tb == NULL) { return NULL; } - qatomic_set(&cpu->tb_jmp_cache[hash], tb); + qatomic_set(&cpu->tb_jmp_cache->array[hash].tb, tb); return tb; } @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) tb = tb_lookup(cpu, pc, cs_base, flags, cflags); if (tb == NULL) { + uint32_t h; + mmap_lock(); tb = tb_gen_code(cpu, pc, cs_base, flags, cflags); mmap_unlock(); @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) * We add the TB in the virtual pc hash table * for the fast lookup */ - qatomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb); + h = tb_jmp_cache_hash_func(pc); + qatomic_set(&cpu->tb_jmp_cache->array[h].tb, tb); } #ifndef CONFIG_USER_ONLY diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns, static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr) { - unsigned int i, i0 = tb_jmp_cache_hash_page(page_addr); + int i, i0 = tb_jmp_cache_hash_page(page_addr); + CPUJumpCache *jc = cpu->tb_jmp_cache; for (i = 0; i < TB_JMP_PAGE_SIZE; i++) { - qatomic_set(&cpu->tb_jmp_cache[i0 + i], NULL); + qatomic_set(&jc->array[i0 + i].tb, NULL); } } @@ -XXX,XX +XXX,XX @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data) qemu_spin_unlock(&env_tlb(env)->c.lock); - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); if (to_clean == ALL_MMUIDX_BITS) { qatomic_set(&env_tlb(env)->c.full_flush_count, @@ -XXX,XX +XXX,XX @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, * longer to clear each entry individually than it will to clear it all. */ if (d.len >= (TARGET_PAGE_SIZE * TB_JMP_CACHE_SIZE)) { - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); return; } diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/tcg.h" #include "qapi/error.h" #include "hw/core/tcg-cpu-ops.h" +#include "tb-jmp-cache.h" #include "tb-hash.h" #include "tb-context.h" #include "internal.h" @@ -XXX,XX +XXX,XX @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count) } CPU_FOREACH(cpu) { - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); } qht_reset_size(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE); @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ h = tb_jmp_cache_hash_func(tb->pc); CPU_FOREACH(cpu) { - if (qatomic_read(&cpu->tb_jmp_cache[h]) == tb) { - qatomic_set(&cpu->tb_jmp_cache[h], NULL); + CPUJumpCache *jc = cpu->tb_jmp_cache; + if (qatomic_read(&jc->array[h].tb) == tb) { + qatomic_set(&jc->array[h].tb, NULL); } } @@ -XXX,XX +XXX,XX @@ int page_unprotect(target_ulong address, uintptr_t pc) } #endif /* CONFIG_USER_ONLY */ +/* + * Called by generic code at e.g. cpu reset after cpu creation, + * therefore we must be prepared to allocate the jump cache. + */ +void tcg_flush_jmp_cache(CPUState *cpu) +{ + CPUJumpCache *jc = cpu->tb_jmp_cache; + + if (likely(jc)) { + for (int i = 0; i < TB_JMP_CACHE_SIZE; i++) { + qatomic_set(&jc->array[i].tb, NULL); + } + } else { + /* This should happen once during realize, and thus never race. */ + jc = g_new0(CPUJumpCache, 1); + jc = qatomic_xchg(&cpu->tb_jmp_cache, jc); + assert(jc == NULL); + } +} + /* This is a wrapper for common code that can not use CONFIG_SOFTMMU */ void tcg_flush_softmmu_tlb(CPUState *cs) { diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/cpu-common.c +++ b/hw/core/cpu-common.c @@ -XXX,XX +XXX,XX @@ static void cpu_common_reset(DeviceState *dev) cpu->cflags_next_tb = -1; if (tcg_enabled()) { - cpu_tb_jmp_cache_clear(cpu); - + tcg_flush_jmp_cache(cpu); tcg_flush_softmmu_tlb(cpu); } } diff --git a/plugins/core.c b/plugins/core.c index XXXXXXX..XXXXXXX 100644 --- a/plugins/core.c +++ b/plugins/core.c @@ -XXX,XX +XXX,XX @@ struct qemu_plugin_ctx *plugin_id_to_ctx_locked(qemu_plugin_id_t id) static void plugin_cpu_update__async(CPUState *cpu, run_on_cpu_data data) { bitmap_copy(cpu->plugin_mask, &data.host_ulong, QEMU_PLUGIN_EV_MAX); - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); } static void plugin_cpu_update__locked(gpointer k, gpointer v, gpointer udata) diff --git a/trace/control-target.c b/trace/control-target.c index XXXXXXX..XXXXXXX 100644 --- a/trace/control-target.c +++ b/trace/control-target.c @@ -XXX,XX +XXX,XX @@ static void trace_event_synchronize_vcpu_state_dynamic( { bitmap_copy(vcpu->trace_dstate, vcpu->trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS); - cpu_tb_jmp_cache_clear(vcpu); + tcg_flush_jmp_cache(vcpu); } void trace_event_set_vcpu_state_dynamic(CPUState *vcpu, -- 2.34.1 Populate this new method for all targets. Always match the result that would be given by cpu_get_tb_cpu_state, as we will want these values to correspond in the logs. Reviewed-by: Taylor Simpson <tsimpson@quicinc.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> (target/sparc) Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- Cc: Eduardo Habkost <eduardo@habkost.net> (supporter:Machine core) Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> (supporter:Machine core) Cc: "Philippe Mathieu-Daudé" <f4bug@amsat.org> (reviewer:Machine core) Cc: Yanan Wang <wangyanan55@huawei.com> (reviewer:Machine core) Cc: Michael Rolnik <mrolnik@gmail.com> (maintainer:AVR TCG CPUs) Cc: "Edgar E. Iglesias" <edgar.iglesias@gmail.com> (maintainer:CRIS TCG CPUs) Cc: Taylor Simpson <tsimpson@quicinc.com> (supporter:Hexagon TCG CPUs) Cc: Song Gao <gaosong@loongson.cn> (maintainer:LoongArch TCG CPUs) Cc: Xiaojuan Yang <yangxiaojuan@loongson.cn> (maintainer:LoongArch TCG CPUs) Cc: Laurent Vivier <laurent@vivier.eu> (maintainer:M68K TCG CPUs) Cc: Jiaxun Yang <jiaxun.yang@flygoat.com> (reviewer:MIPS TCG CPUs) Cc: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> (reviewer:MIPS TCG CPUs) Cc: Chris Wulff <crwulff@gmail.com> (maintainer:NiosII TCG CPUs) Cc: Marek Vasut <marex@denx.de> (maintainer:NiosII TCG CPUs) Cc: Stafford Horne <shorne@gmail.com> (odd fixer:OpenRISC TCG CPUs) Cc: Yoshinori Sato <ysato@users.sourceforge.jp> (reviewer:RENESAS RX CPUs) Cc: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> (maintainer:SPARC TCG CPUs) Cc: Bastian Koppelmann <kbastian@mail.uni-paderborn.de> (maintainer:TriCore TCG CPUs) Cc: Max Filippov <jcmvbkbc@gmail.com> (maintainer:Xtensa TCG CPUs) Cc: qemu-arm@nongnu.org (open list:ARM TCG CPUs) Cc: qemu-ppc@nongnu.org (open list:PowerPC TCG CPUs) Cc: qemu-riscv@nongnu.org (open list:RISC-V TCG CPUs) Cc: qemu-s390x@nongnu.org (open list:S390 TCG CPUs) --- include/hw/core/cpu.h | 3 +++ target/alpha/cpu.c | 9 +++++++++ target/arm/cpu.c | 13 +++++++++++++ target/avr/cpu.c | 8 ++++++++ target/cris/cpu.c | 8 ++++++++ target/hexagon/cpu.c | 8 ++++++++ target/hppa/cpu.c | 8 ++++++++ target/i386/cpu.c | 9 +++++++++ target/loongarch/cpu.c | 9 +++++++++ target/m68k/cpu.c | 8 ++++++++ target/microblaze/cpu.c | 8 ++++++++ target/mips/cpu.c | 8 ++++++++ target/nios2/cpu.c | 9 +++++++++ target/openrisc/cpu.c | 8 ++++++++ target/ppc/cpu_init.c | 8 ++++++++ target/riscv/cpu.c | 13 +++++++++++++ target/rx/cpu.c | 8 ++++++++ target/s390x/cpu.c | 8 ++++++++ target/sh4/cpu.c | 8 ++++++++ target/sparc/cpu.c | 8 ++++++++ target/tricore/cpu.c | 9 +++++++++ target/xtensa/cpu.c | 8 ++++++++ 22 files changed, 186 insertions(+) diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct SysemuCPUOps; * If the target behaviour here is anything other than "set * the PC register to the value passed in" then the target must * also implement the synchronize_from_tb hook. + * @get_pc: Callback for getting the Program Counter register. + * As above, with the semantics of the target architecture. * @gdb_read_register: Callback for letting GDB read a register. * @gdb_write_register: Callback for letting GDB write a register. * @gdb_adjust_breakpoint: Callback for adjusting the address of a @@ -XXX,XX +XXX,XX @@ struct CPUClass { void (*dump_state)(CPUState *cpu, FILE *, int flags); int64_t (*get_arch_id)(CPUState *cpu); void (*set_pc)(CPUState *cpu, vaddr value); + vaddr (*get_pc)(CPUState *cpu); int (*gdb_read_register)(CPUState *cpu, GByteArray *buf, int reg); int (*gdb_write_register)(CPUState *cpu, uint8_t *buf, int reg); vaddr (*gdb_adjust_breakpoint)(CPUState *cpu, vaddr addr); diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/cpu.c +++ b/target/alpha/cpu.c @@ -XXX,XX +XXX,XX @@ static void alpha_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr alpha_cpu_get_pc(CPUState *cs) +{ + AlphaCPU *cpu = ALPHA_CPU(cs); + + return cpu->env.pc; +} + + static bool alpha_cpu_has_work(CPUState *cs) { /* Here we are checking to see if the CPU should wake up from HALT. @@ -XXX,XX +XXX,XX @@ static void alpha_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = alpha_cpu_has_work; cc->dump_state = alpha_cpu_dump_state; cc->set_pc = alpha_cpu_set_pc; + cc->get_pc = alpha_cpu_get_pc; cc->gdb_read_register = alpha_cpu_gdb_read_register; cc->gdb_write_register = alpha_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_pc(CPUState *cs, vaddr value) } } +static vaddr arm_cpu_get_pc(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + + if (is_a64(env)) { + return env->pc; + } else { + return env->regs[15]; + } +} + #ifdef CONFIG_TCG void arm_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = arm_cpu_has_work; cc->dump_state = arm_cpu_dump_state; cc->set_pc = arm_cpu_set_pc; + cc->get_pc = arm_cpu_get_pc; cc->gdb_read_register = arm_cpu_gdb_read_register; cc->gdb_write_register = arm_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/avr/cpu.c b/target/avr/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -XXX,XX +XXX,XX @@ static void avr_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc_w = value / 2; /* internally PC points to words */ } +static vaddr avr_cpu_get_pc(CPUState *cs) +{ + AVRCPU *cpu = AVR_CPU(cs); + + return cpu->env.pc_w * 2; +} + static bool avr_cpu_has_work(CPUState *cs) { AVRCPU *cpu = AVR_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void avr_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = avr_cpu_has_work; cc->dump_state = avr_cpu_dump_state; cc->set_pc = avr_cpu_set_pc; + cc->get_pc = avr_cpu_get_pc; dc->vmsd = &vms_avr_cpu; cc->sysemu_ops = &avr_sysemu_ops; cc->disas_set_info = avr_cpu_disas_set_info; diff --git a/target/cris/cpu.c b/target/cris/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/cris/cpu.c +++ b/target/cris/cpu.c @@ -XXX,XX +XXX,XX @@ static void cris_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr cris_cpu_get_pc(CPUState *cs) +{ + CRISCPU *cpu = CRIS_CPU(cs); + + return cpu->env.pc; +} + static bool cris_cpu_has_work(CPUState *cs) { return cs->interrupt_request & (CPU_INTERRUPT_HARD | CPU_INTERRUPT_NMI); @@ -XXX,XX +XXX,XX @@ static void cris_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = cris_cpu_has_work; cc->dump_state = cris_cpu_dump_state; cc->set_pc = cris_cpu_set_pc; + cc->get_pc = cris_cpu_get_pc; cc->gdb_read_register = cris_cpu_gdb_read_register; cc->gdb_write_register = cris_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_set_pc(CPUState *cs, vaddr value) env->gpr[HEX_REG_PC] = value; } +static vaddr hexagon_cpu_get_pc(CPUState *cs) +{ + HexagonCPU *cpu = HEXAGON_CPU(cs); + CPUHexagonState *env = &cpu->env; + return env->gpr[HEX_REG_PC]; +} + static void hexagon_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_class_init(ObjectClass *c, void *data) cc->has_work = hexagon_cpu_has_work; cc->dump_state = hexagon_dump_state; cc->set_pc = hexagon_cpu_set_pc; + cc->get_pc = hexagon_cpu_get_pc; cc->gdb_read_register = hexagon_gdb_read_register; cc->gdb_write_register = hexagon_gdb_write_register; cc->gdb_num_core_regs = TOTAL_PER_THREAD_REGS + NUM_VREGS + NUM_QREGS; diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -XXX,XX +XXX,XX @@ static void hppa_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.iaoq_b = value + 4; } +static vaddr hppa_cpu_get_pc(CPUState *cs) +{ + HPPACPU *cpu = HPPA_CPU(cs); + + return cpu->env.iaoq_f; +} + static void hppa_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void hppa_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = hppa_cpu_has_work; cc->dump_state = hppa_cpu_dump_state; cc->set_pc = hppa_cpu_set_pc; + cc->get_pc = hppa_cpu_get_pc; cc->gdb_read_register = hppa_cpu_gdb_read_register; cc->gdb_write_register = hppa_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/i386/cpu.c b/target/i386/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -XXX,XX +XXX,XX @@ static void x86_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.eip = value; } +static vaddr x86_cpu_get_pc(CPUState *cs) +{ + X86CPU *cpu = X86_CPU(cs); + + /* Match cpu_get_tb_cpu_state. */ + return cpu->env.eip + cpu->env.segs[R_CS].base; +} + int x86_cpu_pending_interrupt(CPUState *cs, int interrupt_request) { X86CPU *cpu = X86_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data) cc->has_work = x86_cpu_has_work; cc->dump_state = x86_cpu_dump_state; cc->set_pc = x86_cpu_set_pc; + cc->get_pc = x86_cpu_get_pc; cc->gdb_read_register = x86_cpu_gdb_read_register; cc->gdb_write_register = x86_cpu_gdb_write_register; cc->get_arch_id = x86_cpu_get_arch_id; diff --git a/target/loongarch/cpu.c b/target/loongarch/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/cpu.c +++ b/target/loongarch/cpu.c @@ -XXX,XX +XXX,XX @@ static void loongarch_cpu_set_pc(CPUState *cs, vaddr value) env->pc = value; } +static vaddr loongarch_cpu_get_pc(CPUState *cs) +{ + LoongArchCPU *cpu = LOONGARCH_CPU(cs); + CPULoongArchState *env = &cpu->env; + + return env->pc; +} + #ifndef CONFIG_USER_ONLY #include "hw/loongarch/virt.h" @@ -XXX,XX +XXX,XX @@ static void loongarch_cpu_class_init(ObjectClass *c, void *data) cc->has_work = loongarch_cpu_has_work; cc->dump_state = loongarch_cpu_dump_state; cc->set_pc = loongarch_cpu_set_pc; + cc->get_pc = loongarch_cpu_get_pc; #ifndef CONFIG_USER_ONLY dc->vmsd = &vmstate_loongarch_cpu; cc->sysemu_ops = &loongarch_sysemu_ops; diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr m68k_cpu_get_pc(CPUState *cs) +{ + M68kCPU *cpu = M68K_CPU(cs); + + return cpu->env.pc; +} + static bool m68k_cpu_has_work(CPUState *cs) { return cs->interrupt_request & CPU_INTERRUPT_HARD; @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_class_init(ObjectClass *c, void *data) cc->has_work = m68k_cpu_has_work; cc->dump_state = m68k_cpu_dump_state; cc->set_pc = m68k_cpu_set_pc; + cc->get_pc = m68k_cpu_get_pc; cc->gdb_read_register = m68k_cpu_gdb_read_register; cc->gdb_write_register = m68k_cpu_gdb_write_register; #if defined(CONFIG_SOFTMMU) diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -XXX,XX +XXX,XX @@ static void mb_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.iflags = 0; } +static vaddr mb_cpu_get_pc(CPUState *cs) +{ + MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs); + + return cpu->env.pc; +} + static void mb_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void mb_cpu_class_init(ObjectClass *oc, void *data) cc->dump_state = mb_cpu_dump_state; cc->set_pc = mb_cpu_set_pc; + cc->get_pc = mb_cpu_get_pc; cc->gdb_read_register = mb_cpu_gdb_read_register; cc->gdb_write_register = mb_cpu_gdb_write_register; diff --git a/target/mips/cpu.c b/target/mips/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/cpu.c +++ b/target/mips/cpu.c @@ -XXX,XX +XXX,XX @@ static void mips_cpu_set_pc(CPUState *cs, vaddr value) mips_env_set_pc(&cpu->env, value); } +static vaddr mips_cpu_get_pc(CPUState *cs) +{ + MIPSCPU *cpu = MIPS_CPU(cs); + + return cpu->env.active_tc.PC; +} + static bool mips_cpu_has_work(CPUState *cs) { MIPSCPU *cpu = MIPS_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void mips_cpu_class_init(ObjectClass *c, void *data) cc->has_work = mips_cpu_has_work; cc->dump_state = mips_cpu_dump_state; cc->set_pc = mips_cpu_set_pc; + cc->get_pc = mips_cpu_get_pc; cc->gdb_read_register = mips_cpu_gdb_read_register; cc->gdb_write_register = mips_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_set_pc(CPUState *cs, vaddr value) env->pc = value; } +static vaddr nios2_cpu_get_pc(CPUState *cs) +{ + Nios2CPU *cpu = NIOS2_CPU(cs); + CPUNios2State *env = &cpu->env; + + return env->pc; +} + static bool nios2_cpu_has_work(CPUState *cs) { return cs->interrupt_request & CPU_INTERRUPT_HARD; @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = nios2_cpu_has_work; cc->dump_state = nios2_cpu_dump_state; cc->set_pc = nios2_cpu_set_pc; + cc->get_pc = nios2_cpu_get_pc; cc->disas_set_info = nios2_cpu_disas_set_info; #ifndef CONFIG_USER_ONLY cc->sysemu_ops = &nios2_sysemu_ops; diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.dflag = 0; } +static vaddr openrisc_cpu_get_pc(CPUState *cs) +{ + OpenRISCCPU *cpu = OPENRISC_CPU(cs); + + return cpu->env.pc; +} + static void openrisc_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = openrisc_cpu_has_work; cc->dump_state = openrisc_cpu_dump_state; cc->set_pc = openrisc_cpu_set_pc; + cc->get_pc = openrisc_cpu_get_pc; cc->gdb_read_register = openrisc_cpu_gdb_read_register; cc->gdb_write_register = openrisc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.nip = value; } +static vaddr ppc_cpu_get_pc(CPUState *cs) +{ + PowerPCCPU *cpu = POWERPC_CPU(cs); + + return cpu->env.nip; +} + static bool ppc_cpu_has_work(CPUState *cs) { PowerPCCPU *cpu = POWERPC_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = ppc_cpu_has_work; cc->dump_state = ppc_cpu_dump_state; cc->set_pc = ppc_cpu_set_pc; + cc->get_pc = ppc_cpu_get_pc; cc->gdb_read_register = ppc_cpu_gdb_read_register; cc->gdb_write_register = ppc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_set_pc(CPUState *cs, vaddr value) } } +static vaddr riscv_cpu_get_pc(CPUState *cs) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + + /* Match cpu_get_tb_cpu_state. */ + if (env->xl == MXL_RV32) { + return env->pc & UINT32_MAX; + } + return env->pc; +} + static void riscv_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_class_init(ObjectClass *c, void *data) cc->has_work = riscv_cpu_has_work; cc->dump_state = riscv_cpu_dump_state; cc->set_pc = riscv_cpu_set_pc; + cc->get_pc = riscv_cpu_get_pc; cc->gdb_read_register = riscv_cpu_gdb_read_register; cc->gdb_write_register = riscv_cpu_gdb_write_register; cc->gdb_num_core_regs = 33; diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ static void rx_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr rx_cpu_get_pc(CPUState *cs) +{ + RXCPU *cpu = RX_CPU(cs); + + return cpu->env.pc; +} + static void rx_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void rx_cpu_class_init(ObjectClass *klass, void *data) cc->has_work = rx_cpu_has_work; cc->dump_state = rx_cpu_dump_state; cc->set_pc = rx_cpu_set_pc; + cc->get_pc = rx_cpu_get_pc; #ifndef CONFIG_USER_ONLY cc->sysemu_ops = &rx_sysemu_ops; diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.psw.addr = value; } +static vaddr s390_cpu_get_pc(CPUState *cs) +{ + S390CPU *cpu = S390_CPU(cs); + + return cpu->env.psw.addr; +} + static bool s390_cpu_has_work(CPUState *cs) { S390CPU *cpu = S390_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void s390_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = s390_cpu_has_work; cc->dump_state = s390_cpu_dump_state; cc->set_pc = s390_cpu_set_pc; + cc->get_pc = s390_cpu_get_pc; cc->gdb_read_register = s390_cpu_gdb_read_register; cc->gdb_write_register = s390_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static void superh_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr superh_cpu_get_pc(CPUState *cs) +{ + SuperHCPU *cpu = SUPERH_CPU(cs); + + return cpu->env.pc; +} + static void superh_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void superh_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = superh_cpu_has_work; cc->dump_state = superh_cpu_dump_state; cc->set_pc = superh_cpu_set_pc; + cc->get_pc = superh_cpu_get_pc; cc->gdb_read_register = superh_cpu_gdb_read_register; cc->gdb_write_register = superh_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.npc = value + 4; } +static vaddr sparc_cpu_get_pc(CPUState *cs) +{ + SPARCCPU *cpu = SPARC_CPU(cs); + + return cpu->env.pc; +} + static void sparc_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_class_init(ObjectClass *oc, void *data) cc->memory_rw_debug = sparc_cpu_memory_rw_debug; #endif cc->set_pc = sparc_cpu_set_pc; + cc->get_pc = sparc_cpu_get_pc; cc->gdb_read_register = sparc_cpu_gdb_read_register; cc->gdb_write_register = sparc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/cpu.c +++ b/target/tricore/cpu.c @@ -XXX,XX +XXX,XX @@ static void tricore_cpu_set_pc(CPUState *cs, vaddr value) env->PC = value & ~(target_ulong)1; } +static vaddr tricore_cpu_get_pc(CPUState *cs) +{ + TriCoreCPU *cpu = TRICORE_CPU(cs); + CPUTriCoreState *env = &cpu->env; + + return env->PC; +} + static void tricore_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void tricore_cpu_class_init(ObjectClass *c, void *data) cc->dump_state = tricore_cpu_dump_state; cc->set_pc = tricore_cpu_set_pc; + cc->get_pc = tricore_cpu_get_pc; cc->sysemu_ops = &tricore_sysemu_ops; cc->tcg_ops = &tricore_tcg_ops; } diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr xtensa_cpu_get_pc(CPUState *cs) +{ + XtensaCPU *cpu = XTENSA_CPU(cs); + + return cpu->env.pc; +} + static bool xtensa_cpu_has_work(CPUState *cs) { #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = xtensa_cpu_has_work; cc->dump_state = xtensa_cpu_dump_state; cc->set_pc = xtensa_cpu_set_pc; + cc->get_pc = xtensa_cpu_get_pc; cc->gdb_read_register = xtensa_cpu_gdb_read_register; cc->gdb_write_register = xtensa_cpu_gdb_write_register; cc->gdb_stop_before_watchpoint = true; -- 2.34.1 The availability of tb->pc will shortly be conditional. Introduce accessor functions to minimize ifdefs. Pass around a known pc to places like tcg_gen_code, where the caller must already have the value. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/internal.h | 6 ++++ include/exec/exec-all.h | 6 ++++ include/tcg/tcg.h | 2 +- accel/tcg/cpu-exec.c | 46 ++++++++++++++----------- accel/tcg/translate-all.c | 37 +++++++++++--------- target/arm/cpu.c | 4 +-- target/avr/cpu.c | 2 +- target/hexagon/cpu.c | 2 +- target/hppa/cpu.c | 4 +-- target/i386/tcg/tcg-cpu.c | 2 +- target/loongarch/cpu.c | 2 +- target/microblaze/cpu.c | 2 +- target/mips/tcg/exception.c | 2 +- target/mips/tcg/sysemu/special_helper.c | 2 +- target/openrisc/cpu.c | 2 +- target/riscv/cpu.c | 4 +-- target/rx/cpu.c | 2 +- target/sh4/cpu.c | 4 +-- target/sparc/cpu.c | 2 +- target/tricore/cpu.c | 2 +- tcg/tcg.c | 8 ++--- 21 files changed, 82 insertions(+), 61 deletions(-) diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -XXX,XX +XXX,XX @@ G_NORETURN void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr); void page_init(void); void tb_htable_init(void); +/* Return the current PC from CPU, which may be cached in TB. */ +static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb) +{ + return tb_pc(tb); +} + #endif /* ACCEL_TCG_INTERNAL_H */ diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ struct TranslationBlock { uintptr_t jmp_dest[2]; }; +/* Hide the read to avoid ifdefs for TARGET_TB_PCREL. */ +static inline target_ulong tb_pc(const TranslationBlock *tb) +{ + return tb->pc; +} + /* Hide the qatomic_read to make code a little easier on the eyes */ static inline uint32_t tb_cflags(const TranslationBlock *tb) { diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ void tcg_register_thread(void); void tcg_prologue_init(TCGContext *s); void tcg_func_start(TCGContext *s); -int tcg_gen_code(TCGContext *s, TranslationBlock *tb); +int tcg_gen_code(TCGContext *s, TranslationBlock *tb, target_ulong pc_start); void tcg_set_frame(TCGContext *s, TCGReg reg, intptr_t start, intptr_t size); diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) const TranslationBlock *tb = p; const struct tb_desc *desc = d; - if (tb->pc == desc->pc && + if (tb_pc(tb) == desc->pc && tb->page_addr[0] == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, return tb; } -static inline void log_cpu_exec(target_ulong pc, CPUState *cpu, - const TranslationBlock *tb) +static void log_cpu_exec(target_ulong pc, CPUState *cpu, + const TranslationBlock *tb) { - if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) - && qemu_log_in_addr_range(pc)) { - + if (qemu_log_in_addr_range(pc)) { qemu_log_mask(CPU_LOG_EXEC, "Trace %d: %p [" TARGET_FMT_lx "/" TARGET_FMT_lx "/%08x/%08x] %s\n", @@ -XXX,XX +XXX,XX @@ const void *HELPER(lookup_tb_ptr)(CPUArchState *env) return tcg_code_gen_epilogue; } - log_cpu_exec(pc, cpu, tb); + if (qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) { + log_cpu_exec(pc, cpu, tb); + } return tb->tc.ptr; } @@ -XXX,XX +XXX,XX @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) TranslationBlock *last_tb; const void *tb_ptr = itb->tc.ptr; - log_cpu_exec(itb->pc, cpu, itb); + if (qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) { + log_cpu_exec(log_pc(cpu, itb), cpu, itb); + } qemu_thread_jit_execute(); ret = tcg_qemu_tb_exec(env, tb_ptr); @@ -XXX,XX +XXX,XX @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) * of the start of the TB. */ CPUClass *cc = CPU_GET_CLASS(cpu); - qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc, - "Stopped execution of TB chain before %p [" - TARGET_FMT_lx "] %s\n", - last_tb->tc.ptr, last_tb->pc, - lookup_symbol(last_tb->pc)); + if (cc->tcg_ops->synchronize_from_tb) { cc->tcg_ops->synchronize_from_tb(cpu, last_tb); } else { assert(cc->set_pc); - cc->set_pc(cpu, last_tb->pc); + cc->set_pc(cpu, tb_pc(last_tb)); + } + if (qemu_loglevel_mask(CPU_LOG_EXEC)) { + target_ulong pc = log_pc(cpu, last_tb); + if (qemu_log_in_addr_range(pc)) { + qemu_log("Stopped execution of TB chain before %p [" + TARGET_FMT_lx "] %s\n", + last_tb->tc.ptr, pc, lookup_symbol(pc)); + } } } @@ -XXX,XX +XXX,XX @@ static inline void tb_add_jump(TranslationBlock *tb, int n, qemu_spin_unlock(&tb_next->jmp_lock); - qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc, - "Linking TBs %p [" TARGET_FMT_lx - "] index %d -> %p [" TARGET_FMT_lx "]\n", - tb->tc.ptr, tb->pc, n, - tb_next->tc.ptr, tb_next->pc); + qemu_log_mask(CPU_LOG_EXEC, "Linking TBs %p index %d -> %p\n", + tb->tc.ptr, n, tb_next->tc.ptr); return; out_unlock_next: @@ -XXX,XX +XXX,XX @@ static inline bool cpu_handle_interrupt(CPUState *cpu, } static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb, + target_ulong pc, TranslationBlock **last_tb, int *tb_exit) { int32_t insns_left; - trace_exec_tb(tb, tb->pc); + trace_exec_tb(tb, pc); tb = cpu_tb_exec(cpu, tb, tb_exit); if (*tb_exit != TB_EXIT_REQUESTED) { *last_tb = tb; @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) tb_add_jump(last_tb, tb_exit, tb); } - cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit); + cpu_loop_exec_tb(cpu, tb, pc, &last_tb, &tb_exit); /* Try to align the host and virtual clocks if the guest is in advance */ diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static int encode_search(TranslationBlock *tb, uint8_t *block) for (j = 0; j < TARGET_INSN_START_WORDS; ++j) { if (i == 0) { - prev = (j == 0 ? tb->pc : 0); + prev = (j == 0 ? tb_pc(tb) : 0); } else { prev = tcg_ctx->gen_insn_data[i - 1][j]; } @@ -XXX,XX +XXX,XX @@ static int encode_search(TranslationBlock *tb, uint8_t *block) static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, uintptr_t searched_pc, bool reset_icount) { - target_ulong data[TARGET_INSN_START_WORDS] = { tb->pc }; + target_ulong data[TARGET_INSN_START_WORDS] = { tb_pc(tb) }; uintptr_t host_pc = (uintptr_t)tb->tc.ptr; CPUArchState *env = cpu->env_ptr; const uint8_t *p = tb->tc.ptr + tb->tc.size; @@ -XXX,XX +XXX,XX @@ static bool tb_cmp(const void *ap, const void *bp) const TranslationBlock *a = ap; const TranslationBlock *b = bp; - return a->pc == b->pc && + return tb_pc(a) == tb_pc(b) && a->cs_base == b->cs_base && a->flags == b->flags && (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && @@ -XXX,XX +XXX,XX @@ static void do_tb_invalidate_check(void *p, uint32_t hash, void *userp) TranslationBlock *tb = p; target_ulong addr = *(target_ulong *)userp; - if (!(addr + TARGET_PAGE_SIZE <= tb->pc || addr >= tb->pc + tb->size)) { + if (!(addr + TARGET_PAGE_SIZE <= tb_pc(tb) || + addr >= tb_pc(tb) + tb->size)) { printf("ERROR invalidate: address=" TARGET_FMT_lx - " PC=%08lx size=%04x\n", addr, (long)tb->pc, tb->size); + " PC=%08lx size=%04x\n", addr, (long)tb_pc(tb), tb->size); } } @@ -XXX,XX +XXX,XX @@ static void do_tb_page_check(void *p, uint32_t hash, void *userp) TranslationBlock *tb = p; int flags1, flags2; - flags1 = page_get_flags(tb->pc); - flags2 = page_get_flags(tb->pc + tb->size - 1); + flags1 = page_get_flags(tb_pc(tb)); + flags2 = page_get_flags(tb_pc(tb) + tb->size - 1); if ((flags1 & PAGE_WRITE) || (flags2 & PAGE_WRITE)) { printf("ERROR page flags: PC=%08lx size=%04x f1=%x f2=%x\n", - (long)tb->pc, tb->size, flags1, flags2); + (long)tb_pc(tb), tb->size, flags1, flags2); } } @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ phys_pc = tb->page_addr[0]; - h = tb_hash_func(phys_pc, tb->pc, tb->flags, orig_cflags, + h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { return; @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, } /* add in the hash table */ - h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags, + h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, tb->cflags, tb->trace_vcpu_dstate); qht_insert(&tb_ctx.htable, tb, h, &existing_tb); @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, tcg_ctx->cpu = NULL; max_insns = tb->icount; - trace_translate_block(tb, tb->pc, tb->tc.ptr); + trace_translate_block(tb, pc, tb->tc.ptr); /* generate machine code */ tb->jmp_reset_offset[0] = TB_JMP_RESET_OFFSET_INVALID; @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, ti = profile_getclock(); #endif - gen_code_size = tcg_gen_code(tcg_ctx, tb); + gen_code_size = tcg_gen_code(tcg_ctx, tb, pc); if (unlikely(gen_code_size < 0)) { error_return: switch (gen_code_size) { @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, #ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) && - qemu_log_in_addr_range(tb->pc)) { + qemu_log_in_addr_range(pc)) { FILE *logfile = qemu_log_trylock(); if (logfile) { int code_size, data_size; @@ -XXX,XX +XXX,XX @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr) */ cpu->cflags_next_tb = curr_cflags(cpu) | CF_MEMI_ONLY | CF_LAST_IO | n; - qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc, - "cpu_io_recompile: rewound execution of TB to " - TARGET_FMT_lx "\n", tb->pc); + if (qemu_loglevel_mask(CPU_LOG_EXEC)) { + target_ulong pc = log_pc(cpu, tb); + if (qemu_log_in_addr_range(pc)) { + qemu_log("cpu_io_recompile: rewound execution of TB to " + TARGET_FMT_lx "\n", pc); + } + } cpu_loop_exit_noexc(cpu); } diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_synchronize_from_tb(CPUState *cs, * never possible for an AArch64 TB to chain to an AArch32 TB. */ if (is_a64(env)) { - env->pc = tb->pc; + env->pc = tb_pc(tb); } else { - env->regs[15] = tb->pc; + env->regs[15] = tb_pc(tb); } } #endif /* CONFIG_TCG */ diff --git a/target/avr/cpu.c b/target/avr/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -XXX,XX +XXX,XX @@ static void avr_cpu_synchronize_from_tb(CPUState *cs, AVRCPU *cpu = AVR_CPU(cs); CPUAVRState *env = &cpu->env; - env->pc_w = tb->pc / 2; /* internally PC points to words */ + env->pc_w = tb_pc(tb) / 2; /* internally PC points to words */ } static void avr_cpu_reset(DeviceState *ds) diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_synchronize_from_tb(CPUState *cs, { HexagonCPU *cpu = HEXAGON_CPU(cs); CPUHexagonState *env = &cpu->env; - env->gpr[HEX_REG_PC] = tb->pc; + env->gpr[HEX_REG_PC] = tb_pc(tb); } static bool hexagon_cpu_has_work(CPUState *cs) diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -XXX,XX +XXX,XX @@ static void hppa_cpu_synchronize_from_tb(CPUState *cs, HPPACPU *cpu = HPPA_CPU(cs); #ifdef CONFIG_USER_ONLY - cpu->env.iaoq_f = tb->pc; + cpu->env.iaoq_f = tb_pc(tb); cpu->env.iaoq_b = tb->cs_base; #else /* Recover the IAOQ values from the GVA + PRIV. */ @@ -XXX,XX +XXX,XX @@ static void hppa_cpu_synchronize_from_tb(CPUState *cs, int32_t diff = cs_base; cpu->env.iasq_f = iasq_f; - cpu->env.iaoq_f = (tb->pc & ~iasq_f) + priv; + cpu->env.iaoq_f = (tb_pc(tb) & ~iasq_f) + priv; if (diff) { cpu->env.iaoq_b = cpu->env.iaoq_f + diff; } diff --git a/target/i386/tcg/tcg-cpu.c b/target/i386/tcg/tcg-cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/tcg-cpu.c +++ b/target/i386/tcg/tcg-cpu.c @@ -XXX,XX +XXX,XX @@ static void x86_cpu_synchronize_from_tb(CPUState *cs, { X86CPU *cpu = X86_CPU(cs); - cpu->env.eip = tb->pc - tb->cs_base; + cpu->env.eip = tb_pc(tb) - tb->cs_base; } #ifndef CONFIG_USER_ONLY diff --git a/target/loongarch/cpu.c b/target/loongarch/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/cpu.c +++ b/target/loongarch/cpu.c @@ -XXX,XX +XXX,XX @@ static void loongarch_cpu_synchronize_from_tb(CPUState *cs, LoongArchCPU *cpu = LOONGARCH_CPU(cs); CPULoongArchState *env = &cpu->env; - env->pc = tb->pc; + env->pc = tb_pc(tb); } #endif /* CONFIG_TCG */ diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -XXX,XX +XXX,XX @@ static void mb_cpu_synchronize_from_tb(CPUState *cs, { MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); cpu->env.iflags = tb->flags & IFLAGS_TB_MASK; } diff --git a/target/mips/tcg/exception.c b/target/mips/tcg/exception.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/exception.c +++ b/target/mips/tcg/exception.c @@ -XXX,XX +XXX,XX @@ void mips_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) MIPSCPU *cpu = MIPS_CPU(cs); CPUMIPSState *env = &cpu->env; - env->active_tc.PC = tb->pc; + env->active_tc.PC = tb_pc(tb); env->hflags &= ~MIPS_HFLAG_BMASK; env->hflags |= tb->flags & MIPS_HFLAG_BMASK; } diff --git a/target/mips/tcg/sysemu/special_helper.c b/target/mips/tcg/sysemu/special_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/sysemu/special_helper.c +++ b/target/mips/tcg/sysemu/special_helper.c @@ -XXX,XX +XXX,XX @@ bool mips_io_recompile_replay_branch(CPUState *cs, const TranslationBlock *tb) CPUMIPSState *env = &cpu->env; if ((env->hflags & MIPS_HFLAG_BMASK) != 0 - && env->active_tc.PC != tb->pc) { + && env->active_tc.PC != tb_pc(tb)) { env->active_tc.PC -= (env->hflags & MIPS_HFLAG_B16 ? 2 : 4); env->hflags &= ~MIPS_HFLAG_BMASK; return true; diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_synchronize_from_tb(CPUState *cs, { OpenRISCCPU *cpu = OPENRISC_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); } diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_synchronize_from_tb(CPUState *cs, RISCVMXL xl = FIELD_EX32(tb->flags, TB_FLAGS, XL); if (xl == MXL_RV32) { - env->pc = (int32_t)tb->pc; + env->pc = (int32_t)tb_pc(tb); } else { - env->pc = tb->pc; + env->pc = tb_pc(tb); } } diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ static void rx_cpu_synchronize_from_tb(CPUState *cs, { RXCPU *cpu = RX_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); } static bool rx_cpu_has_work(CPUState *cs) diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static void superh_cpu_synchronize_from_tb(CPUState *cs, { SuperHCPU *cpu = SUPERH_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); cpu->env.flags = tb->flags & TB_FLAG_ENVFLAGS_MASK; } @@ -XXX,XX +XXX,XX @@ static bool superh_io_recompile_replay_branch(CPUState *cs, CPUSH4State *env = &cpu->env; if ((env->flags & ((DELAY_SLOT | DELAY_SLOT_CONDITIONAL))) != 0 - && env->pc != tb->pc) { + && env->pc != tb_pc(tb)) { env->pc -= 2; env->flags &= ~(DELAY_SLOT | DELAY_SLOT_CONDITIONAL); return true; diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_synchronize_from_tb(CPUState *cs, { SPARCCPU *cpu = SPARC_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); cpu->env.npc = tb->cs_base; } diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/cpu.c +++ b/target/tricore/cpu.c @@ -XXX,XX +XXX,XX @@ static void tricore_cpu_synchronize_from_tb(CPUState *cs, TriCoreCPU *cpu = TRICORE_CPU(cs); CPUTriCoreState *env = &cpu->env; - env->PC = tb->pc; + env->PC = tb_pc(tb); } static void tricore_cpu_reset(DeviceState *dev) diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ int64_t tcg_cpu_exec_time(void) #endif -int tcg_gen_code(TCGContext *s, TranslationBlock *tb) +int tcg_gen_code(TCGContext *s, TranslationBlock *tb, target_ulong pc_start) { #ifdef CONFIG_PROFILER TCGProfile *prof = &s->prof; @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb) #ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP) - && qemu_log_in_addr_range(tb->pc))) { + && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); if (logfile) { fprintf(logfile, "OP:\n"); @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb) if (s->nb_indirects > 0) { #ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_IND) - && qemu_log_in_addr_range(tb->pc))) { + && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); if (logfile) { fprintf(logfile, "OP before indirect lowering:\n"); @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb) #ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_OPT) - && qemu_log_in_addr_range(tb->pc))) { + && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); if (logfile) { fprintf(logfile, "OP after optimization and liveness analysis:\n"); -- 2.34.1 Prepare for targets to be able to produce TBs that can run in more than one virtual context. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/internal.h | 4 +++ accel/tcg/tb-jmp-cache.h | 41 +++++++++++++++++++++++++ include/exec/cpu-defs.h | 3 ++ include/exec/exec-all.h | 32 ++++++++++++++++++-- accel/tcg/cpu-exec.c | 16 ++++++---- accel/tcg/translate-all.c | 64 ++++++++++++++++++++++++++------------- 6 files changed, 131 insertions(+), 29 deletions(-) diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -XXX,XX +XXX,XX @@ void tb_htable_init(void); /* Return the current PC from CPU, which may be cached in TB. */ static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb) { +#if TARGET_TB_PCREL + return cpu->cc->get_pc(cpu); +#else return tb_pc(tb); +#endif } #endif /* ACCEL_TCG_INTERNAL_H */ diff --git a/accel/tcg/tb-jmp-cache.h b/accel/tcg/tb-jmp-cache.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tb-jmp-cache.h +++ b/accel/tcg/tb-jmp-cache.h @@ -XXX,XX +XXX,XX @@ /* * Accessed in parallel; all accesses to 'tb' must be atomic. + * For TARGET_TB_PCREL, accesses to 'pc' must be protected by + * a load_acquire/store_release to 'tb'. */ struct CPUJumpCache { struct { TranslationBlock *tb; +#if TARGET_TB_PCREL + target_ulong pc; +#endif } array[TB_JMP_CACHE_SIZE]; }; +static inline TranslationBlock * +tb_jmp_cache_get_tb(CPUJumpCache *jc, uint32_t hash) +{ +#if TARGET_TB_PCREL + /* Use acquire to ensure current load of pc from jc. */ + return qatomic_load_acquire(&jc->array[hash].tb); +#else + /* Use rcu_read to ensure current load of pc from *tb. */ + return qatomic_rcu_read(&jc->array[hash].tb); +#endif +} + +static inline target_ulong +tb_jmp_cache_get_pc(CPUJumpCache *jc, uint32_t hash, TranslationBlock *tb) +{ +#if TARGET_TB_PCREL + return jc->array[hash].pc; +#else + return tb_pc(tb); +#endif +} + +static inline void +tb_jmp_cache_set(CPUJumpCache *jc, uint32_t hash, + TranslationBlock *tb, target_ulong pc) +{ +#if TARGET_TB_PCREL + jc->array[hash].pc = pc; + /* Use store_release on tb to ensure pc is written first. */ + qatomic_store_release(&jc->array[hash].tb, tb); +#else + /* Use the pc value already stored in tb->pc. */ + qatomic_set(&jc->array[hash].tb, tb); +#endif +} + #endif /* ACCEL_TCG_TB_JMP_CACHE_H */ diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ # error TARGET_PAGE_BITS must be defined in cpu-param.h # endif #endif +#ifndef TARGET_TB_PCREL +# define TARGET_TB_PCREL 0 +#endif #define TARGET_LONG_SIZE (TARGET_LONG_BITS / 8) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ struct tb_tc { }; struct TranslationBlock { - target_ulong pc; /* simulated PC corresponding to this block (EIP + CS base) */ - target_ulong cs_base; /* CS base for this block */ +#if !TARGET_TB_PCREL + /* + * Guest PC corresponding to this block. This must be the true + * virtual address. Therefore e.g. x86 stores EIP + CS_BASE, and + * targets like Arm, MIPS, HP-PA, which reuse low bits for ISA or + * privilege, must store those bits elsewhere. + * + * If TARGET_TB_PCREL, the opcodes for the TranslationBlock are + * written such that the TB is associated only with the physical + * page and may be run in any virtual address context. In this case, + * PC must always be taken from ENV in a target-specific manner. + * Unwind information is taken as offsets from the page, to be + * deposited into the "current" PC. + */ + target_ulong pc; +#endif + + /* + * Target-specific data associated with the TranslationBlock, e.g.: + * x86: the original user, the Code Segment virtual base, + * arm: an extension of tb->flags, + * s390x: instruction data for EXECUTE, + * sparc: the next pc of the instruction queue (for delay slots). + */ + target_ulong cs_base; + uint32_t flags; /* flags defining in which context the code was generated */ uint32_t cflags; /* compile flags */ @@ -XXX,XX +XXX,XX @@ struct TranslationBlock { /* Hide the read to avoid ifdefs for TARGET_TB_PCREL. */ static inline target_ulong tb_pc(const TranslationBlock *tb) { +#if TARGET_TB_PCREL + qemu_build_not_reached(); +#else return tb->pc; +#endif } /* Hide the qatomic_read to make code a little easier on the eyes */ diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) const TranslationBlock *tb = p; const struct tb_desc *desc = d; - if (tb_pc(tb) == desc->pc && + if ((TARGET_TB_PCREL || tb_pc(tb) == desc->pc) && tb->page_addr[0] == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && @@ -XXX,XX +XXX,XX @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, return NULL; } desc.page_addr0 = phys_pc; - h = tb_hash_func(phys_pc, pc, flags, cflags, *cpu->trace_dstate); + h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : pc), + flags, cflags, *cpu->trace_dstate); return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp); } @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, uint32_t flags, uint32_t cflags) { TranslationBlock *tb; + CPUJumpCache *jc; uint32_t hash; /* we should never be trying to look up an INVALID tb */ tcg_debug_assert(!(cflags & CF_INVALID)); hash = tb_jmp_cache_hash_func(pc); - tb = qatomic_rcu_read(&cpu->tb_jmp_cache->array[hash].tb); + jc = cpu->tb_jmp_cache; + tb = tb_jmp_cache_get_tb(jc, hash); if (likely(tb && - tb->pc == pc && + tb_jmp_cache_get_pc(jc, hash, tb) == pc && tb->cs_base == cs_base && tb->flags == flags && tb->trace_vcpu_dstate == *cpu->trace_dstate && @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, if (tb == NULL) { return NULL; } - qatomic_set(&cpu->tb_jmp_cache->array[hash].tb, tb); + tb_jmp_cache_set(jc, hash, tb, pc); return tb; } @@ -XXX,XX +XXX,XX @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) if (cc->tcg_ops->synchronize_from_tb) { cc->tcg_ops->synchronize_from_tb(cpu, last_tb); } else { + assert(!TARGET_TB_PCREL); assert(cc->set_pc); cc->set_pc(cpu, tb_pc(last_tb)); } @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) * for the fast lookup */ h = tb_jmp_cache_hash_func(pc); - qatomic_set(&cpu->tb_jmp_cache->array[h].tb, tb); + tb_jmp_cache_set(cpu->tb_jmp_cache, h, tb, pc); } #ifndef CONFIG_USER_ONLY diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static int encode_search(TranslationBlock *tb, uint8_t *block) for (j = 0; j < TARGET_INSN_START_WORDS; ++j) { if (i == 0) { - prev = (j == 0 ? tb_pc(tb) : 0); + prev = (!TARGET_TB_PCREL && j == 0 ? tb_pc(tb) : 0); } else { prev = tcg_ctx->gen_insn_data[i - 1][j]; } @@ -XXX,XX +XXX,XX @@ static int encode_search(TranslationBlock *tb, uint8_t *block) static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, uintptr_t searched_pc, bool reset_icount) { - target_ulong data[TARGET_INSN_START_WORDS] = { tb_pc(tb) }; + target_ulong data[TARGET_INSN_START_WORDS]; uintptr_t host_pc = (uintptr_t)tb->tc.ptr; CPUArchState *env = cpu->env_ptr; const uint8_t *p = tb->tc.ptr + tb->tc.size; @@ -XXX,XX +XXX,XX @@ static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, return -1; } + memset(data, 0, sizeof(data)); + if (!TARGET_TB_PCREL) { + data[0] = tb_pc(tb); + } + /* Reconstruct the stored insn data while looking for the point at which the end of the insn exceeds the searched_pc. */ for (i = 0; i < num_insns; ++i) { @@ -XXX,XX +XXX,XX @@ static bool tb_cmp(const void *ap, const void *bp) const TranslationBlock *a = ap; const TranslationBlock *b = bp; - return tb_pc(a) == tb_pc(b) && - a->cs_base == b->cs_base && - a->flags == b->flags && - (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && - a->trace_vcpu_dstate == b->trace_vcpu_dstate && - a->page_addr[0] == b->page_addr[0] && - a->page_addr[1] == b->page_addr[1]; + return ((TARGET_TB_PCREL || tb_pc(a) == tb_pc(b)) && + a->cs_base == b->cs_base && + a->flags == b->flags && + (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && + a->trace_vcpu_dstate == b->trace_vcpu_dstate && + a->page_addr[0] == b->page_addr[0] && + a->page_addr[1] == b->page_addr[1]); } void tb_htable_init(void) @@ -XXX,XX +XXX,XX @@ static inline void tb_jmp_unlink(TranslationBlock *dest) qemu_spin_unlock(&dest->jmp_lock); } +static void tb_jmp_cache_inval_tb(TranslationBlock *tb) +{ + CPUState *cpu; + + if (TARGET_TB_PCREL) { + /* A TB may be at any virtual address */ + CPU_FOREACH(cpu) { + tcg_flush_jmp_cache(cpu); + } + } else { + uint32_t h = tb_jmp_cache_hash_func(tb_pc(tb)); + + CPU_FOREACH(cpu) { + CPUJumpCache *jc = cpu->tb_jmp_cache; + + if (qatomic_read(&jc->array[h].tb) == tb) { + qatomic_set(&jc->array[h].tb, NULL); + } + } + } +} + /* * In user-mode, call with mmap_lock held. * In !user-mode, if @rm_from_page_list is set, call with the TB's pages' @@ -XXX,XX +XXX,XX @@ static inline void tb_jmp_unlink(TranslationBlock *dest) */ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) { - CPUState *cpu; PageDesc *p; uint32_t h; tb_page_addr_t phys_pc; @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ phys_pc = tb->page_addr[0]; - h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, orig_cflags, - tb->trace_vcpu_dstate); + h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)), + tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { return; } @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) } /* remove the TB from the hash list */ - h = tb_jmp_cache_hash_func(tb->pc); - CPU_FOREACH(cpu) { - CPUJumpCache *jc = cpu->tb_jmp_cache; - if (qatomic_read(&jc->array[h].tb) == tb) { - qatomic_set(&jc->array[h].tb, NULL); - } - } + tb_jmp_cache_inval_tb(tb); /* suppress this TB from the two jump lists */ tb_remove_from_jmp_list(tb, 0); @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, } /* add in the hash table */ - h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, tb->cflags, - tb->trace_vcpu_dstate); + h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)), + tb->flags, tb->cflags, tb->trace_vcpu_dstate); qht_insert(&tb_ctx.htable, tb, h, &existing_tb); /* remove TB from the page(s) if we couldn't insert it */ @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, gen_code_buf = tcg_ctx->code_gen_ptr; tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf); +#if !TARGET_TB_PCREL tb->pc = pc; +#endif tb->cs_base = cs_base; tb->flags = flags; tb->cflags = cflags; -- 2.34.1 From: Leandro Lupori <leandro.lupori@eldorado.org.br> PowerPC64 processors handle direct branches better than indirect ones, resulting in less stalled cycles and branch misses. However, PPC's tb_target_set_jmp_target() was only using direct branches for 16-bit jumps, while PowerPC64's unconditional branch instructions are able to handle displacements of up to 26 bits. To take advantage of this, now jumps whose displacements fit in between 17 and 26 bits are also converted to direct branches. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Leandro Lupori <leandro.lupori@eldorado.org.br> [rth: Expanded some commentary.] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.c.inc | 119 +++++++++++++++++++++++++++++---------- 1 file changed, 88 insertions(+), 31 deletions(-) diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) tcg_out32(s, insn); } +static inline uint64_t make_pair(tcg_insn_unit i1, tcg_insn_unit i2) +{ + if (HOST_BIG_ENDIAN) { + return (uint64_t)i1 << 32 | i2; + } + return (uint64_t)i2 << 32 | i1; +} + +static inline void ppc64_replace2(uintptr_t rx, uintptr_t rw, + tcg_insn_unit i0, tcg_insn_unit i1) +{ +#if TCG_TARGET_REG_BITS == 64 + qatomic_set((uint64_t *)rw, make_pair(i0, i1)); + flush_idcache_range(rx, rw, 8); +#else + qemu_build_not_reached(); +#endif +} + +static inline void ppc64_replace4(uintptr_t rx, uintptr_t rw, + tcg_insn_unit i0, tcg_insn_unit i1, + tcg_insn_unit i2, tcg_insn_unit i3) +{ + uint64_t p[2]; + + p[!HOST_BIG_ENDIAN] = make_pair(i0, i1); + p[HOST_BIG_ENDIAN] = make_pair(i2, i3); + + /* + * There's no convenient way to get the compiler to allocate a pair + * of registers at an even index, so copy into r6/r7 and clobber. + */ + asm("mr %%r6, %1\n\t" + "mr %%r7, %2\n\t" + "stq %%r6, %0" + : "=Q"(*(__int128 *)rw) : "r"(p[0]), "r"(p[1]) : "r6", "r7"); + flush_idcache_range(rx, rw, 16); +} + void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_rx, uintptr_t jmp_rw, uintptr_t addr) { - if (TCG_TARGET_REG_BITS == 64) { - tcg_insn_unit i1, i2; - intptr_t tb_diff = addr - tc_ptr; - intptr_t br_diff = addr - (jmp_rx + 4); - uint64_t pair; + tcg_insn_unit i0, i1, i2, i3; + intptr_t tb_diff = addr - tc_ptr; + intptr_t br_diff = addr - (jmp_rx + 4); + intptr_t lo, hi; - /* This does not exercise the range of the branch, but we do - still need to be able to load the new value of TCG_REG_TB. - But this does still happen quite often. */ - if (tb_diff == (int16_t)tb_diff) { - i1 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, tb_diff); - i2 = B | (br_diff & 0x3fffffc); - } else { - intptr_t lo = (int16_t)tb_diff; - intptr_t hi = (int32_t)(tb_diff - lo); - assert(tb_diff == hi + lo); - i1 = ADDIS | TAI(TCG_REG_TB, TCG_REG_TB, hi >> 16); - i2 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, lo); - } -#if HOST_BIG_ENDIAN - pair = (uint64_t)i1 << 32 | i2; -#else - pair = (uint64_t)i2 << 32 | i1; -#endif - - /* As per the enclosing if, this is ppc64. Avoid the _Static_assert - within qatomic_set that would fail to build a ppc32 host. */ - qatomic_set__nocheck((uint64_t *)jmp_rw, pair); - flush_idcache_range(jmp_rx, jmp_rw, 8); - } else { + if (TCG_TARGET_REG_BITS == 32) { intptr_t diff = addr - jmp_rx; tcg_debug_assert(in_range_b(diff)); qatomic_set((uint32_t *)jmp_rw, B | (diff & 0x3fffffc)); flush_idcache_range(jmp_rx, jmp_rw, 4); + return; } + + /* + * For 16-bit displacements, we can use a single add + branch. + * This happens quite often. + */ + if (tb_diff == (int16_t)tb_diff) { + i0 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, tb_diff); + i1 = B | (br_diff & 0x3fffffc); + ppc64_replace2(jmp_rx, jmp_rw, i0, i1); + return; + } + + lo = (int16_t)tb_diff; + hi = (int32_t)(tb_diff - lo); + assert(tb_diff == hi + lo); + i0 = ADDIS | TAI(TCG_REG_TB, TCG_REG_TB, hi >> 16); + i1 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, lo); + + /* + * Without stq from 2.07, we can only update two insns, + * and those must be the ones that load the target address. + */ + if (!have_isa_2_07) { + ppc64_replace2(jmp_rx, jmp_rw, i0, i1); + return; + } + + /* + * For 26-bit displacements, we can use a direct branch. + * Otherwise we still need the indirect branch, which we + * must restore after a potential direct branch write. + */ + br_diff -= 4; + if (in_range_b(br_diff)) { + i2 = B | (br_diff & 0x3fffffc); + i3 = NOP; + } else { + i2 = MTSPR | RS(TCG_REG_TB) | CTR; + i3 = BCCTR | BO_ALWAYS; + } + ppc64_replace4(jmp_rx, jmp_rw, i0, i1, i2, i3); } static void tcg_out_call_int(TCGContext *s, int lk, @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, if (s->tb_jmp_insn_offset) { /* Direct jump. */ if (TCG_TARGET_REG_BITS == 64) { - /* Ensure the next insns are 8-byte aligned. */ - if ((uintptr_t)s->code_ptr & 7) { + /* Ensure the next insns are 8 or 16-byte aligned. */ + while ((uintptr_t)s->code_ptr & (have_isa_2_07 ? 15 : 7)) { tcg_out32(s, NOP); } s->tb_jmp_insn_offset[args[0]] = tcg_current_code_size(s); -- 2.34.1 The value previously chosen overlaps GUSA_MASK. Rename all DELAY_SLOT_* and GUSA_* defines to emphasize that they are included in TB_FLAGs. Add aliases for the FPSCR and SR bits that are included in TB_FLAGS, so that we don't accidentally reassign those bits. Fixes: 4da06fb3062 ("target/sh4: Implement prctl_unalign_sigbus") Resolves: https://gitlab.com/qemu-project/qemu/-/issues/856 Reviewed-by: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sh4/cpu.h | 56 +++++++++++++------------ linux-user/sh4/signal.c | 6 +-- target/sh4/cpu.c | 6 +-- target/sh4/helper.c | 6 +-- target/sh4/translate.c | 90 ++++++++++++++++++++++------------------- 5 files changed, 88 insertions(+), 76 deletions(-) diff --git a/target/sh4/cpu.h b/target/sh4/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.h +++ b/target/sh4/cpu.h @@ -XXX,XX +XXX,XX @@ #define FPSCR_RM_NEAREST (0 << 0) #define FPSCR_RM_ZERO (1 << 0) -#define DELAY_SLOT_MASK 0x7 -#define DELAY_SLOT (1 << 0) -#define DELAY_SLOT_CONDITIONAL (1 << 1) -#define DELAY_SLOT_RTE (1 << 2) +#define TB_FLAG_DELAY_SLOT (1 << 0) +#define TB_FLAG_DELAY_SLOT_COND (1 << 1) +#define TB_FLAG_DELAY_SLOT_RTE (1 << 2) +#define TB_FLAG_PENDING_MOVCA (1 << 3) +#define TB_FLAG_GUSA_SHIFT 4 /* [11:4] */ +#define TB_FLAG_GUSA_EXCLUSIVE (1 << 12) +#define TB_FLAG_UNALIGN (1 << 13) +#define TB_FLAG_SR_FD (1 << SR_FD) /* 15 */ +#define TB_FLAG_FPSCR_PR FPSCR_PR /* 19 */ +#define TB_FLAG_FPSCR_SZ FPSCR_SZ /* 20 */ +#define TB_FLAG_FPSCR_FR FPSCR_FR /* 21 */ +#define TB_FLAG_SR_RB (1 << SR_RB) /* 29 */ +#define TB_FLAG_SR_MD (1 << SR_MD) /* 30 */ -#define TB_FLAG_PENDING_MOVCA (1 << 3) -#define TB_FLAG_UNALIGN (1 << 4) - -#define GUSA_SHIFT 4 -#ifdef CONFIG_USER_ONLY -#define GUSA_EXCLUSIVE (1 << 12) -#define GUSA_MASK ((0xff << GUSA_SHIFT) | GUSA_EXCLUSIVE) -#else -/* Provide dummy versions of the above to allow tests against tbflags - to be elided while avoiding ifdefs. */ -#define GUSA_EXCLUSIVE 0 -#define GUSA_MASK 0 -#endif - -#define TB_FLAG_ENVFLAGS_MASK (DELAY_SLOT_MASK | GUSA_MASK) +#define TB_FLAG_DELAY_SLOT_MASK (TB_FLAG_DELAY_SLOT | \ + TB_FLAG_DELAY_SLOT_COND | \ + TB_FLAG_DELAY_SLOT_RTE) +#define TB_FLAG_GUSA_MASK ((0xff << TB_FLAG_GUSA_SHIFT) | \ + TB_FLAG_GUSA_EXCLUSIVE) +#define TB_FLAG_FPSCR_MASK (TB_FLAG_FPSCR_PR | \ + TB_FLAG_FPSCR_SZ | \ + TB_FLAG_FPSCR_FR) +#define TB_FLAG_SR_MASK (TB_FLAG_SR_FD | \ + TB_FLAG_SR_RB | \ + TB_FLAG_SR_MD) +#define TB_FLAG_ENVFLAGS_MASK (TB_FLAG_DELAY_SLOT_MASK | \ + TB_FLAG_GUSA_MASK) typedef struct tlb_t { uint32_t vpn; /* virtual page number */ @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index (CPUSH4State *env, bool ifetch) { /* The instruction in a RTE delay slot is fetched in privileged mode, but executed in user mode. */ - if (ifetch && (env->flags & DELAY_SLOT_RTE)) { + if (ifetch && (env->flags & TB_FLAG_DELAY_SLOT_RTE)) { return 0; } else { return (env->sr & (1u << SR_MD)) == 0 ? 1 : 0; @@ -XXX,XX +XXX,XX @@ static inline void cpu_get_tb_cpu_state(CPUSH4State *env, target_ulong *pc, { *pc = env->pc; /* For a gUSA region, notice the end of the region. */ - *cs_base = env->flags & GUSA_MASK ? env->gregs[0] : 0; - *flags = env->flags /* TB_FLAG_ENVFLAGS_MASK: bits 0-2, 4-12 */ - | (env->fpscr & (FPSCR_FR | FPSCR_SZ | FPSCR_PR)) /* Bits 19-21 */ - | (env->sr & ((1u << SR_MD) | (1u << SR_RB))) /* Bits 29-30 */ - | (env->sr & (1u << SR_FD)) /* Bit 15 */ + *cs_base = env->flags & TB_FLAG_GUSA_MASK ? env->gregs[0] : 0; + *flags = env->flags + | (env->fpscr & TB_FLAG_FPSCR_MASK) + | (env->sr & TB_FLAG_SR_MASK) | (env->movcal_backup ? TB_FLAG_PENDING_MOVCA : 0); /* Bit 3 */ #ifdef CONFIG_USER_ONLY *flags |= TB_FLAG_UNALIGN * !env_cpu(env)->prctl_unalign_sigbus; diff --git a/linux-user/sh4/signal.c b/linux-user/sh4/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/sh4/signal.c +++ b/linux-user/sh4/signal.c @@ -XXX,XX +XXX,XX @@ static void restore_sigcontext(CPUSH4State *regs, struct target_sigcontext *sc) __get_user(regs->fpul, &sc->sc_fpul); regs->tra = -1; /* disable syscall checks */ - regs->flags &= ~(DELAY_SLOT_MASK | GUSA_MASK); + regs->flags = 0; } void setup_frame(int sig, struct target_sigaction *ka, @@ -XXX,XX +XXX,XX @@ void setup_frame(int sig, struct target_sigaction *ka, regs->gregs[5] = 0; regs->gregs[6] = frame_addr += offsetof(typeof(*frame), sc); regs->pc = (unsigned long) ka->_sa_handler; - regs->flags &= ~(DELAY_SLOT_MASK | GUSA_MASK); + regs->flags &= ~(TB_FLAG_DELAY_SLOT_MASK | TB_FLAG_GUSA_MASK); unlock_user_struct(frame, frame_addr, 1); return; @@ -XXX,XX +XXX,XX @@ void setup_rt_frame(int sig, struct target_sigaction *ka, regs->gregs[5] = frame_addr + offsetof(typeof(*frame), info); regs->gregs[6] = frame_addr + offsetof(typeof(*frame), uc); regs->pc = (unsigned long) ka->_sa_handler; - regs->flags &= ~(DELAY_SLOT_MASK | GUSA_MASK); + regs->flags &= ~(TB_FLAG_DELAY_SLOT_MASK | TB_FLAG_GUSA_MASK); unlock_user_struct(frame, frame_addr, 1); return; diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static void superh_cpu_synchronize_from_tb(CPUState *cs, SuperHCPU *cpu = SUPERH_CPU(cs); cpu->env.pc = tb_pc(tb); - cpu->env.flags = tb->flags & TB_FLAG_ENVFLAGS_MASK; + cpu->env.flags = tb->flags; } #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static bool superh_io_recompile_replay_branch(CPUState *cs, SuperHCPU *cpu = SUPERH_CPU(cs); CPUSH4State *env = &cpu->env; - if ((env->flags & ((DELAY_SLOT | DELAY_SLOT_CONDITIONAL))) != 0 + if ((env->flags & (TB_FLAG_DELAY_SLOT | TB_FLAG_DELAY_SLOT_COND)) && env->pc != tb_pc(tb)) { env->pc -= 2; - env->flags &= ~(DELAY_SLOT | DELAY_SLOT_CONDITIONAL); + env->flags &= ~(TB_FLAG_DELAY_SLOT | TB_FLAG_DELAY_SLOT_COND); return true; } return false; diff --git a/target/sh4/helper.c b/target/sh4/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/helper.c +++ b/target/sh4/helper.c @@ -XXX,XX +XXX,XX @@ void superh_cpu_do_interrupt(CPUState *cs) env->sr |= (1u << SR_BL) | (1u << SR_MD) | (1u << SR_RB); env->lock_addr = -1; - if (env->flags & DELAY_SLOT_MASK) { + if (env->flags & TB_FLAG_DELAY_SLOT_MASK) { /* Branch instruction should be executed again before delay slot. */ env->spc -= 2; /* Clear flags for exception/interrupt routine. */ - env->flags &= ~DELAY_SLOT_MASK; + env->flags &= ~TB_FLAG_DELAY_SLOT_MASK; } if (do_exp) { @@ -XXX,XX +XXX,XX @@ bool superh_cpu_exec_interrupt(CPUState *cs, int interrupt_request) CPUSH4State *env = &cpu->env; /* Delay slots are indivisible, ignore interrupts */ - if (env->flags & DELAY_SLOT_MASK) { + if (env->flags & TB_FLAG_DELAY_SLOT_MASK) { return false; } else { superh_cpu_do_interrupt(cs); diff --git a/target/sh4/translate.c b/target/sh4/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -XXX,XX +XXX,XX @@ void superh_cpu_dump_state(CPUState *cs, FILE *f, int flags) i, env->gregs[i], i + 1, env->gregs[i + 1], i + 2, env->gregs[i + 2], i + 3, env->gregs[i + 3]); } - if (env->flags & DELAY_SLOT) { + if (env->flags & TB_FLAG_DELAY_SLOT) { qemu_printf("in delay slot (delayed_pc=0x%08x)\n", env->delayed_pc); - } else if (env->flags & DELAY_SLOT_CONDITIONAL) { + } else if (env->flags & TB_FLAG_DELAY_SLOT_COND) { qemu_printf("in conditional delay slot (delayed_pc=0x%08x)\n", env->delayed_pc); - } else if (env->flags & DELAY_SLOT_RTE) { + } else if (env->flags & TB_FLAG_DELAY_SLOT_RTE) { qemu_fprintf(f, "in rte delay slot (delayed_pc=0x%08x)\n", env->delayed_pc); } @@ -XXX,XX +XXX,XX @@ static inline void gen_save_cpu_state(DisasContext *ctx, bool save_pc) static inline bool use_exit_tb(DisasContext *ctx) { - return (ctx->tbflags & GUSA_EXCLUSIVE) != 0; + return (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) != 0; } static bool use_goto_tb(DisasContext *ctx, target_ulong dest) @@ -XXX,XX +XXX,XX @@ static void gen_conditional_jump(DisasContext *ctx, target_ulong dest, TCGLabel *l1 = gen_new_label(); TCGCond cond_not_taken = jump_if_true ? TCG_COND_EQ : TCG_COND_NE; - if (ctx->tbflags & GUSA_EXCLUSIVE) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* When in an exclusive region, we must continue to the end. Therefore, exit the region on a taken branch, but otherwise fall through to the next instruction. */ tcg_gen_brcondi_i32(cond_not_taken, cpu_sr_t, 0, l1); - tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~GUSA_MASK); + tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~TB_FLAG_GUSA_MASK); /* Note that this won't actually use a goto_tb opcode because we disallow it in use_goto_tb, but it handles exit + singlestep. */ gen_goto_tb(ctx, 0, dest); @@ -XXX,XX +XXX,XX @@ static void gen_delayed_conditional_jump(DisasContext * ctx) tcg_gen_mov_i32(ds, cpu_delayed_cond); tcg_gen_discard_i32(cpu_delayed_cond); - if (ctx->tbflags & GUSA_EXCLUSIVE) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* When in an exclusive region, we must continue to the end. Therefore, exit the region on a taken branch, but otherwise fall through to the next instruction. */ tcg_gen_brcondi_i32(TCG_COND_EQ, ds, 0, l1); /* Leave the gUSA region. */ - tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~GUSA_MASK); + tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~TB_FLAG_GUSA_MASK); gen_jump(ctx); gen_set_label(l1); @@ -XXX,XX +XXX,XX @@ static inline void gen_store_fpr64(DisasContext *ctx, TCGv_i64 t, int reg) #define XHACK(x) ((((x) & 1 ) << 4) | ((x) & 0xe)) #define CHECK_NOT_DELAY_SLOT \ - if (ctx->envflags & DELAY_SLOT_MASK) { \ - goto do_illegal_slot; \ + if (ctx->envflags & TB_FLAG_DELAY_SLOT_MASK) { \ + goto do_illegal_slot; \ } #define CHECK_PRIVILEGED \ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0x000b: /* rts */ CHECK_NOT_DELAY_SLOT tcg_gen_mov_i32(cpu_delayed_pc, cpu_pr); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x0028: /* clrmac */ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) CHECK_NOT_DELAY_SLOT gen_write_sr(cpu_ssr); tcg_gen_mov_i32(cpu_delayed_pc, cpu_spc); - ctx->envflags |= DELAY_SLOT_RTE; + ctx->envflags |= TB_FLAG_DELAY_SLOT_RTE; ctx->delayed_pc = (uint32_t) - 1; ctx->base.is_jmp = DISAS_STOP; return; @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) return; case 0xe000: /* mov #imm,Rn */ #ifdef CONFIG_USER_ONLY - /* Detect the start of a gUSA region. If so, update envflags - and end the TB. This will allow us to see the end of the - region (stored in R0) in the next TB. */ + /* + * Detect the start of a gUSA region (mov #-n, r15). + * If so, update envflags and end the TB. This will allow us + * to see the end of the region (stored in R0) in the next TB. + */ if (B11_8 == 15 && B7_0s < 0 && (tb_cflags(ctx->base.tb) & CF_PARALLEL)) { - ctx->envflags = deposit32(ctx->envflags, GUSA_SHIFT, 8, B7_0s); + ctx->envflags = + deposit32(ctx->envflags, TB_FLAG_GUSA_SHIFT, 8, B7_0s); ctx->base.is_jmp = DISAS_STOP; } #endif @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0xa000: /* bra disp */ CHECK_NOT_DELAY_SLOT ctx->delayed_pc = ctx->base.pc_next + 4 + B11_0s * 2; - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; return; case 0xb000: /* bsr disp */ CHECK_NOT_DELAY_SLOT tcg_gen_movi_i32(cpu_pr, ctx->base.pc_next + 4); ctx->delayed_pc = ctx->base.pc_next + 4 + B11_0s * 2; - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; return; } @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) CHECK_NOT_DELAY_SLOT tcg_gen_xori_i32(cpu_delayed_cond, cpu_sr_t, 1); ctx->delayed_pc = ctx->base.pc_next + 4 + B7_0s * 2; - ctx->envflags |= DELAY_SLOT_CONDITIONAL; + ctx->envflags |= TB_FLAG_DELAY_SLOT_COND; return; case 0x8900: /* bt label */ CHECK_NOT_DELAY_SLOT @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) CHECK_NOT_DELAY_SLOT tcg_gen_mov_i32(cpu_delayed_cond, cpu_sr_t); ctx->delayed_pc = ctx->base.pc_next + 4 + B7_0s * 2; - ctx->envflags |= DELAY_SLOT_CONDITIONAL; + ctx->envflags |= TB_FLAG_DELAY_SLOT_COND; return; case 0x8800: /* cmp/eq #imm,R0 */ tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_sr_t, REG(0), B7_0s); @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0x0023: /* braf Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_addi_i32(cpu_delayed_pc, REG(B11_8), ctx->base.pc_next + 4); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x0003: /* bsrf Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_movi_i32(cpu_pr, ctx->base.pc_next + 4); tcg_gen_add_i32(cpu_delayed_pc, REG(B11_8), cpu_pr); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x4015: /* cmp/pl Rn */ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0x402b: /* jmp @Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_mov_i32(cpu_delayed_pc, REG(B11_8)); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x400b: /* jsr @Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_movi_i32(cpu_pr, ctx->base.pc_next + 4); tcg_gen_mov_i32(cpu_delayed_pc, REG(B11_8)); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x400e: /* ldc Rm,SR */ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) fflush(stderr); #endif do_illegal: - if (ctx->envflags & DELAY_SLOT_MASK) { + if (ctx->envflags & TB_FLAG_DELAY_SLOT_MASK) { do_illegal_slot: gen_save_cpu_state(ctx, true); gen_helper_raise_slot_illegal_instruction(cpu_env); @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) do_fpu_disabled: gen_save_cpu_state(ctx, true); - if (ctx->envflags & DELAY_SLOT_MASK) { + if (ctx->envflags & TB_FLAG_DELAY_SLOT_MASK) { gen_helper_raise_slot_fpu_disable(cpu_env); } else { gen_helper_raise_fpu_disable(cpu_env); @@ -XXX,XX +XXX,XX @@ static void decode_opc(DisasContext * ctx) _decode_opc(ctx); - if (old_flags & DELAY_SLOT_MASK) { + if (old_flags & TB_FLAG_DELAY_SLOT_MASK) { /* go out of the delay slot */ - ctx->envflags &= ~DELAY_SLOT_MASK; + ctx->envflags &= ~TB_FLAG_DELAY_SLOT_MASK; /* When in an exclusive region, we must continue to the end for conditional branches. */ - if (ctx->tbflags & GUSA_EXCLUSIVE - && old_flags & DELAY_SLOT_CONDITIONAL) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE + && old_flags & TB_FLAG_DELAY_SLOT_COND) { gen_delayed_conditional_jump(ctx); return; } /* Otherwise this is probably an invalid gUSA region. Drop the GUSA bits so the next TB doesn't see them. */ - ctx->envflags &= ~GUSA_MASK; + ctx->envflags &= ~TB_FLAG_GUSA_MASK; tcg_gen_movi_i32(cpu_flags, ctx->envflags); - if (old_flags & DELAY_SLOT_CONDITIONAL) { + if (old_flags & TB_FLAG_DELAY_SLOT_COND) { gen_delayed_conditional_jump(ctx); } else { gen_jump(ctx); @@ -XXX,XX +XXX,XX @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) } /* The entire region has been translated. */ - ctx->envflags &= ~GUSA_MASK; + ctx->envflags &= ~TB_FLAG_GUSA_MASK; ctx->base.pc_next = pc_end; ctx->base.num_insns += max_insns - 1; return; @@ -XXX,XX +XXX,XX @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) /* Restart with the EXCLUSIVE bit set, within a TB run via cpu_exec_step_atomic holding the exclusive lock. */ - ctx->envflags |= GUSA_EXCLUSIVE; + ctx->envflags |= TB_FLAG_GUSA_EXCLUSIVE; gen_save_cpu_state(ctx, false); gen_helper_exclusive(cpu_env); ctx->base.is_jmp = DISAS_NORETURN; @@ -XXX,XX +XXX,XX @@ static void sh4_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) (tbflags & (1 << SR_RB))) * 0x10; ctx->fbank = tbflags & FPSCR_FR ? 0x10 : 0; - if (tbflags & GUSA_MASK) { +#ifdef CONFIG_USER_ONLY + if (tbflags & TB_FLAG_GUSA_MASK) { + /* In gUSA exclusive region. */ uint32_t pc = ctx->base.pc_next; uint32_t pc_end = ctx->base.tb->cs_base; - int backup = sextract32(ctx->tbflags, GUSA_SHIFT, 8); + int backup = sextract32(ctx->tbflags, TB_FLAG_GUSA_SHIFT, 8); int max_insns = (pc_end - pc) / 2; if (pc != pc_end + backup || max_insns < 2) { /* This is a malformed gUSA region. Don't do anything special, since the interpreter is likely to get confused. */ - ctx->envflags &= ~GUSA_MASK; - } else if (tbflags & GUSA_EXCLUSIVE) { + ctx->envflags &= ~TB_FLAG_GUSA_MASK; + } else if (tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* Regardless of single-stepping or the end of the page, we must complete execution of the gUSA region while holding the exclusive lock. */ @@ -XXX,XX +XXX,XX @@ static void sh4_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) return; } } +#endif /* Since the ISA is fixed-width, we can bound by the number of instructions remaining on the page. */ @@ -XXX,XX +XXX,XX @@ static void sh4_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) DisasContext *ctx = container_of(dcbase, DisasContext, base); #ifdef CONFIG_USER_ONLY - if (unlikely(ctx->envflags & GUSA_MASK) - && !(ctx->envflags & GUSA_EXCLUSIVE)) { + if (unlikely(ctx->envflags & TB_FLAG_GUSA_MASK) + && !(ctx->envflags & TB_FLAG_GUSA_EXCLUSIVE)) { /* We're in an gUSA region, and we have not already fallen back on using an exclusive region. Attempt to parse the region into a single supported atomic operation. Failure @@ -XXX,XX +XXX,XX @@ static void sh4_tr_tb_stop(DisasContextBase *dcbase, CPUState *cs) { DisasContext *ctx = container_of(dcbase, DisasContext, base); - if (ctx->tbflags & GUSA_EXCLUSIVE) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* Ending the region of exclusivity. Clear the bits. */ - ctx->envflags &= ~GUSA_MASK; + ctx->envflags &= ~TB_FLAG_GUSA_MASK; } switch (ctx->base.is_jmp) { -- 2.34.1 The following changes since commit b52daaf2c868f2bab102eb5acbf55b2917f46aea: Merge tag 'pull-block-2023-06-05' of https://gitlab.com/hreitz/qemu into staging (2023-06-05 10:27:31 -0700) are available in the Git repository at: https://gitlab.com/rth7680/qemu.git tags/pull-tcg-20230605 for you to fetch changes up to a7f6911c127b1dd1b8764e03b0ebcf0a227a15e4: tcg/tcg-op-vec: Remove left over _link_error() definitions (2023-06-05 12:20:16 -0700) ---------------------------------------------------------------- Build tcg/ once for system and once for user. Unmap perf_marker. Remove left over _link_error() definitions. ---------------------------------------------------------------- Ilya Leoshkevich (1): accel/tcg: Unmap perf_marker Philippe Mathieu-Daudé (2): target/ppc: Inline gen_icount_io_start() tcg/tcg-op-vec: Remove left over _link_error() definitions Richard Henderson (49): tcg/ppc: Remove TARGET_LONG_BITS, TCG_TYPE_TL tcg/riscv: Remove TARGET_LONG_BITS, TCG_TYPE_TL tcg/s390x: Remove TARGET_LONG_BITS, TCG_TYPE_TL tcg/sparc64: Remove TARGET_LONG_BITS, TCG_TYPE_TL tcg: Move TCG_TYPE_TL from tcg.h to tcg-op.h tcg: Widen CPUTLBEntry comparators to 64-bits tcg: Add tlb_fast_offset to TCGContext target/avr: Add missing includes of qemu/error-report.h target/*: Add missing includes of tcg/debug-assert.h *: Add missing includes of tcg/tcg.h tcg: Split out tcg-target-reg-bits.h target/arm: Fix test of TCG_OVERSIZED_GUEST tcg: Split out tcg/oversized-guest.h tcg: Move TCGv, dup_const_tl definitions to tcg-op.h tcg: Split tcg/tcg-op-common.h from tcg/tcg-op.h target/arm: Include helper-gen.h in translator.h target/hexagon: Include helper-gen.h where needed tcg: Remove outdated comments in helper-head.h tcg: Move TCGHelperInfo and dependencies to tcg/helper-info.h tcg: Pass TCGHelperInfo to tcg_gen_callN tcg: Move temp_idx and tcgv_i32_temp debug out of line tcg: Split tcg_gen_callN tcg: Split helper-gen.h tcg: Split helper-proto.h target/sh4: Emit insn_start for each insn in gUSA region tcg: Add insn_start_words to TCGContext tcg: Add guest_mo to TCGContext tcg: Move TLB_FLAGS_MASK check out of get_alignment_bits tcg: Split tcg/tcg-op-gvec.h tcg: Remove NO_CPU_IO_DEFS exec-all: Widen tb_page_addr_t for user-only exec-all: Widen TranslationBlock pc and cs_base to 64-bits tcg: Spit out exec/translation-block.h include/exec: Remove CODE_GEN_AVG_BLOCK_SIZE accel/tcg: Move most of gen-icount.h into translator.c accel/tcg: Introduce translator_io_start accel/tcg: Move translator_fake_ldb out of line target/arm: Tidy helpers for translation target/mips: Tidy helpers for translation target/*: Add missing includes of exec/translation-block.h target/arm: Add missing include of exec/exec-all.h accel/tcg: Tidy includes for translator.[ch] tcg: Fix PAGE/PROT confusion tcg: Move env defines out of NEED_CPU_H in helper-head.h tcg: Remove target-specific headers from tcg.[ch] plugins: Move plugin_insn_append to translator.c plugins: Drop unused headers from exec/plugin-gen.h exec/poison: Do not poison CONFIG_SOFTMMU tcg: Build once for system and once for user-only MAINTAINERS | 3 +- include/exec/cpu-all.h | 3 + include/exec/cpu-defs.h | 50 +- include/exec/cpu_ldst.h | 22 +- include/exec/exec-all.h | 142 +-- include/exec/gen-icount.h | 83 -- include/exec/helper-gen-common.h | 18 + include/exec/helper-gen.h | 97 +- include/exec/helper-head.h | 24 +- include/exec/helper-proto-common.h | 18 + include/exec/helper-proto.h | 73 +- include/exec/helper-tcg.h | 75 -- include/exec/plugin-gen.h | 24 - include/exec/poison.h | 1 - include/exec/tlb-common.h | 56 ++ include/exec/translation-block.h | 149 +++ include/exec/translator.h | 24 +- include/qemu/typedefs.h | 1 + include/tcg/helper-info.h | 64 ++ include/tcg/insn-start-words.h | 17 + include/tcg/oversized-guest.h | 23 + include/tcg/tcg-op-common.h | 996 +++++++++++++++++++ include/tcg/tcg-op-gvec-common.h | 426 ++++++++ include/tcg/tcg-op-gvec.h | 444 +-------- include/tcg/tcg-op.h | 1033 +------------------- include/tcg/tcg-opc.h | 6 +- include/tcg/tcg.h | 107 +- target/arm/cpregs.h | 4 +- target/arm/tcg/translate.h | 5 + target/mips/tcg/translate.h | 5 +- target/ppc/cpu.h | 2 - target/sparc/cpu.h | 2 - tcg/aarch64/tcg-target-reg-bits.h | 12 + tcg/arm/tcg-target-reg-bits.h | 12 + tcg/i386/tcg-target-reg-bits.h | 16 + tcg/i386/tcg-target.h | 2 - tcg/loongarch64/tcg-target-reg-bits.h | 21 + tcg/loongarch64/tcg-target.h | 11 - tcg/mips/tcg-target-reg-bits.h | 18 + tcg/mips/tcg-target.h | 8 - tcg/ppc/tcg-target-reg-bits.h | 16 + tcg/ppc/tcg-target.h | 5 - tcg/riscv/tcg-target-reg-bits.h | 19 + tcg/riscv/tcg-target.h | 9 - tcg/s390x/tcg-target-reg-bits.h | 17 + tcg/sparc64/tcg-target-reg-bits.h | 12 + tcg/tcg-internal.h | 47 +- tcg/tci/tcg-target-reg-bits.h | 18 + tcg/tci/tcg-target.h | 8 - include/exec/helper-gen.h.inc | 102 ++ include/exec/helper-proto.h.inc | 68 ++ accel/tcg/cpu-exec.c | 2 +- accel/tcg/cputlb.c | 12 +- accel/tcg/monitor.c | 1 + accel/tcg/perf.c | 19 +- accel/tcg/plugin-gen.c | 6 + accel/tcg/tcg-accel-ops-mttcg.c | 2 +- accel/tcg/tcg-accel-ops-rr.c | 2 +- accel/tcg/tcg-all.c | 1 + accel/tcg/tcg-runtime-gvec.c | 2 +- accel/tcg/tcg-runtime.c | 6 +- accel/tcg/translate-all.c | 30 +- accel/tcg/translator.c | 140 ++- target/alpha/translate.c | 18 +- target/arm/ptw.c | 8 +- target/arm/tcg/translate-a64.c | 42 +- target/arm/tcg/translate-m-nocp.c | 2 - target/arm/tcg/translate-mve.c | 4 - target/arm/tcg/translate-neon.c | 4 - target/arm/tcg/translate-sme.c | 7 - target/arm/tcg/translate-sve.c | 11 - target/arm/tcg/translate-vfp.c | 7 +- target/arm/tcg/translate.c | 41 +- target/avr/cpu.c | 1 + target/avr/helper.c | 1 + target/avr/translate.c | 6 +- target/cris/translate.c | 8 +- target/hexagon/genptr.c | 1 + target/hexagon/translate.c | 7 + target/hppa/translate.c | 10 +- target/i386/helper.c | 3 + target/i386/tcg/translate.c | 57 +- target/loongarch/translate.c | 7 +- target/m68k/translate.c | 5 +- target/microblaze/translate.c | 6 +- target/mips/tcg/msa_translate.c | 3 - target/mips/tcg/mxu_translate.c | 2 - target/mips/tcg/octeon_translate.c | 4 +- target/mips/tcg/rel6_translate.c | 2 - target/mips/tcg/translate.c | 53 +- target/mips/tcg/translate_addr_const.c | 1 - target/mips/tcg/tx79_translate.c | 4 +- target/mips/tcg/vr54xx_translate.c | 3 - target/nios2/translate.c | 6 +- target/openrisc/sys_helper.c | 1 + target/openrisc/translate.c | 14 +- target/ppc/translate.c | 78 +- target/riscv/cpu_helper.c | 1 + target/riscv/translate.c | 6 +- target/rx/cpu.c | 1 + target/rx/op_helper.c | 1 + target/rx/translate.c | 7 +- target/s390x/tcg/translate.c | 10 +- target/sh4/translate.c | 21 +- target/sparc/translate.c | 78 +- target/tricore/cpu.c | 1 + target/tricore/translate.c | 7 +- target/xtensa/translate.c | 31 +- tcg/optimize.c | 2 +- tcg/region.c | 20 +- tcg/tcg-op-gvec.c | 4 +- tcg/tcg-op-ldst.c | 26 +- tcg/tcg-op-vec.c | 13 +- tcg/tcg-op.c | 4 +- tcg/tcg.c | 218 +++-- tcg/tci.c | 3 +- include/exec/helper-info.c.inc | 96 ++ target/loongarch/insn_trans/trans_extra.c.inc | 4 +- target/loongarch/insn_trans/trans_privileged.c.inc | 4 +- target/ppc/power8-pmu-regs.c.inc | 10 +- target/ppc/translate/branch-impl.c.inc | 2 +- target/riscv/insn_trans/trans_privileged.c.inc | 8 +- target/riscv/insn_trans/trans_rvi.c.inc | 24 +- tcg/aarch64/tcg-target.c.inc | 8 +- tcg/arm/tcg-target.c.inc | 8 +- tcg/i386/tcg-target.c.inc | 9 +- tcg/loongarch64/tcg-target.c.inc | 8 +- tcg/mips/tcg-target.c.inc | 20 +- tcg/ppc/tcg-target.c.inc | 46 +- tcg/riscv/tcg-target.c.inc | 21 +- tcg/s390x/tcg-target.c.inc | 22 +- tcg/sparc64/tcg-target.c.inc | 20 +- scripts/make-config-poison.sh | 5 +- target/hexagon/idef-parser/idef-parser.y | 3 +- tcg/meson.build | 30 +- 135 files changed, 3088 insertions(+), 2782 deletions(-) delete mode 100644 include/exec/gen-icount.h create mode 100644 include/exec/helper-gen-common.h create mode 100644 include/exec/helper-proto-common.h delete mode 100644 include/exec/helper-tcg.h create mode 100644 include/exec/tlb-common.h create mode 100644 include/exec/translation-block.h create mode 100644 include/tcg/helper-info.h create mode 100644 include/tcg/insn-start-words.h create mode 100644 include/tcg/oversized-guest.h create mode 100644 include/tcg/tcg-op-common.h create mode 100644 include/tcg/tcg-op-gvec-common.h create mode 100644 tcg/aarch64/tcg-target-reg-bits.h create mode 100644 tcg/arm/tcg-target-reg-bits.h create mode 100644 tcg/i386/tcg-target-reg-bits.h create mode 100644 tcg/loongarch64/tcg-target-reg-bits.h create mode 100644 tcg/mips/tcg-target-reg-bits.h create mode 100644 tcg/ppc/tcg-target-reg-bits.h create mode 100644 tcg/riscv/tcg-target-reg-bits.h create mode 100644 tcg/s390x/tcg-target-reg-bits.h create mode 100644 tcg/sparc64/tcg-target-reg-bits.h create mode 100644 tcg/tci/tcg-target-reg-bits.h create mode 100644 include/exec/helper-gen.h.inc create mode 100644 include/exec/helper-proto.h.inc create mode 100644 include/exec/helper-info.c.inc All uses replaced with TCGContext.addr_type. Reviewed-by: Anton Johansson <anjo@rev.ng> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.c.inc | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, TCGReg addrlo, TCGReg addrhi, MemOpIdx oi, bool is_ld) { + TCGType addr_type = s->addr_type; TCGLabelQemuLdst *ldst = NULL; MemOp opc = get_memop(oi); MemOp a_bits, s_bits; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out32(s, AND | SAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_R0)); /* Load the (low part) TLB comparator into TMP2. */ - if (cmp_off == 0 && TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { - uint32_t lxu = (TCG_TARGET_REG_BITS == 32 || TARGET_LONG_BITS == 32 + if (cmp_off == 0 + && (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32)) { + uint32_t lxu = (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32 ? LWZUX : LDUX); tcg_out32(s, lxu | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2)); } else { tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2)); - if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { + if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) { tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off + 4 * HOST_BIG_ENDIAN); } else { - tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off); + tcg_out_ld(s, addr_type, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off); } } @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, * Load the TLB addend for use on the fast path. * Do this asap to minimize any load use delay. */ - if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) { tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_REG_TMP1, offsetof(CPUTLBEntry, addend)); } @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, } /* Mask the address for the requested alignment. */ - if (TARGET_LONG_BITS == 32) { + if (addr_type == TCG_TYPE_I32) { tcg_out_rlw(s, RLWINM, TCG_REG_R0, t, 0, (32 - a_bits) & 31, 31 - s->page_bits); } else if (a_bits == 0) { @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, } } - if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { + if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) { /* Low part comparison into cr7. */ tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, 0, 7, TCG_TYPE_I32); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out32(s, CRAND | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ)); } else { /* Full comparison into cr7. */ - tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, - 0, 7, TCG_TYPE_TL); + tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, 0, 7, addr_type); } /* Load a pointer into the current opcode w/conditional branch-link. */ @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, h->base = guest_base ? TCG_GUEST_BASE_REG : 0; #endif - if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { + if (TCG_TARGET_REG_BITS == 64 && addr_type == TCG_TYPE_I32) { /* Zero-extend the guest address for use in the host address. */ tcg_out_ext32u(s, TCG_REG_R0, addrlo); h->index = TCG_REG_R0; -- 2.34.1 All uses replaced with TCGContext.addr_type. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/riscv/tcg-target.c.inc | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/riscv/tcg-target.c.inc +++ b/tcg/riscv/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, TCGReg addr_reg, MemOpIdx oi, bool is_ld) { + TCGType addr_type = s->addr_type; TCGLabelQemuLdst *ldst = NULL; MemOp opc = get_memop(oi); TCGAtomAlign aa; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, addr_adj = addr_reg; if (a_mask < s_mask) { addr_adj = TCG_REG_TMP0; - tcg_out_opc_imm(s, TARGET_LONG_BITS == 32 ? OPC_ADDIW : OPC_ADDI, + tcg_out_opc_imm(s, addr_type == TCG_TYPE_I32 ? OPC_ADDIW : OPC_ADDI, addr_adj, addr_reg, s_mask - a_mask); } compare_mask = s->page_mask | a_mask; if (compare_mask == sextreg(compare_mask, 0, 12)) { tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_adj, compare_mask); } else { - tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_TMP1, compare_mask); + tcg_out_movi(s, addr_type, TCG_REG_TMP1, compare_mask); tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addr_adj); } /* Load the tlb comparator and the addend. */ - tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_TMP0, TCG_REG_TMP2, + tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2, is_ld ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP2, @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, tcg_out_opc_branch(s, OPC_BNE, TCG_REG_TMP0, TCG_REG_TMP1, 0); /* TLB Hit - translate address using addend. */ - if (TARGET_LONG_BITS == 64) { + if (addr_type != TCG_TYPE_I32) { tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, addr_reg, TCG_REG_TMP2); } else if (have_zba) { tcg_out_opc_reg(s, OPC_ADD_UW, TCG_REG_TMP0, addr_reg, TCG_REG_TMP2); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, if (guest_base != 0) { base = TCG_REG_TMP0; - if (TARGET_LONG_BITS == 64) { + if (addr_type != TCG_TYPE_I32) { tcg_out_opc_reg(s, OPC_ADD, base, addr_reg, TCG_GUEST_BASE_REG); } else if (have_zba) { tcg_out_opc_reg(s, OPC_ADD_UW, base, addr_reg, TCG_GUEST_BASE_REG); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, tcg_out_ext32u(s, base, addr_reg); tcg_out_opc_reg(s, OPC_ADD, base, base, TCG_GUEST_BASE_REG); } - } else if (TARGET_LONG_BITS == 64) { + } else if (addr_type != TCG_TYPE_I32) { base = addr_reg; } else { base = TCG_REG_TMP0; -- 2.34.1 All uses replaced with TCGContext.addr_type. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/s390x/tcg-target.c.inc | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/s390x/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, TCGReg addr_reg, MemOpIdx oi, bool is_ld) { + TCGType addr_type = s->addr_type; TCGLabelQemuLdst *ldst = NULL; MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tgen_andi_risbg(s, TCG_REG_R0, addr_reg, tlb_mask); } else { tcg_out_insn(s, RX, LA, TCG_REG_R0, addr_reg, TCG_REG_NONE, a_off); - tgen_andi(s, TCG_TYPE_TL, TCG_REG_R0, tlb_mask); + tgen_andi(s, addr_type, TCG_REG_R0, tlb_mask); } if (is_ld) { @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, } else { ofs = offsetof(CPUTLBEntry, addr_write); } - if (TARGET_LONG_BITS == 32) { + if (addr_type == TCG_TYPE_I32) { tcg_out_insn(s, RX, C, TCG_REG_R0, TCG_TMP0, TCG_REG_NONE, ofs); } else { tcg_out_insn(s, RXY, CG, TCG_REG_R0, TCG_TMP0, TCG_REG_NONE, ofs); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out_insn(s, RXY, LG, h->index, TCG_TMP0, TCG_REG_NONE, offsetof(CPUTLBEntry, addend)); - if (TARGET_LONG_BITS == 32) { + if (addr_type == TCG_TYPE_I32) { tcg_out_insn(s, RRE, ALGFR, h->index, addr_reg); h->base = TCG_REG_NONE; } else { @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, } h->base = addr_reg; - if (TARGET_LONG_BITS == 32) { + if (addr_type == TCG_TYPE_I32) { tcg_out_ext32u(s, TCG_TMP0, addr_reg); h->base = TCG_TMP0; } -- 2.34.1 All uses replaced with TCGContext.addr_type. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/sparc64/tcg-target.c.inc | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tcg/sparc64/tcg-target.c.inc b/tcg/sparc64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/sparc64/tcg-target.c.inc +++ b/tcg/sparc64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, TCGReg addr_reg, MemOpIdx oi, bool is_ld) { + TCGType addr_type = s->addr_type; TCGLabelQemuLdst *ldst = NULL; MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out_arith(s, TCG_REG_T1, TCG_REG_T1, TCG_REG_T3, ARITH_ADD); /* Load the tlb comparator and the addend. */ - tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_T2, TCG_REG_T1, cmp_off); + tcg_out_ld(s, addr_type, TCG_REG_T2, TCG_REG_T1, cmp_off); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_T1, TCG_REG_T1, add_off); h->base = TCG_REG_T1; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ldst->label_ptr[0] = s->code_ptr; /* bne,pn %[xi]cc, label0 */ - cc = TARGET_LONG_BITS == 64 ? BPCC_XCC : BPCC_ICC; + cc = addr_type == TCG_TYPE_I32 ? BPCC_ICC : BPCC_XCC; tcg_out_bpcc0(s, COND_NE, BPCC_PN | cc, 0); #else /* @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, #endif /* If the guest address must be zero-extended, do in the delay slot. */ - if (TARGET_LONG_BITS == 32) { + if (addr_type == TCG_TYPE_I32) { tcg_out_ext32u(s, TCG_REG_T2, addr_reg); h->index = TCG_REG_T2; } else { -- 2.34.1 Removes the only use of TARGET_LONG_BITS from tcg.h, which is to be target independent. Move the symbol to a define in tcg-op.h, which will continue to be target dependent. Rather than complicate matters for the use in tb_gen_code(), expand the definition there. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg-op.h | 8 ++++++++ include/tcg/tcg.h | 7 ------- accel/tcg/translate-all.c | 2 +- 3 files changed, 9 insertions(+), 8 deletions(-) diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -XXX,XX +XXX,XX @@ static inline void tcg_gen_concat32_i64(TCGv_i64 ret, TCGv_i64 lo, TCGv_i64 hi) #error must include QEMU headers #endif +#if TARGET_LONG_BITS == 32 +# define TCG_TYPE_TL TCG_TYPE_I32 +#elif TARGET_LONG_BITS == 64 +# define TCG_TYPE_TL TCG_TYPE_I64 +#else +# error +#endif + #if TARGET_INSN_START_WORDS == 1 static inline void tcg_gen_insn_start(target_ulong pc) { diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ typedef enum TCGType { #else TCG_TYPE_PTR = TCG_TYPE_I64, #endif - - /* An alias for the size of the target "long", aka register. */ -#if TARGET_LONG_BITS == 64 - TCG_TYPE_TL = TCG_TYPE_I64, -#else - TCG_TYPE_TL = TCG_TYPE_I32, -#endif } TCGType; /** diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, tb_set_page_addr0(tb, phys_pc); tb_set_page_addr1(tb, -1); tcg_ctx->gen_tb = tb; - tcg_ctx->addr_type = TCG_TYPE_TL; + tcg_ctx->addr_type = TARGET_LONG_BITS == 32 ? TCG_TYPE_I32 : TCG_TYPE_I64; #ifdef CONFIG_SOFTMMU tcg_ctx->page_bits = TARGET_PAGE_BITS; tcg_ctx->page_mask = TARGET_PAGE_MASK; -- 2.34.1 This makes CPUTLBEntry agnostic to the address size of the guest. When 32-bit addresses are in effect, we can simply read the low 32 bits of the 64-bit field. Similarly when we need to update the field for setting TLB_NOTDIRTY. For TCG backends that could in theory be big-endian, but in practice are not (arm, loongarch, riscv), use QEMU_BUILD_BUG_ON to document and ensure this is not accidentally missed. For s390x, which is always big-endian, use HOST_BIG_ENDIAN anyway, to document the reason for the adjustment. For sparc64 and ppc64, always perform a 64-bit load, and rely on the following 32-bit comparison to ignore the high bits. Rearrange mips and ppc if ladders for clarity. Reviewed-by: Anton Johansson <anjo@rev.ng> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 37 +++++++++++--------------------- include/exec/cpu_ldst.h | 19 ++++++++++------ accel/tcg/cputlb.c | 8 +++++-- tcg/aarch64/tcg-target.c.inc | 1 + tcg/arm/tcg-target.c.inc | 1 + tcg/loongarch64/tcg-target.c.inc | 1 + tcg/mips/tcg-target.c.inc | 13 ++++++----- tcg/ppc/tcg-target.c.inc | 28 +++++++++++++----------- tcg/riscv/tcg-target.c.inc | 1 + tcg/s390x/tcg-target.c.inc | 1 + tcg/sparc64/tcg-target.c.inc | 8 +++++-- 11 files changed, 67 insertions(+), 51 deletions(-) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ /* use a fully associative victim tlb of 8 entries */ #define CPU_VTLB_SIZE 8 -#if HOST_LONG_BITS == 32 && TARGET_LONG_BITS == 32 -#define CPU_TLB_ENTRY_BITS 4 -#else #define CPU_TLB_ENTRY_BITS 5 -#endif #define CPU_TLB_DYN_MIN_BITS 6 #define CPU_TLB_DYN_DEFAULT_BITS 8 @@ -XXX,XX +XXX,XX @@ # endif /* Minimalized TLB entry for use by TCG fast path. */ -typedef struct CPUTLBEntry { - /* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address - bit TARGET_PAGE_BITS-1..4 : Nonzero for accesses that should not - go directly to ram. - bit 3 : indicates that the entry is invalid - bit 2..0 : zero - */ - union { - struct { - target_ulong addr_read; - target_ulong addr_write; - target_ulong addr_code; - /* Addend to virtual address to get host address. IO accesses - use the corresponding iotlb value. */ - uintptr_t addend; - }; +typedef union CPUTLBEntry { + struct { + uint64_t addr_read; + uint64_t addr_write; + uint64_t addr_code; /* - * Padding to get a power of two size, as well as index - * access to addr_{read,write,code}. + * Addend to virtual address to get host address. IO accesses + * use the corresponding iotlb value. */ - target_ulong addr_idx[(1 << CPU_TLB_ENTRY_BITS) / TARGET_LONG_SIZE]; + uintptr_t addend; }; + /* + * Padding to get a power of two size, as well as index + * access to addr_{read,write,code}. + */ + uint64_t addr_idx[(1 << CPU_TLB_ENTRY_BITS) / sizeof(uint64_t)]; } CPUTLBEntry; QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS)); - #endif /* !CONFIG_USER_ONLY && CONFIG_TCG */ #if !defined(CONFIG_USER_ONLY) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ static inline target_ulong tlb_read_idx(const CPUTLBEntry *entry, { /* Do not rearrange the CPUTLBEntry structure members. */ QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_read) != - MMU_DATA_LOAD * TARGET_LONG_SIZE); + MMU_DATA_LOAD * sizeof(uint64_t)); QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_write) != - MMU_DATA_STORE * TARGET_LONG_SIZE); + MMU_DATA_STORE * sizeof(uint64_t)); QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_code) != - MMU_INST_FETCH * TARGET_LONG_SIZE); + MMU_INST_FETCH * sizeof(uint64_t)); - const target_ulong *ptr = &entry->addr_idx[access_type]; -#if TCG_OVERSIZED_GUEST - return *ptr; +#if TARGET_LONG_BITS == 32 + /* Use qatomic_read, in case of addr_write; only care about low bits. */ + const uint32_t *ptr = (uint32_t *)&entry->addr_idx[access_type]; + ptr += HOST_BIG_ENDIAN; + return qatomic_read(ptr); #else + const uint64_t *ptr = &entry->addr_idx[access_type]; +# if TCG_OVERSIZED_GUEST + return *ptr; +# else /* ofs might correspond to .addr_write, so use qatomic_read */ return qatomic_read(ptr); +# endif #endif } diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tlb_reset_dirty_range_locked(CPUTLBEntry *tlb_entry, addr &= TARGET_PAGE_MASK; addr += tlb_entry->addend; if ((addr - start) < length) { -#if TCG_OVERSIZED_GUEST +#if TARGET_LONG_BITS == 32 + uint32_t *ptr_write = (uint32_t *)&tlb_entry->addr_write; + ptr_write += HOST_BIG_ENDIAN; + qatomic_set(ptr_write, *ptr_write | TLB_NOTDIRTY); +#elif TCG_OVERSIZED_GUEST tlb_entry->addr_write |= TLB_NOTDIRTY; #else qatomic_set(&tlb_entry->addr_write, - tlb_entry->addr_write | TLB_NOTDIRTY); + tlb_entry->addr_write | TLB_NOTDIRTY); #endif } } diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/aarch64/tcg-target.c.inc +++ b/tcg/aarch64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out_insn(s, 3502, ADD, 1, TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP0); /* Load the tlb comparator into TMP0, and the fast path addend into TMP1. */ + QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN); tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP1, is_ld ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, * Add the tlb_table pointer, creating the CPUTLBEntry address in R1. * Load the tlb comparator into R2/R3 and the fast path addend into R1. */ + QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN); if (cmp_off == 0) { if (s->addr_type == TCG_TYPE_I32) { tcg_out_ld32_rwb(s, COND_AL, TCG_REG_R2, TCG_REG_R1, TCG_REG_R0); diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/loongarch64/tcg-target.c.inc +++ b/tcg/loongarch64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out_opc_add_d(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1); /* Load the tlb comparator and the addend. */ + QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN); tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2, is_ld ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/mips/tcg-target.c.inc +++ b/tcg/mips/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, /* Add the tlb_table pointer, creating the CPUTLBEntry address in TMP3. */ tcg_out_opc_reg(s, ALIAS_PADD, TCG_TMP3, TCG_TMP3, TCG_TMP1); + if (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32) { + /* Load the (low half) tlb comparator. */ + tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3, + cmp_off + HOST_BIG_ENDIAN * 4); + } else { + tcg_out_ld(s, TCG_TYPE_I64, TCG_TMP0, TCG_TMP3, cmp_off); + } + if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) { - /* Load the tlb comparator. */ - tcg_out_ld(s, addr_type, TCG_TMP0, TCG_TMP3, cmp_off); /* Load the tlb addend for the fast path. */ tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off); - } else { - /* Load the low half of the tlb comparator. */ - tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF); } /* diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, } tcg_out32(s, AND | SAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_R0)); - /* Load the (low part) TLB comparator into TMP2. */ - if (cmp_off == 0 - && (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32)) { - uint32_t lxu = (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32 - ? LWZUX : LDUX); - tcg_out32(s, lxu | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2)); + /* + * Load the (low part) TLB comparator into TMP2. + * For 64-bit host, always load the entire 64-bit slot for simplicity. + * We will ignore the high bits with tcg_out_cmp(..., addr_type). + */ + if (TCG_TARGET_REG_BITS == 64) { + if (cmp_off == 0) { + tcg_out32(s, LDUX | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2)); + } else { + tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2)); + tcg_out_ld(s, TCG_TYPE_I64, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off); + } + } else if (cmp_off == 0 && !HOST_BIG_ENDIAN) { + tcg_out32(s, LWZUX | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2)); } else { tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2)); - if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) { - tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, - TCG_REG_TMP1, cmp_off + 4 * HOST_BIG_ENDIAN); - } else { - tcg_out_ld(s, addr_type, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off); - } + tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1, + cmp_off + 4 * HOST_BIG_ENDIAN); } /* diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/riscv/tcg-target.c.inc +++ b/tcg/riscv/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, } /* Load the tlb comparator and the addend. */ + QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN); tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2, is_ld ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/s390x/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ofs = offsetof(CPUTLBEntry, addr_write); } if (addr_type == TCG_TYPE_I32) { + ofs += HOST_BIG_ENDIAN * 4; tcg_out_insn(s, RX, C, TCG_REG_R0, TCG_TMP0, TCG_REG_NONE, ofs); } else { tcg_out_insn(s, RXY, CG, TCG_REG_R0, TCG_TMP0, TCG_REG_NONE, ofs); diff --git a/tcg/sparc64/tcg-target.c.inc b/tcg/sparc64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/sparc64/tcg-target.c.inc +++ b/tcg/sparc64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, /* Add the tlb_table pointer, creating the CPUTLBEntry address into R2. */ tcg_out_arith(s, TCG_REG_T1, TCG_REG_T1, TCG_REG_T3, ARITH_ADD); - /* Load the tlb comparator and the addend. */ - tcg_out_ld(s, addr_type, TCG_REG_T2, TCG_REG_T1, cmp_off); + /* + * Load the tlb comparator and the addend. + * Always load the entire 64-bit comparator for simplicity. + * We will ignore the high bits via BPCC_ICC below. + */ + tcg_out_ld(s, TCG_TYPE_I64, TCG_REG_T2, TCG_REG_T1, cmp_off); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_T1, TCG_REG_T1, add_off); h->base = TCG_REG_T1; -- 2.34.1 Disconnect the layout of ArchCPU from TCG compilation. Pass the relative offset of 'env' and 'neg.tlb.f' as a parameter. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 39 +--------------------- include/exec/tlb-common.h | 56 ++++++++++++++++++++++++++++++++ include/tcg/tcg.h | 1 + accel/tcg/translate-all.c | 2 ++ tcg/tcg.c | 13 ++++++++ tcg/aarch64/tcg-target.c.inc | 7 ++-- tcg/arm/tcg-target.c.inc | 7 ++-- tcg/i386/tcg-target.c.inc | 9 ++--- tcg/loongarch64/tcg-target.c.inc | 7 ++-- tcg/mips/tcg-target.c.inc | 7 ++-- tcg/ppc/tcg-target.c.inc | 7 ++-- tcg/riscv/tcg-target.c.inc | 7 ++-- tcg/s390x/tcg-target.c.inc | 7 ++-- tcg/sparc64/tcg-target.c.inc | 7 ++-- 14 files changed, 110 insertions(+), 66 deletions(-) create mode 100644 include/exec/tlb-common.h diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ #define NB_MMU_MODES 16 #if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG) +#include "exec/tlb-common.h" /* use a fully associative victim tlb of 8 entries */ #define CPU_VTLB_SIZE 8 -#define CPU_TLB_ENTRY_BITS 5 - #define CPU_TLB_DYN_MIN_BITS 6 #define CPU_TLB_DYN_DEFAULT_BITS 8 @@ -XXX,XX +XXX,XX @@ # endif # endif -/* Minimalized TLB entry for use by TCG fast path. */ -typedef union CPUTLBEntry { - struct { - uint64_t addr_read; - uint64_t addr_write; - uint64_t addr_code; - /* - * Addend to virtual address to get host address. IO accesses - * use the corresponding iotlb value. - */ - uintptr_t addend; - }; - /* - * Padding to get a power of two size, as well as index - * access to addr_{read,write,code}. - */ - uint64_t addr_idx[(1 << CPU_TLB_ENTRY_BITS) / sizeof(uint64_t)]; -} CPUTLBEntry; - -QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS)); - #endif /* !CONFIG_USER_ONLY && CONFIG_TCG */ #if !defined(CONFIG_USER_ONLY) @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBDesc { CPUTLBEntryFull *fulltlb; } CPUTLBDesc; -/* - * Data elements that are per MMU mode, accessed by the fast path. - * The structure is aligned to aid loading the pair with one insn. - */ -typedef struct CPUTLBDescFast { - /* Contains (n_entries - 1) << CPU_TLB_ENTRY_BITS */ - uintptr_t mask; - /* The array of tlb entries itself. */ - CPUTLBEntry *table; -} CPUTLBDescFast QEMU_ALIGNED(2 * sizeof(void *)); - /* * Data elements that are shared between all MMU modes. */ @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLB { CPUTLBDescFast f[NB_MMU_MODES]; } CPUTLB; -/* This will be used by TCG backends to compute offsets. */ -#define TLB_MASK_TABLE_OFS(IDX) \ - ((int)offsetof(ArchCPU, neg.tlb.f[IDX]) - (int)offsetof(ArchCPU, env)) - #else typedef struct CPUTLB { } CPUTLB; diff --git a/include/exec/tlb-common.h b/include/exec/tlb-common.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/tlb-common.h @@ -XXX,XX +XXX,XX @@ +/* + * Common definitions for the softmmu tlb + * + * Copyright (c) 2003 Fabrice Bellard + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ +#ifndef EXEC_TLB_COMMON_H +#define EXEC_TLB_COMMON_H 1 + +#define CPU_TLB_ENTRY_BITS 5 + +/* Minimalized TLB entry for use by TCG fast path. */ +typedef union CPUTLBEntry { + struct { + uint64_t addr_read; + uint64_t addr_write; + uint64_t addr_code; + /* + * Addend to virtual address to get host address. IO accesses + * use the corresponding iotlb value. + */ + uintptr_t addend; + }; + /* + * Padding to get a power of two size, as well as index + * access to addr_{read,write,code}. + */ + uint64_t addr_idx[(1 << CPU_TLB_ENTRY_BITS) / sizeof(uint64_t)]; +} CPUTLBEntry; + +QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS)); + +/* + * Data elements that are per MMU mode, accessed by the fast path. + * The structure is aligned to aid loading the pair with one insn. + */ +typedef struct CPUTLBDescFast { + /* Contains (n_entries - 1) << CPU_TLB_ENTRY_BITS */ + uintptr_t mask; + /* The array of tlb entries itself. */ + CPUTLBEntry *table; +} CPUTLBDescFast QEMU_ALIGNED(2 * sizeof(void *)); + +#endif /* EXEC_TLB_COMMON_H */ diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ struct TCGContext { TCGType addr_type; /* TCG_TYPE_I32 or TCG_TYPE_I64 */ #ifdef CONFIG_SOFTMMU + int tlb_fast_offset; int page_mask; uint8_t page_bits; uint8_t tlb_dyn_max_bits; diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, tcg_ctx->page_bits = TARGET_PAGE_BITS; tcg_ctx->page_mask = TARGET_PAGE_MASK; tcg_ctx->tlb_dyn_max_bits = CPU_TLB_DYN_MAX_BITS; + tcg_ctx->tlb_fast_offset = + (int)offsetof(ArchCPU, neg.tlb.f) - (int)offsetof(ArchCPU, env); #endif tb_overflow: diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ #define NO_CPU_IO_DEFS #include "exec/exec-all.h" +#include "exec/tlb-common.h" #include "tcg/tcg-op.h" #if UINTPTR_MAX == UINT32_MAX @@ -XXX,XX +XXX,XX @@ static uintptr_t G_GNUC_UNUSED get_jmp_target_addr(TCGContext *s, int which) return (uintptr_t)tcg_splitwx_to_rx(&s->gen_tb->jmp_target_addr[which]); } +#if defined(CONFIG_SOFTMMU) && !defined(CONFIG_TCG_INTERPRETER) +static int tlb_mask_table_ofs(TCGContext *s, int which) +{ + return s->tlb_fast_offset + which * sizeof(CPUTLBDescFast); +} +#endif + /* Signal overflow, starting over with fewer guest insns. */ static G_NORETURN void tcg_raise_tb_overflow(TCGContext *s) @@ -XXX,XX +XXX,XX @@ void tcg_func_start(TCGContext *s) tcg_debug_assert(s->addr_type == TCG_TYPE_I32 || s->addr_type == TCG_TYPE_I64); + +#if defined(CONFIG_SOFTMMU) && !defined(CONFIG_TCG_INTERPRETER) + tcg_debug_assert(s->tlb_fast_offset < 0); + tcg_debug_assert(s->tlb_fast_offset >= MIN_TLB_MASK_TABLE_OFS); +#endif } static TCGTemp *tcg_temp_alloc(TCGContext *s) diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/aarch64/tcg-target.c.inc +++ b/tcg/aarch64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) return true; } +/* We expect to use a 7-bit scaled negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -512 + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ? TCG_TYPE_I64 : TCG_TYPE_I32); /* Load env_tlb(env)->f[mmu_idx].{mask,table} into {tmp0,tmp1}. */ - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -512); QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, mask) != 0); QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, table) != 8); tcg_out_insn(s, 3314, LDP, TCG_REG_TMP0, TCG_REG_TMP1, TCG_AREG0, - TLB_MASK_TABLE_OFS(mem_index), 1, 0); + tlb_mask_table_ofs(s, mem_index), 1, 0); /* Extract the TLB index from the address into X0. */ tcg_out_insn(s, 3502S, AND_LSR, mask_type == TCG_TYPE_I64, diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) return true; } +/* We expect to use an 9-bit sign-magnitude negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -256 + static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, TCGReg addrlo, TCGReg addrhi, MemOpIdx oi, bool is_ld) @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, int mem_index = get_mmuidx(oi); int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write); - int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int fast_off = tlb_mask_table_ofs(s, mem_index); unsigned s_mask = (1 << (opc & MO_SIZE)) - 1; TCGReg t_addr; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ldst->addrhi_reg = addrhi; /* Load env_tlb(env)->f[mmu_idx].{mask,table} into {r0,r1}. */ - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -256); QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, mask) != 0); QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, table) != 4); tcg_out_ldrd_8(s, COND_AL, TCG_REG_R0, TCG_AREG0, fast_off); diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static inline int setup_guest_base_seg(void) #endif /* setup_guest_base_seg */ #endif /* !SOFTMMU */ +#define MIN_TLB_MASK_TABLE_OFS INT_MIN + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, int trexw = 0, hrexw = 0, tlbrexw = 0; unsigned mem_index = get_mmuidx(oi); unsigned s_mask = (1 << s_bits) - 1; + int fast_ofs = tlb_mask_table_ofs(s, mem_index); int tlb_mask; ldst = new_ldst_label(s); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, s->page_bits - CPU_TLB_ENTRY_BITS); tcg_out_modrm_offset(s, OPC_AND_GvEv + trexw, TCG_REG_L0, TCG_AREG0, - TLB_MASK_TABLE_OFS(mem_index) + - offsetof(CPUTLBDescFast, mask)); + fast_ofs + offsetof(CPUTLBDescFast, mask)); tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, TCG_REG_L0, TCG_AREG0, - TLB_MASK_TABLE_OFS(mem_index) + - offsetof(CPUTLBDescFast, table)); + fast_ofs + offsetof(CPUTLBDescFast, table)); /* * If the required alignment is at least as large as the access, simply diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/loongarch64/tcg-target.c.inc +++ b/tcg/loongarch64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ bool tcg_target_has_memory_bswap(MemOp memop) return false; } +/* We expect to use a 12-bit negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -(1 << 11) + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, #ifdef CONFIG_SOFTMMU unsigned s_bits = opc & MO_SIZE; int mem_index = get_mmuidx(oi); - int fast_ofs = TLB_MASK_TABLE_OFS(mem_index); + int fast_ofs = tlb_mask_table_ofs(s, mem_index); int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask); int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ldst->oi = oi; ldst->addrlo_reg = addr_reg; - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11)); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs); diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/mips/tcg-target.c.inc +++ b/tcg/mips/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ bool tcg_target_has_memory_bswap(MemOp memop) return false; } +/* We expect to use a 16-bit negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -32768 + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, #ifdef CONFIG_SOFTMMU unsigned s_mask = (1 << s_bits) - 1; int mem_index = get_mmuidx(oi); - int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int fast_off = tlb_mask_table_ofs(s, mem_index); int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); int table_off = fast_off + offsetof(CPUTLBDescFast, table); int add_off = offsetof(CPUTLBEntry, addend); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ldst->addrhi_reg = addrhi; /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -32768); tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_AREG0, mask_off); tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP1, TCG_AREG0, table_off); diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ bool tcg_target_has_memory_bswap(MemOp memop) return aa.atom <= MO_64; } +/* We expect to use a 16-bit negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -32768 + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, int mem_index = get_mmuidx(oi); int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write); - int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int fast_off = tlb_mask_table_ofs(s, mem_index); int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); int table_off = fast_off + offsetof(CPUTLBDescFast, table); @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, ldst->addrhi_reg = addrhi; /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -32768); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, mask_off); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_AREG0, table_off); diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/riscv/tcg-target.c.inc +++ b/tcg/riscv/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) return true; } +/* We expect to use a 12-bit negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -(1 << 11) + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, unsigned s_bits = opc & MO_SIZE; unsigned s_mask = (1u << s_bits) - 1; int mem_index = get_mmuidx(oi); - int fast_ofs = TLB_MASK_TABLE_OFS(mem_index); + int fast_ofs = tlb_mask_table_ofs(s, mem_index); int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask); int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table); int compare_mask; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase, ldst->oi = oi; ldst->addrlo_reg = addr_reg; - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11)); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs); diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/s390x/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) return true; } +/* We're expecting to use a 20-bit negative offset on the tlb memory ops. */ +#define MIN_TLB_MASK_TABLE_OFS -(1 << 19) + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, #ifdef CONFIG_SOFTMMU unsigned s_mask = (1 << s_bits) - 1; int mem_index = get_mmuidx(oi); - int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int fast_off = tlb_mask_table_ofs(s, mem_index); int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); int table_off = fast_off + offsetof(CPUTLBDescFast, table); int ofs, a_off; @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, tcg_out_sh64(s, RSY_SRLG, TCG_TMP0, addr_reg, TCG_REG_NONE, s->page_bits - CPU_TLB_ENTRY_BITS); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 19)); tcg_out_insn(s, RXY, NG, TCG_TMP0, TCG_AREG0, TCG_REG_NONE, mask_off); tcg_out_insn(s, RXY, AG, TCG_TMP0, TCG_AREG0, TCG_REG_NONE, table_off); diff --git a/tcg/sparc64/tcg-target.c.inc b/tcg/sparc64/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/sparc64/tcg-target.c.inc +++ b/tcg/sparc64/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ bool tcg_target_has_memory_bswap(MemOp memop) return true; } +/* We expect to use a 13-bit negative offset from ENV. */ +#define MIN_TLB_MASK_TABLE_OFS -(1 << 12) + /* * For softmmu, perform the TLB load and compare. * For useronly, perform any required alignment tests. @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, #ifdef CONFIG_SOFTMMU int mem_index = get_mmuidx(oi); - int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int fast_off = tlb_mask_table_ofs(s, mem_index); int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); int table_off = fast_off + offsetof(CPUTLBDescFast, table); int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read) @@ -XXX,XX +XXX,XX @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, int cc; /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); - QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 12)); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_T2, TCG_AREG0, mask_off); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_T3, TCG_AREG0, table_off); -- 2.34.1 This had been pulled in from tcg/tcg.h, via exec/cpu_ldst.h, via exec/exec-all.h, but the include of tcg.h will be removed. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/avr/helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/avr/helper.c b/target/avr/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/helper.c +++ b/target/avr/helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/log.h" +#include "qemu/error-report.h" #include "cpu.h" #include "hw/core/tcg-cpu-ops.h" #include "exec/exec-all.h" -- 2.34.1 This had been pulled in from tcg/tcg.h, via exec/cpu_ldst.h, via exec/exec-all.h, but the include of tcg.h will be removed. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/avr/cpu.c | 1 + target/rx/cpu.c | 1 + target/rx/op_helper.c | 1 + target/tricore/cpu.c | 1 + 4 files changed, 4 insertions(+) diff --git a/target/avr/cpu.c b/target/avr/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "cpu.h" #include "disas/dis-asm.h" +#include "tcg/debug-assert.h" static void avr_cpu_set_pc(CPUState *cs, vaddr value) { diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "hw/loader.h" #include "fpu/softfloat.h" +#include "tcg/debug-assert.h" static void rx_cpu_set_pc(CPUState *cs, vaddr value) { diff --git a/target/rx/op_helper.c b/target/rx/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/op_helper.c +++ b/target/rx/op_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "exec/cpu_ldst.h" #include "fpu/softfloat.h" +#include "tcg/debug-assert.h" static inline G_NORETURN void raise_exception(CPURXState *env, int index, diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/cpu.c +++ b/target/tricore/cpu.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/exec-all.h" #include "qemu/error-report.h" +#include "tcg/debug-assert.h" static inline void set_feature(CPUTriCoreState *env, int feature) { -- 2.34.1 This had been pulled in from exec/cpu_ldst.h, via exec/exec-all.h, but the include of tcg.h will be removed. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/monitor.c | 1 + accel/tcg/tcg-accel-ops-mttcg.c | 2 +- accel/tcg/tcg-accel-ops-rr.c | 2 +- target/i386/helper.c | 3 +++ target/openrisc/sys_helper.c | 1 + 5 files changed, 7 insertions(+), 2 deletions(-) diff --git a/accel/tcg/monitor.c b/accel/tcg/monitor.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/monitor.c +++ b/accel/tcg/monitor.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/cpus.h" #include "sysemu/cpu-timers.h" #include "sysemu/tcg.h" +#include "tcg/tcg.h" #include "internal.h" diff --git a/accel/tcg/tcg-accel-ops-mttcg.c b/accel/tcg/tcg-accel-ops-mttcg.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-accel-ops-mttcg.c +++ b/accel/tcg/tcg-accel-ops-mttcg.c @@ -XXX,XX +XXX,XX @@ #include "qemu/guest-random.h" #include "exec/exec-all.h" #include "hw/boards.h" - +#include "tcg/tcg.h" #include "tcg-accel-ops.h" #include "tcg-accel-ops-mttcg.h" diff --git a/accel/tcg/tcg-accel-ops-rr.c b/accel/tcg/tcg-accel-ops-rr.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-accel-ops-rr.c +++ b/accel/tcg/tcg-accel-ops-rr.c @@ -XXX,XX +XXX,XX @@ #include "qemu/notify.h" #include "qemu/guest-random.h" #include "exec/exec-all.h" - +#include "tcg/tcg.h" #include "tcg-accel-ops.h" #include "tcg-accel-ops-rr.h" #include "tcg-accel-ops-icount.h" diff --git a/target/i386/helper.c b/target/i386/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/helper.c +++ b/target/i386/helper.c @@ -XXX,XX +XXX,XX @@ #include "monitor/monitor.h" #endif #include "qemu/log.h" +#ifdef CONFIG_TCG +#include "tcg/tcg.h" +#endif void cpu_sync_avx_hflag(CPUX86State *env) { diff --git a/target/openrisc/sys_helper.c b/target/openrisc/sys_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/sys_helper.c +++ b/target/openrisc/sys_helper.c @@ -XXX,XX +XXX,XX @@ #ifndef CONFIG_USER_ONLY #include "hw/boards.h" #endif +#include "tcg/tcg.h" #define TO_SPR(group, number) (((group) << 11) + (number)) -- 2.34.1 Often, the only thing we need to know about the TCG host is the register size. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg.h | 12 +----------- tcg/aarch64/tcg-target-reg-bits.h | 12 ++++++++++++ tcg/arm/tcg-target-reg-bits.h | 12 ++++++++++++ tcg/i386/tcg-target-reg-bits.h | 16 ++++++++++++++++ tcg/i386/tcg-target.h | 2 -- tcg/loongarch64/tcg-target-reg-bits.h | 21 +++++++++++++++++++++ tcg/loongarch64/tcg-target.h | 11 ----------- tcg/mips/tcg-target-reg-bits.h | 18 ++++++++++++++++++ tcg/mips/tcg-target.h | 8 -------- tcg/ppc/tcg-target-reg-bits.h | 16 ++++++++++++++++ tcg/ppc/tcg-target.h | 5 ----- tcg/riscv/tcg-target-reg-bits.h | 19 +++++++++++++++++++ tcg/riscv/tcg-target.h | 9 --------- tcg/s390x/tcg-target-reg-bits.h | 17 +++++++++++++++++ tcg/sparc64/tcg-target-reg-bits.h | 12 ++++++++++++ tcg/tci/tcg-target-reg-bits.h | 18 ++++++++++++++++++ tcg/tci/tcg-target.h | 8 -------- tcg/s390x/tcg-target.c.inc | 5 ----- 18 files changed, 162 insertions(+), 59 deletions(-) create mode 100644 tcg/aarch64/tcg-target-reg-bits.h create mode 100644 tcg/arm/tcg-target-reg-bits.h create mode 100644 tcg/i386/tcg-target-reg-bits.h create mode 100644 tcg/loongarch64/tcg-target-reg-bits.h create mode 100644 tcg/mips/tcg-target-reg-bits.h create mode 100644 tcg/ppc/tcg-target-reg-bits.h create mode 100644 tcg/riscv/tcg-target-reg-bits.h create mode 100644 tcg/s390x/tcg-target-reg-bits.h create mode 100644 tcg/sparc64/tcg-target-reg-bits.h create mode 100644 tcg/tci/tcg-target-reg-bits.h diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ #include "qemu/plugin.h" #include "qemu/queue.h" #include "tcg/tcg-mo.h" +#include "tcg-target-reg-bits.h" #include "tcg-target.h" #include "tcg/tcg-cond.h" #include "tcg/debug-assert.h" @@ -XXX,XX +XXX,XX @@ #define CPU_TEMP_BUF_NLONGS 128 #define TCG_STATIC_FRAME_SIZE (CPU_TEMP_BUF_NLONGS * sizeof(long)) -/* Default target word size to pointer size. */ -#ifndef TCG_TARGET_REG_BITS -# if UINTPTR_MAX == UINT32_MAX -# define TCG_TARGET_REG_BITS 32 -# elif UINTPTR_MAX == UINT64_MAX -# define TCG_TARGET_REG_BITS 64 -# else -# error Unknown pointer size for tcg target -# endif -#endif - #if TCG_TARGET_REG_BITS == 32 typedef int32_t tcg_target_long; typedef uint32_t tcg_target_ulong; diff --git a/tcg/aarch64/tcg-target-reg-bits.h b/tcg/aarch64/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/aarch64/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Define target-specific register size + * Copyright (c) 2023 Linaro + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#define TCG_TARGET_REG_BITS 64 + +#endif diff --git a/tcg/arm/tcg-target-reg-bits.h b/tcg/arm/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/arm/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2023 Linaro + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#define TCG_TARGET_REG_BITS 32 + +#endif diff --git a/tcg/i386/tcg-target-reg-bits.h b/tcg/i386/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/i386/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#ifdef __x86_64__ +# define TCG_TARGET_REG_BITS 64 +#else +# define TCG_TARGET_REG_BITS 32 +#endif + +#endif diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -XXX,XX +XXX,XX @@ #define TCG_TARGET_INSN_UNIT_SIZE 1 #ifdef __x86_64__ -# define TCG_TARGET_REG_BITS 64 # define TCG_TARGET_NB_REGS 32 # define MAX_CODE_GEN_BUFFER_SIZE (2 * GiB) #else -# define TCG_TARGET_REG_BITS 32 # define TCG_TARGET_NB_REGS 24 # define MAX_CODE_GEN_BUFFER_SIZE UINT32_MAX #endif diff --git a/tcg/loongarch64/tcg-target-reg-bits.h b/tcg/loongarch64/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/loongarch64/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2021 WANG Xuerui <git@xen0n.name> + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +/* + * Loongson removed the (incomplete) 32-bit support from kernel and toolchain + * for the initial upstreaming of this architecture, so don't bother and just + * support the LP64* ABI for now. + */ +#if defined(__loongarch64) +# define TCG_TARGET_REG_BITS 64 +#else +# error unsupported LoongArch register size +#endif + +#endif diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/loongarch64/tcg-target.h +++ b/tcg/loongarch64/tcg-target.h @@ -XXX,XX +XXX,XX @@ #ifndef LOONGARCH_TCG_TARGET_H #define LOONGARCH_TCG_TARGET_H -/* - * Loongson removed the (incomplete) 32-bit support from kernel and toolchain - * for the initial upstreaming of this architecture, so don't bother and just - * support the LP64* ABI for now. - */ -#if defined(__loongarch64) -# define TCG_TARGET_REG_BITS 64 -#else -# error unsupported LoongArch register size -#endif - #define TCG_TARGET_INSN_UNIT_SIZE 4 #define TCG_TARGET_NB_REGS 32 diff --git a/tcg/mips/tcg-target-reg-bits.h b/tcg/mips/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/mips/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2008-2009 Arnaud Patard <arnaud.patard@rtp-net.org> + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#if _MIPS_SIM == _ABIO32 +# define TCG_TARGET_REG_BITS 32 +#elif _MIPS_SIM == _ABIN32 || _MIPS_SIM == _ABI64 +# define TCG_TARGET_REG_BITS 64 +#else +# error "Unknown ABI" +#endif + +#endif diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/mips/tcg-target.h +++ b/tcg/mips/tcg-target.h @@ -XXX,XX +XXX,XX @@ #ifndef MIPS_TCG_TARGET_H #define MIPS_TCG_TARGET_H -#if _MIPS_SIM == _ABIO32 -# define TCG_TARGET_REG_BITS 32 -#elif _MIPS_SIM == _ABIN32 || _MIPS_SIM == _ABI64 -# define TCG_TARGET_REG_BITS 64 -#else -# error "Unknown ABI" -#endif - #define TCG_TARGET_INSN_UNIT_SIZE 4 #define TCG_TARGET_NB_REGS 32 diff --git a/tcg/ppc/tcg-target-reg-bits.h b/tcg/ppc/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/ppc/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#ifdef _ARCH_PPC64 +# define TCG_TARGET_REG_BITS 64 +#else +# define TCG_TARGET_REG_BITS 32 +#endif + +#endif diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.h +++ b/tcg/ppc/tcg-target.h @@ -XXX,XX +XXX,XX @@ #ifndef PPC_TCG_TARGET_H #define PPC_TCG_TARGET_H -#ifdef _ARCH_PPC64 -# define TCG_TARGET_REG_BITS 64 -#else -# define TCG_TARGET_REG_BITS 32 -#endif #define MAX_CODE_GEN_BUFFER_SIZE ((size_t)-1) #define TCG_TARGET_NB_REGS 64 diff --git a/tcg/riscv/tcg-target-reg-bits.h b/tcg/riscv/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/riscv/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2018 SiFive, Inc + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +/* + * We don't support oversize guests. + * Since we will only build tcg once, this in turn requires a 64-bit host. + */ +#if __riscv_xlen != 64 +#error "unsupported code generation mode" +#endif +#define TCG_TARGET_REG_BITS 64 + +#endif diff --git a/tcg/riscv/tcg-target.h b/tcg/riscv/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/riscv/tcg-target.h +++ b/tcg/riscv/tcg-target.h @@ -XXX,XX +XXX,XX @@ #ifndef RISCV_TCG_TARGET_H #define RISCV_TCG_TARGET_H -/* - * We don't support oversize guests. - * Since we will only build tcg once, this in turn requires a 64-bit host. - */ -#if __riscv_xlen != 64 -#error "unsupported code generation mode" -#endif -#define TCG_TARGET_REG_BITS 64 - #define TCG_TARGET_INSN_UNIT_SIZE 4 #define TCG_TARGET_NB_REGS 32 #define MAX_CODE_GEN_BUFFER_SIZE ((size_t)-1) diff --git a/tcg/s390x/tcg-target-reg-bits.h b/tcg/s390x/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/s390x/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2009 Ulrich Hecht <uli@suse.de> + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +/* We only support generating code for 64-bit mode. */ +#if UINTPTR_MAX == UINT64_MAX +# define TCG_TARGET_REG_BITS 64 +#else +# error "unsupported code generation mode" +#endif + +#endif diff --git a/tcg/sparc64/tcg-target-reg-bits.h b/tcg/sparc64/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/sparc64/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2023 Linaro + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#define TCG_TARGET_REG_BITS 64 + +#endif diff --git a/tcg/tci/tcg-target-reg-bits.h b/tcg/tci/tcg-target-reg-bits.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tcg/tci/tcg-target-reg-bits.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define target-specific register size + * Copyright (c) 2009, 2011 Stefan Weil + */ + +#ifndef TCG_TARGET_REG_BITS_H +#define TCG_TARGET_REG_BITS_H + +#if UINTPTR_MAX == UINT32_MAX +# define TCG_TARGET_REG_BITS 32 +#elif UINTPTR_MAX == UINT64_MAX +# define TCG_TARGET_REG_BITS 64 +#else +# error Unknown pointer size for tci target +#endif + +#endif diff --git a/tcg/tci/tcg-target.h b/tcg/tci/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/tci/tcg-target.h +++ b/tcg/tci/tcg-target.h @@ -XXX,XX +XXX,XX @@ #define TCG_TARGET_INSN_UNIT_SIZE 4 #define MAX_CODE_GEN_BUFFER_SIZE ((size_t)-1) -#if UINTPTR_MAX == UINT32_MAX -# define TCG_TARGET_REG_BITS 32 -#elif UINTPTR_MAX == UINT64_MAX -# define TCG_TARGET_REG_BITS 64 -#else -# error Unknown pointer size for tci target -#endif - /* Optional instructions. */ #define TCG_TARGET_HAS_bswap16_i32 1 diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/s390x/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ * THE SOFTWARE. */ -/* We only support generating code for 64-bit mode. */ -#if TCG_TARGET_REG_BITS != 64 -#error "unsupported code generation mode" -#endif - #include "../tcg-ldst.c.inc" #include "../tcg-pool.c.inc" #include "elf.h" -- 2.34.1 The symbol is always defined, even if to 0. We wanted to test for TCG_OVERSIZED_GUEST == 0. This fixed, the #error is reached while building arm-softmmu, because TCG_OVERSIZED_GUEST is not true (nor supposed to be true) for arm32 guest on a 32-bit host. But that's ok, because this feature doesn't apply to arm32. Add an #ifdef for TARGET_AARCH64. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/ptw.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static uint64_t arm_casq_ptw(CPUARMState *env, uint64_t old_val, uint64_t new_val, S1Translate *ptw, ARMMMUFaultInfo *fi) { +#ifdef TARGET_AARCH64 uint64_t cur_val; void *host = ptw->out_host; @@ -XXX,XX +XXX,XX @@ static uint64_t arm_casq_ptw(CPUARMState *env, uint64_t old_val, * we know that TCG_OVERSIZED_GUEST is set, which means that we are * running in round-robin mode and could only race with dma i/o. */ -#ifndef TCG_OVERSIZED_GUEST +#if !TCG_OVERSIZED_GUEST # error "Unexpected configuration" #endif bool locked = qemu_mutex_iothread_locked(); @@ -XXX,XX +XXX,XX @@ static uint64_t arm_casq_ptw(CPUARMState *env, uint64_t old_val, #endif return cur_val; +#else + /* AArch32 does not have FEAT_HADFS. */ + g_assert_not_reached(); +#endif } static bool get_level1_table_address(CPUARMState *env, ARMMMUIdx mmu_idx, -- 2.34.1 Move a use of TARGET_LONG_BITS out of tcg/tcg.h. Include the new file only where required. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 3 +-- include/tcg/oversized-guest.h | 23 +++++++++++++++++++++++ include/tcg/tcg.h | 9 --------- accel/tcg/cputlb.c | 1 + accel/tcg/tcg-all.c | 1 + target/arm/ptw.c | 1 + target/riscv/cpu_helper.c | 1 + 7 files changed, 28 insertions(+), 11 deletions(-) create mode 100644 include/tcg/oversized-guest.h diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ static inline void clear_helper_retaddr(void) #else -/* Needed for TCG_OVERSIZED_GUEST */ -#include "tcg/tcg.h" +#include "tcg/oversized-guest.h" static inline target_ulong tlb_read_idx(const CPUTLBEntry *entry, MMUAccessType access_type) diff --git a/include/tcg/oversized-guest.h b/include/tcg/oversized-guest.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/tcg/oversized-guest.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define TCG_OVERSIZED_GUEST + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef EXEC_TCG_OVERSIZED_GUEST_H +#define EXEC_TCG_OVERSIZED_GUEST_H + +#include "tcg-target-reg-bits.h" +#include "cpu-param.h" + +/* + * Oversized TCG guests make things like MTTCG hard + * as we can't use atomics for cputlb updates. + */ +#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS +#define TCG_OVERSIZED_GUEST 1 +#else +#define TCG_OVERSIZED_GUEST 0 +#endif + +#endif diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ typedef uint64_t tcg_target_ulong; #error unsupported #endif -/* Oversized TCG guests make things like MTTCG hard - * as we can't use atomics for cputlb updates. - */ -#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS -#define TCG_OVERSIZED_GUEST 1 -#else -#define TCG_OVERSIZED_GUEST 0 -#endif - #if TCG_TARGET_NB_REGS <= 32 typedef uint32_t TCGRegSet; #elif TCG_TARGET_NB_REGS <= 64 diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ #include "qemu/plugin-memory.h" #endif #include "tcg/tcg-ldst.h" +#include "tcg/oversized-guest.h" #include "exec/helper-proto.h" /* DEBUG defines, enable DEBUG_TLB_LOG to log to the CPU_LOG_MMU target */ diff --git a/accel/tcg/tcg-all.c b/accel/tcg/tcg-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-all.c +++ b/accel/tcg/tcg-all.c @@ -XXX,XX +XXX,XX @@ #include "exec/replay-core.h" #include "sysemu/cpu-timers.h" #include "tcg/tcg.h" +#include "tcg/oversized-guest.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/accel.h" diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "internals.h" #include "idau.h" +#include "tcg/oversized-guest.h" typedef struct S1Translate { diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu_helper.c +++ b/target/riscv/cpu_helper.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/cpu-timers.h" #include "cpu_bits.h" #include "debug.h" +#include "tcg/oversized-guest.h" int riscv_cpu_mmu_index(CPURISCVState *env, bool ifetch) { -- 2.34.1 These two items are the last uses of TARGET_LONG_BITS within tcg.h, and are more in common with the other "_tl" definitions within that file. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg-op.h | 15 ++++++++++++++- include/tcg/tcg.h | 19 ------------------- target/mips/tcg/translate.h | 1 + 3 files changed, 15 insertions(+), 20 deletions(-) diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -XXX,XX +XXX,XX @@ static inline void tcg_gen_plugin_cb_end(void) } #if TARGET_LONG_BITS == 32 +typedef TCGv_i32 TCGv; #define tcg_temp_new() tcg_temp_new_i32() #define tcg_global_mem_new tcg_global_mem_new_i32 #define tcg_temp_free tcg_temp_free_i32 #define tcgv_tl_temp tcgv_i32_temp #define tcg_gen_qemu_ld_tl tcg_gen_qemu_ld_i32 #define tcg_gen_qemu_st_tl tcg_gen_qemu_st_i32 -#else +#elif TARGET_LONG_BITS == 64 +typedef TCGv_i64 TCGv; #define tcg_temp_new() tcg_temp_new_i64() #define tcg_global_mem_new tcg_global_mem_new_i64 #define tcg_temp_free tcg_temp_free_i64 #define tcgv_tl_temp tcgv_i64_temp #define tcg_gen_qemu_ld_tl tcg_gen_qemu_ld_i64 #define tcg_gen_qemu_st_tl tcg_gen_qemu_st_i64 +#else +#error Unhandled TARGET_LONG_BITS value #endif void tcg_gen_qemu_ld_i32_chk(TCGv_i32, TCGTemp *, TCGArg, MemOp, TCGType); @@ -XXX,XX +XXX,XX @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_atomic_umax_fetch_tl tcg_gen_atomic_umax_fetch_i64 #define tcg_gen_dup_tl_vec tcg_gen_dup_i64_vec #define tcg_gen_dup_tl tcg_gen_dup_i64 +#define dup_const_tl dup_const #else #define tcg_gen_movi_tl tcg_gen_movi_i32 #define tcg_gen_mov_tl tcg_gen_mov_i32 @@ -XXX,XX +XXX,XX @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_atomic_umax_fetch_tl tcg_gen_atomic_umax_fetch_i32 #define tcg_gen_dup_tl_vec tcg_gen_dup_i32_vec #define tcg_gen_dup_tl tcg_gen_dup_i32 + +#define dup_const_tl(VECE, C) \ + (__builtin_constant_p(VECE) \ + ? ( (VECE) == MO_8 ? 0x01010101ul * (uint8_t)(C) \ + : (VECE) == MO_16 ? 0x00010001ul * (uint16_t)(C) \ + : (VECE) == MO_32 ? 0x00000001ul * (uint32_t)(C) \ + : (qemu_build_not_reached_always(), 0)) \ + : (target_long)dup_const(VECE, C)) #endif #if UINTPTR_MAX == UINT32_MAX diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ typedef struct TCGv_i128_d *TCGv_i128; typedef struct TCGv_ptr_d *TCGv_ptr; typedef struct TCGv_vec_d *TCGv_vec; typedef TCGv_ptr TCGv_env; -#if TARGET_LONG_BITS == 32 -#define TCGv TCGv_i32 -#elif TARGET_LONG_BITS == 64 -#define TCGv TCGv_i64 -#else -#error Unhandled TARGET_LONG_BITS value -#endif /* call flags */ /* Helper does not read globals (either directly or through an exception). It @@ -XXX,XX +XXX,XX @@ uint64_t dup_const(unsigned vece, uint64_t c); : (qemu_build_not_reached_always(), 0)) \ : dup_const(VECE, C)) -#if TARGET_LONG_BITS == 64 -# define dup_const_tl dup_const -#else -# define dup_const_tl(VECE, C) \ - (__builtin_constant_p(VECE) \ - ? ( (VECE) == MO_8 ? 0x01010101ul * (uint8_t)(C) \ - : (VECE) == MO_16 ? 0x00010001ul * (uint16_t)(C) \ - : (VECE) == MO_32 ? 0x00000001ul * (uint32_t)(C) \ - : (qemu_build_not_reached_always(), 0)) \ - : (target_long)dup_const(VECE, C)) -#endif - #ifdef CONFIG_DEBUG_TCG void tcg_assert_listed_vecop(TCGOpcode); #else diff --git a/target/mips/tcg/translate.h b/target/mips/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.h +++ b/target/mips/tcg/translate.h @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "exec/translator.h" +#include "tcg/tcg-op.h" #define MIPS_DEBUG_DISAS 0 -- 2.34.1 Create tcg/tcg-op-common.h, moving everything that does not concern TARGET_LONG_BITS or TCGv. Adjust tcg/*.c to use the new header instead of tcg-op.h, in preparation for compiling tcg/ only once. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg-op-common.h | 996 ++++++++++++++++++++++++++++++++++ include/tcg/tcg-op.h | 1004 +---------------------------------- tcg/optimize.c | 2 +- tcg/tcg-op-gvec.c | 2 +- tcg/tcg-op-ldst.c | 2 +- tcg/tcg-op-vec.c | 2 +- tcg/tcg-op.c | 2 +- tcg/tcg.c | 2 +- tcg/tci.c | 3 +- 9 files changed, 1007 insertions(+), 1008 deletions(-) create mode 100644 include/tcg/tcg-op-common.h diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/tcg/tcg-op-common.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Target independent opcode generation functions. + * + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef TCG_TCG_OP_COMMON_H +#define TCG_TCG_OP_COMMON_H + +#include "tcg/tcg.h" +#include "exec/helper-proto.h" +#include "exec/helper-gen.h" + +/* Basic output routines. Not for general consumption. */ + +void tcg_gen_op1(TCGOpcode, TCGArg); +void tcg_gen_op2(TCGOpcode, TCGArg, TCGArg); +void tcg_gen_op3(TCGOpcode, TCGArg, TCGArg, TCGArg); +void tcg_gen_op4(TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg); +void tcg_gen_op5(TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg, TCGArg); +void tcg_gen_op6(TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg, TCGArg, TCGArg); + +void vec_gen_2(TCGOpcode, TCGType, unsigned, TCGArg, TCGArg); +void vec_gen_3(TCGOpcode, TCGType, unsigned, TCGArg, TCGArg, TCGArg); +void vec_gen_4(TCGOpcode, TCGType, unsigned, TCGArg, TCGArg, TCGArg, TCGArg); + +static inline void tcg_gen_op1_i32(TCGOpcode opc, TCGv_i32 a1) +{ + tcg_gen_op1(opc, tcgv_i32_arg(a1)); +} + +static inline void tcg_gen_op1_i64(TCGOpcode opc, TCGv_i64 a1) +{ + tcg_gen_op1(opc, tcgv_i64_arg(a1)); +} + +static inline void tcg_gen_op1i(TCGOpcode opc, TCGArg a1) +{ + tcg_gen_op1(opc, a1); +} + +static inline void tcg_gen_op2_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2) +{ + tcg_gen_op2(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2)); +} + +static inline void tcg_gen_op2_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2) +{ + tcg_gen_op2(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2)); +} + +static inline void tcg_gen_op2i_i32(TCGOpcode opc, TCGv_i32 a1, TCGArg a2) +{ + tcg_gen_op2(opc, tcgv_i32_arg(a1), a2); +} + +static inline void tcg_gen_op2i_i64(TCGOpcode opc, TCGv_i64 a1, TCGArg a2) +{ + tcg_gen_op2(opc, tcgv_i64_arg(a1), a2); +} + +static inline void tcg_gen_op2ii(TCGOpcode opc, TCGArg a1, TCGArg a2) +{ + tcg_gen_op2(opc, a1, a2); +} + +static inline void tcg_gen_op3_i32(TCGOpcode opc, TCGv_i32 a1, + TCGv_i32 a2, TCGv_i32 a3) +{ + tcg_gen_op3(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), tcgv_i32_arg(a3)); +} + +static inline void tcg_gen_op3_i64(TCGOpcode opc, TCGv_i64 a1, + TCGv_i64 a2, TCGv_i64 a3) +{ + tcg_gen_op3(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), tcgv_i64_arg(a3)); +} + +static inline void tcg_gen_op3i_i32(TCGOpcode opc, TCGv_i32 a1, + TCGv_i32 a2, TCGArg a3) +{ + tcg_gen_op3(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), a3); +} + +static inline void tcg_gen_op3i_i64(TCGOpcode opc, TCGv_i64 a1, + TCGv_i64 a2, TCGArg a3) +{ + tcg_gen_op3(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), a3); +} + +static inline void tcg_gen_ldst_op_i32(TCGOpcode opc, TCGv_i32 val, + TCGv_ptr base, TCGArg offset) +{ + tcg_gen_op3(opc, tcgv_i32_arg(val), tcgv_ptr_arg(base), offset); +} + +static inline void tcg_gen_ldst_op_i64(TCGOpcode opc, TCGv_i64 val, + TCGv_ptr base, TCGArg offset) +{ + tcg_gen_op3(opc, tcgv_i64_arg(val), tcgv_ptr_arg(base), offset); +} + +static inline void tcg_gen_op4_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGv_i32 a4) +{ + tcg_gen_op4(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), tcgv_i32_arg(a4)); +} + +static inline void tcg_gen_op4_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGv_i64 a4) +{ + tcg_gen_op4(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), tcgv_i64_arg(a4)); +} + +static inline void tcg_gen_op4i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGArg a4) +{ + tcg_gen_op4(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), a4); +} + +static inline void tcg_gen_op4i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGArg a4) +{ + tcg_gen_op4(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), a4); +} + +static inline void tcg_gen_op4ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGArg a3, TCGArg a4) +{ + tcg_gen_op4(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), a3, a4); +} + +static inline void tcg_gen_op4ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGArg a3, TCGArg a4) +{ + tcg_gen_op4(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), a3, a4); +} + +static inline void tcg_gen_op5_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGv_i32 a4, TCGv_i32 a5) +{ + tcg_gen_op5(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), tcgv_i32_arg(a4), tcgv_i32_arg(a5)); +} + +static inline void tcg_gen_op5_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGv_i64 a4, TCGv_i64 a5) +{ + tcg_gen_op5(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), tcgv_i64_arg(a4), tcgv_i64_arg(a5)); +} + +static inline void tcg_gen_op5i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGv_i32 a4, TCGArg a5) +{ + tcg_gen_op5(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), tcgv_i32_arg(a4), a5); +} + +static inline void tcg_gen_op5i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGv_i64 a4, TCGArg a5) +{ + tcg_gen_op5(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), tcgv_i64_arg(a4), a5); +} + +static inline void tcg_gen_op5ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGArg a4, TCGArg a5) +{ + tcg_gen_op5(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), a4, a5); +} + +static inline void tcg_gen_op5ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGArg a4, TCGArg a5) +{ + tcg_gen_op5(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), a4, a5); +} + +static inline void tcg_gen_op6_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGv_i32 a4, + TCGv_i32 a5, TCGv_i32 a6) +{ + tcg_gen_op6(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), tcgv_i32_arg(a4), tcgv_i32_arg(a5), + tcgv_i32_arg(a6)); +} + +static inline void tcg_gen_op6_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGv_i64 a4, + TCGv_i64 a5, TCGv_i64 a6) +{ + tcg_gen_op6(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), tcgv_i64_arg(a4), tcgv_i64_arg(a5), + tcgv_i64_arg(a6)); +} + +static inline void tcg_gen_op6i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGv_i32 a4, + TCGv_i32 a5, TCGArg a6) +{ + tcg_gen_op6(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), tcgv_i32_arg(a4), tcgv_i32_arg(a5), a6); +} + +static inline void tcg_gen_op6i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGv_i64 a4, + TCGv_i64 a5, TCGArg a6) +{ + tcg_gen_op6(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), tcgv_i64_arg(a4), tcgv_i64_arg(a5), a6); +} + +static inline void tcg_gen_op6ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, + TCGv_i32 a3, TCGv_i32 a4, + TCGArg a5, TCGArg a6) +{ + tcg_gen_op6(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), + tcgv_i32_arg(a3), tcgv_i32_arg(a4), a5, a6); +} + +static inline void tcg_gen_op6ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, + TCGv_i64 a3, TCGv_i64 a4, + TCGArg a5, TCGArg a6) +{ + tcg_gen_op6(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), + tcgv_i64_arg(a3), tcgv_i64_arg(a4), a5, a6); +} + + +/* Generic ops. */ + +static inline void gen_set_label(TCGLabel *l) +{ + l->present = 1; + tcg_gen_op1(INDEX_op_set_label, label_arg(l)); +} + +void tcg_gen_br(TCGLabel *l); +void tcg_gen_mb(TCGBar); + +/** + * tcg_gen_exit_tb() - output exit_tb TCG operation + * @tb: The TranslationBlock from which we are exiting + * @idx: Direct jump slot index, or exit request + * + * See tcg/README for more info about this TCG operation. + * See also tcg.h and the block comment above TB_EXIT_MASK. + * + * For a normal exit from the TB, back to the main loop, @tb should + * be NULL and @idx should be 0. Otherwise, @tb should be valid and + * @idx should be one of the TB_EXIT_ values. + */ +void tcg_gen_exit_tb(const TranslationBlock *tb, unsigned idx); + +/** + * tcg_gen_goto_tb() - output goto_tb TCG operation + * @idx: Direct jump slot index (0 or 1) + * + * See tcg/README for more info about this TCG operation. + * + * NOTE: In softmmu emulation, direct jumps with goto_tb are only safe within + * the pages this TB resides in because we don't take care of direct jumps when + * address mapping changes, e.g. in tlb_flush(). In user mode, there's only a + * static address translation, so the destination address is always valid, TBs + * are always invalidated properly, and direct jumps are reset when mapping + * changes. + */ +void tcg_gen_goto_tb(unsigned idx); + +/** + * tcg_gen_lookup_and_goto_ptr() - look up the current TB, jump to it if valid + * @addr: Guest address of the target TB + * + * If the TB is not valid, jump to the epilogue. + * + * This operation is optional. If the TCG backend does not implement goto_ptr, + * this op is equivalent to calling tcg_gen_exit_tb() with 0 as the argument. + */ +void tcg_gen_lookup_and_goto_ptr(void); + +static inline void tcg_gen_plugin_cb_start(unsigned from, unsigned type, + unsigned wr) +{ + tcg_gen_op3(INDEX_op_plugin_cb_start, from, type, wr); +} + +static inline void tcg_gen_plugin_cb_end(void) +{ + tcg_emit_op(INDEX_op_plugin_cb_end, 0); +} + +/* 32 bit ops */ + +void tcg_gen_movi_i32(TCGv_i32 ret, int32_t arg); +void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_subfi_i32(TCGv_i32 ret, int32_t arg1, TCGv_i32 arg2); +void tcg_gen_subi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_andi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_ori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_xori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_shli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_shri_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_sari_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_muli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_div_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_rem_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_divu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_remu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_andc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_eqv_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_nand_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_nor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_orc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_clz_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_ctz_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_clzi_i32(TCGv_i32 ret, TCGv_i32 arg1, uint32_t arg2); +void tcg_gen_ctzi_i32(TCGv_i32 ret, TCGv_i32 arg1, uint32_t arg2); +void tcg_gen_clrsb_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_ctpop_i32(TCGv_i32 a1, TCGv_i32 a2); +void tcg_gen_rotl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_rotli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_rotr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_rotri_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); +void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2, + unsigned int ofs, unsigned int len); +void tcg_gen_deposit_z_i32(TCGv_i32 ret, TCGv_i32 arg, + unsigned int ofs, unsigned int len); +void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg, + unsigned int ofs, unsigned int len); +void tcg_gen_sextract_i32(TCGv_i32 ret, TCGv_i32 arg, + unsigned int ofs, unsigned int len); +void tcg_gen_extract2_i32(TCGv_i32 ret, TCGv_i32 al, TCGv_i32 ah, + unsigned int ofs); +void tcg_gen_brcond_i32(TCGCond cond, TCGv_i32 arg1, TCGv_i32 arg2, TCGLabel *); +void tcg_gen_brcondi_i32(TCGCond cond, TCGv_i32 arg1, int32_t arg2, TCGLabel *); +void tcg_gen_setcond_i32(TCGCond cond, TCGv_i32 ret, + TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_setcondi_i32(TCGCond cond, TCGv_i32 ret, + TCGv_i32 arg1, int32_t arg2); +void tcg_gen_movcond_i32(TCGCond cond, TCGv_i32 ret, TCGv_i32 c1, + TCGv_i32 c2, TCGv_i32 v1, TCGv_i32 v2); +void tcg_gen_add2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al, + TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh); +void tcg_gen_sub2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al, + TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh); +void tcg_gen_mulu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_mulsu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags); +void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_abs_i32(TCGv_i32, TCGv_i32); + +/* Replicate a value of size @vece from @in to all the lanes in @out */ +void tcg_gen_dup_i32(unsigned vece, TCGv_i32 out, TCGv_i32 in); + +static inline void tcg_gen_discard_i32(TCGv_i32 arg) +{ + tcg_gen_op1_i32(INDEX_op_discard, arg); +} + +static inline void tcg_gen_mov_i32(TCGv_i32 ret, TCGv_i32 arg) +{ + if (ret != arg) { + tcg_gen_op2_i32(INDEX_op_mov_i32, ret, arg); + } +} + +static inline void tcg_gen_ld8u_i32(TCGv_i32 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_ld8u_i32, ret, arg2, offset); +} + +static inline void tcg_gen_ld8s_i32(TCGv_i32 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_ld8s_i32, ret, arg2, offset); +} + +static inline void tcg_gen_ld16u_i32(TCGv_i32 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_ld16u_i32, ret, arg2, offset); +} + +static inline void tcg_gen_ld16s_i32(TCGv_i32 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_ld16s_i32, ret, arg2, offset); +} + +static inline void tcg_gen_ld_i32(TCGv_i32 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_ld_i32, ret, arg2, offset); +} + +static inline void tcg_gen_st8_i32(TCGv_i32 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_st8_i32, arg1, arg2, offset); +} + +static inline void tcg_gen_st16_i32(TCGv_i32 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_st16_i32, arg1, arg2, offset); +} + +static inline void tcg_gen_st_i32(TCGv_i32 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i32(INDEX_op_st_i32, arg1, arg2, offset); +} + +static inline void tcg_gen_add_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_add_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_sub_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_sub_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_and_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_and_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_or_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_or_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_xor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_xor_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_shl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_shl_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_shr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_shr_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_sar_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_sar_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_mul_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_op3_i32(INDEX_op_mul_i32, ret, arg1, arg2); +} + +static inline void tcg_gen_neg_i32(TCGv_i32 ret, TCGv_i32 arg) +{ + if (TCG_TARGET_HAS_neg_i32) { + tcg_gen_op2_i32(INDEX_op_neg_i32, ret, arg); + } else { + tcg_gen_subfi_i32(ret, 0, arg); + } +} + +static inline void tcg_gen_not_i32(TCGv_i32 ret, TCGv_i32 arg) +{ + if (TCG_TARGET_HAS_not_i32) { + tcg_gen_op2_i32(INDEX_op_not_i32, ret, arg); + } else { + tcg_gen_xori_i32(ret, arg, -1); + } +} + +/* 64 bit ops */ + +void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg); +void tcg_gen_addi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_subfi_i64(TCGv_i64 ret, int64_t arg1, TCGv_i64 arg2); +void tcg_gen_subi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_andi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_ori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_xori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_shli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_shri_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_sari_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_muli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_div_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_rem_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_divu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_remu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_andc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_eqv_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_nand_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_nor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_orc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_clz_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_ctz_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_clzi_i64(TCGv_i64 ret, TCGv_i64 arg1, uint64_t arg2); +void tcg_gen_ctzi_i64(TCGv_i64 ret, TCGv_i64 arg1, uint64_t arg2); +void tcg_gen_clrsb_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ctpop_i64(TCGv_i64 a1, TCGv_i64 a2); +void tcg_gen_rotl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_rotli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_rotr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_rotri_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); +void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2, + unsigned int ofs, unsigned int len); +void tcg_gen_deposit_z_i64(TCGv_i64 ret, TCGv_i64 arg, + unsigned int ofs, unsigned int len); +void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg, + unsigned int ofs, unsigned int len); +void tcg_gen_sextract_i64(TCGv_i64 ret, TCGv_i64 arg, + unsigned int ofs, unsigned int len); +void tcg_gen_extract2_i64(TCGv_i64 ret, TCGv_i64 al, TCGv_i64 ah, + unsigned int ofs); +void tcg_gen_brcond_i64(TCGCond cond, TCGv_i64 arg1, TCGv_i64 arg2, TCGLabel *); +void tcg_gen_brcondi_i64(TCGCond cond, TCGv_i64 arg1, int64_t arg2, TCGLabel *); +void tcg_gen_setcond_i64(TCGCond cond, TCGv_i64 ret, + TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_setcondi_i64(TCGCond cond, TCGv_i64 ret, + TCGv_i64 arg1, int64_t arg2); +void tcg_gen_movcond_i64(TCGCond cond, TCGv_i64 ret, TCGv_i64 c1, + TCGv_i64 c2, TCGv_i64 v1, TCGv_i64 v2); +void tcg_gen_add2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al, + TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh); +void tcg_gen_sub2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al, + TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh); +void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_mulsu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ext8s_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ext16s_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags); +void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags); +void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_abs_i64(TCGv_i64, TCGv_i64); + +/* Replicate a value of size @vece from @in to all the lanes in @out */ +void tcg_gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in); + +#if TCG_TARGET_REG_BITS == 64 +static inline void tcg_gen_discard_i64(TCGv_i64 arg) +{ + tcg_gen_op1_i64(INDEX_op_discard, arg); +} + +static inline void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg) +{ + if (ret != arg) { + tcg_gen_op2_i64(INDEX_op_mov_i64, ret, arg); + } +} + +static inline void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld8u_i64, ret, arg2, offset); +} + +static inline void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld8s_i64, ret, arg2, offset); +} + +static inline void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld16u_i64, ret, arg2, offset); +} + +static inline void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld16s_i64, ret, arg2, offset); +} + +static inline void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld32u_i64, ret, arg2, offset); +} + +static inline void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld32s_i64, ret, arg2, offset); +} + +static inline void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_ld_i64, ret, arg2, offset); +} + +static inline void tcg_gen_st8_i64(TCGv_i64 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_st8_i64, arg1, arg2, offset); +} + +static inline void tcg_gen_st16_i64(TCGv_i64 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_st16_i64, arg1, arg2, offset); +} + +static inline void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_st32_i64, arg1, arg2, offset); +} + +static inline void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, + tcg_target_long offset) +{ + tcg_gen_ldst_op_i64(INDEX_op_st_i64, arg1, arg2, offset); +} + +static inline void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_add_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_sub_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_and_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_or_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_xor_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_shl_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_shr_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_sar_i64, ret, arg1, arg2); +} + +static inline void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_op3_i64(INDEX_op_mul_i64, ret, arg1, arg2); +} +#else /* TCG_TARGET_REG_BITS == 32 */ +void tcg_gen_st8_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_st16_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); + +void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); + +void tcg_gen_discard_i64(TCGv_i64 arg); +void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); +void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); +#endif /* TCG_TARGET_REG_BITS */ + +static inline void tcg_gen_neg_i64(TCGv_i64 ret, TCGv_i64 arg) +{ + if (TCG_TARGET_HAS_neg_i64) { + tcg_gen_op2_i64(INDEX_op_neg_i64, ret, arg); + } else { + tcg_gen_subfi_i64(ret, 0, arg); + } +} + +/* Size changing operations. */ + +void tcg_gen_extu_i32_i64(TCGv_i64 ret, TCGv_i32 arg); +void tcg_gen_ext_i32_i64(TCGv_i64 ret, TCGv_i32 arg); +void tcg_gen_concat_i32_i64(TCGv_i64 dest, TCGv_i32 low, TCGv_i32 high); +void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg); +void tcg_gen_extrh_i64_i32(TCGv_i32 ret, TCGv_i64 arg); +void tcg_gen_extr_i64_i32(TCGv_i32 lo, TCGv_i32 hi, TCGv_i64 arg); +void tcg_gen_extr32_i64(TCGv_i64 lo, TCGv_i64 hi, TCGv_i64 arg); + +void tcg_gen_mov_i128(TCGv_i128 dst, TCGv_i128 src); +void tcg_gen_extr_i128_i64(TCGv_i64 lo, TCGv_i64 hi, TCGv_i128 arg); +void tcg_gen_concat_i64_i128(TCGv_i128 ret, TCGv_i64 lo, TCGv_i64 hi); + +static inline void tcg_gen_concat32_i64(TCGv_i64 ret, TCGv_i64 lo, TCGv_i64 hi) +{ + tcg_gen_deposit_i64(ret, lo, hi, 32, 32); +} + +/* Local load/store bit ops */ + +void tcg_gen_qemu_ld_i32_chk(TCGv_i32, TCGTemp *, TCGArg, MemOp, TCGType); +void tcg_gen_qemu_st_i32_chk(TCGv_i32, TCGTemp *, TCGArg, MemOp, TCGType); +void tcg_gen_qemu_ld_i64_chk(TCGv_i64, TCGTemp *, TCGArg, MemOp, TCGType); +void tcg_gen_qemu_st_i64_chk(TCGv_i64, TCGTemp *, TCGArg, MemOp, TCGType); +void tcg_gen_qemu_ld_i128_chk(TCGv_i128, TCGTemp *, TCGArg, MemOp, TCGType); +void tcg_gen_qemu_st_i128_chk(TCGv_i128, TCGTemp *, TCGArg, MemOp, TCGType); + +/* Atomic ops */ + +void tcg_gen_atomic_cmpxchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_cmpxchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_cmpxchg_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, + TCGv_i128, TCGArg, MemOp, TCGType); + +void tcg_gen_nonatomic_cmpxchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_nonatomic_cmpxchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_nonatomic_cmpxchg_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, + TCGv_i128, TCGArg, MemOp, TCGType); + +void tcg_gen_atomic_xchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_xchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); + +void tcg_gen_atomic_fetch_add_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_add_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_and_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_and_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_or_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_or_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_xor_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_xor_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_smin_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_smin_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_umin_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_umin_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_smax_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_smax_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_umax_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_umax_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); + +void tcg_gen_atomic_add_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_add_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_and_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_and_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_or_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_or_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_xor_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_xor_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_smin_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_smin_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_umin_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_umin_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_smax_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_smax_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_umax_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_umax_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, + TCGArg, MemOp, TCGType); + +/* Vector ops */ + +void tcg_gen_mov_vec(TCGv_vec, TCGv_vec); +void tcg_gen_dup_i32_vec(unsigned vece, TCGv_vec, TCGv_i32); +void tcg_gen_dup_i64_vec(unsigned vece, TCGv_vec, TCGv_i64); +void tcg_gen_dup_mem_vec(unsigned vece, TCGv_vec, TCGv_ptr, tcg_target_long); +void tcg_gen_dupi_vec(unsigned vece, TCGv_vec, uint64_t); +void tcg_gen_add_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_sub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_mul_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_and_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_or_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_xor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_andc_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_orc_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_nand_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_nor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_eqv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_not_vec(unsigned vece, TCGv_vec r, TCGv_vec a); +void tcg_gen_neg_vec(unsigned vece, TCGv_vec r, TCGv_vec a); +void tcg_gen_abs_vec(unsigned vece, TCGv_vec r, TCGv_vec a); +void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_ussub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_smin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_umin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_smax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_umax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); + +void tcg_gen_shli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); +void tcg_gen_shri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); +void tcg_gen_sari_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); +void tcg_gen_rotli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); +void tcg_gen_rotri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); + +void tcg_gen_shls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); +void tcg_gen_shrs_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); +void tcg_gen_sars_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); +void tcg_gen_rotls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); + +void tcg_gen_shlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); +void tcg_gen_shrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); +void tcg_gen_sarv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); +void tcg_gen_rotlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); +void tcg_gen_rotrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); + +void tcg_gen_cmp_vec(TCGCond cond, unsigned vece, TCGv_vec r, + TCGv_vec a, TCGv_vec b); + +void tcg_gen_bitsel_vec(unsigned vece, TCGv_vec r, TCGv_vec a, + TCGv_vec b, TCGv_vec c); +void tcg_gen_cmpsel_vec(TCGCond cond, unsigned vece, TCGv_vec r, + TCGv_vec a, TCGv_vec b, TCGv_vec c, TCGv_vec d); + +void tcg_gen_ld_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset); +void tcg_gen_st_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset); +void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); + +/* Host pointer ops */ + +#if UINTPTR_MAX == UINT32_MAX +# define PTR i32 +# define NAT TCGv_i32 +#else +# define PTR i64 +# define NAT TCGv_i64 +#endif + +static inline void tcg_gen_ld_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t o) +{ + glue(tcg_gen_ld_,PTR)((NAT)r, a, o); +} + +static inline void tcg_gen_st_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t o) +{ + glue(tcg_gen_st_, PTR)((NAT)r, a, o); +} + +static inline void tcg_gen_discard_ptr(TCGv_ptr a) +{ + glue(tcg_gen_discard_,PTR)((NAT)a); +} + +static inline void tcg_gen_add_ptr(TCGv_ptr r, TCGv_ptr a, TCGv_ptr b) +{ + glue(tcg_gen_add_,PTR)((NAT)r, (NAT)a, (NAT)b); +} + +static inline void tcg_gen_addi_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t b) +{ + glue(tcg_gen_addi_,PTR)((NAT)r, (NAT)a, b); +} + +static inline void tcg_gen_mov_ptr(TCGv_ptr d, TCGv_ptr s) +{ + glue(tcg_gen_mov_,PTR)((NAT)d, (NAT)s); +} + +static inline void tcg_gen_movi_ptr(TCGv_ptr d, intptr_t s) +{ + glue(tcg_gen_movi_,PTR)((NAT)d, s); +} + +static inline void tcg_gen_brcondi_ptr(TCGCond cond, TCGv_ptr a, + intptr_t b, TCGLabel *label) +{ + glue(tcg_gen_brcondi_,PTR)(cond, (NAT)a, b, label); +} + +static inline void tcg_gen_ext_i32_ptr(TCGv_ptr r, TCGv_i32 a) +{ +#if UINTPTR_MAX == UINT32_MAX + tcg_gen_mov_i32((NAT)r, a); +#else + tcg_gen_ext_i32_i64((NAT)r, a); +#endif +} + +static inline void tcg_gen_trunc_i64_ptr(TCGv_ptr r, TCGv_i64 a) +{ +#if UINTPTR_MAX == UINT32_MAX + tcg_gen_extrl_i64_i32((NAT)r, a); +#else + tcg_gen_mov_i64((NAT)r, a); +#endif +} + +static inline void tcg_gen_extu_ptr_i64(TCGv_i64 r, TCGv_ptr a) +{ +#if UINTPTR_MAX == UINT32_MAX + tcg_gen_extu_i32_i64(r, (NAT)a); +#else + tcg_gen_mov_i64(r, (NAT)a); +#endif +} + +static inline void tcg_gen_trunc_ptr_i32(TCGv_i32 r, TCGv_ptr a) +{ +#if UINTPTR_MAX == UINT32_MAX + tcg_gen_mov_i32(r, (NAT)a); +#else + tcg_gen_extrl_i64_i32(r, (NAT)a); +#endif +} + +#undef PTR +#undef NAT + +#endif /* TCG_TCG_OP_COMMON_H */ diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ /* - * Tiny Code Generator for QEMU + * Target dependent opcode generation functions. * * Copyright (c) 2008 Fabrice Bellard - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. */ #ifndef TCG_TCG_OP_H #define TCG_TCG_OP_H -#include "tcg/tcg.h" -#include "exec/helper-proto.h" -#include "exec/helper-gen.h" - -/* Basic output routines. Not for general consumption. */ - -void tcg_gen_op1(TCGOpcode, TCGArg); -void tcg_gen_op2(TCGOpcode, TCGArg, TCGArg); -void tcg_gen_op3(TCGOpcode, TCGArg, TCGArg, TCGArg); -void tcg_gen_op4(TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg); -void tcg_gen_op5(TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg, TCGArg); -void tcg_gen_op6(TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg, TCGArg, TCGArg); - -void vec_gen_2(TCGOpcode, TCGType, unsigned, TCGArg, TCGArg); -void vec_gen_3(TCGOpcode, TCGType, unsigned, TCGArg, TCGArg, TCGArg); -void vec_gen_4(TCGOpcode, TCGType, unsigned, TCGArg, TCGArg, TCGArg, TCGArg); - -static inline void tcg_gen_op1_i32(TCGOpcode opc, TCGv_i32 a1) -{ - tcg_gen_op1(opc, tcgv_i32_arg(a1)); -} - -static inline void tcg_gen_op1_i64(TCGOpcode opc, TCGv_i64 a1) -{ - tcg_gen_op1(opc, tcgv_i64_arg(a1)); -} - -static inline void tcg_gen_op1i(TCGOpcode opc, TCGArg a1) -{ - tcg_gen_op1(opc, a1); -} - -static inline void tcg_gen_op2_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2) -{ - tcg_gen_op2(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2)); -} - -static inline void tcg_gen_op2_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2) -{ - tcg_gen_op2(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2)); -} - -static inline void tcg_gen_op2i_i32(TCGOpcode opc, TCGv_i32 a1, TCGArg a2) -{ - tcg_gen_op2(opc, tcgv_i32_arg(a1), a2); -} - -static inline void tcg_gen_op2i_i64(TCGOpcode opc, TCGv_i64 a1, TCGArg a2) -{ - tcg_gen_op2(opc, tcgv_i64_arg(a1), a2); -} - -static inline void tcg_gen_op2ii(TCGOpcode opc, TCGArg a1, TCGArg a2) -{ - tcg_gen_op2(opc, a1, a2); -} - -static inline void tcg_gen_op3_i32(TCGOpcode opc, TCGv_i32 a1, - TCGv_i32 a2, TCGv_i32 a3) -{ - tcg_gen_op3(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), tcgv_i32_arg(a3)); -} - -static inline void tcg_gen_op3_i64(TCGOpcode opc, TCGv_i64 a1, - TCGv_i64 a2, TCGv_i64 a3) -{ - tcg_gen_op3(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), tcgv_i64_arg(a3)); -} - -static inline void tcg_gen_op3i_i32(TCGOpcode opc, TCGv_i32 a1, - TCGv_i32 a2, TCGArg a3) -{ - tcg_gen_op3(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), a3); -} - -static inline void tcg_gen_op3i_i64(TCGOpcode opc, TCGv_i64 a1, - TCGv_i64 a2, TCGArg a3) -{ - tcg_gen_op3(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), a3); -} - -static inline void tcg_gen_ldst_op_i32(TCGOpcode opc, TCGv_i32 val, - TCGv_ptr base, TCGArg offset) -{ - tcg_gen_op3(opc, tcgv_i32_arg(val), tcgv_ptr_arg(base), offset); -} - -static inline void tcg_gen_ldst_op_i64(TCGOpcode opc, TCGv_i64 val, - TCGv_ptr base, TCGArg offset) -{ - tcg_gen_op3(opc, tcgv_i64_arg(val), tcgv_ptr_arg(base), offset); -} - -static inline void tcg_gen_op4_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGv_i32 a4) -{ - tcg_gen_op4(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), tcgv_i32_arg(a4)); -} - -static inline void tcg_gen_op4_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGv_i64 a4) -{ - tcg_gen_op4(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), tcgv_i64_arg(a4)); -} - -static inline void tcg_gen_op4i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGArg a4) -{ - tcg_gen_op4(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), a4); -} - -static inline void tcg_gen_op4i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGArg a4) -{ - tcg_gen_op4(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), a4); -} - -static inline void tcg_gen_op4ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGArg a3, TCGArg a4) -{ - tcg_gen_op4(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), a3, a4); -} - -static inline void tcg_gen_op4ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGArg a3, TCGArg a4) -{ - tcg_gen_op4(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), a3, a4); -} - -static inline void tcg_gen_op5_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGv_i32 a4, TCGv_i32 a5) -{ - tcg_gen_op5(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), tcgv_i32_arg(a4), tcgv_i32_arg(a5)); -} - -static inline void tcg_gen_op5_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGv_i64 a4, TCGv_i64 a5) -{ - tcg_gen_op5(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), tcgv_i64_arg(a4), tcgv_i64_arg(a5)); -} - -static inline void tcg_gen_op5i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGv_i32 a4, TCGArg a5) -{ - tcg_gen_op5(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), tcgv_i32_arg(a4), a5); -} - -static inline void tcg_gen_op5i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGv_i64 a4, TCGArg a5) -{ - tcg_gen_op5(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), tcgv_i64_arg(a4), a5); -} - -static inline void tcg_gen_op5ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGArg a4, TCGArg a5) -{ - tcg_gen_op5(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), a4, a5); -} - -static inline void tcg_gen_op5ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGArg a4, TCGArg a5) -{ - tcg_gen_op5(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), a4, a5); -} - -static inline void tcg_gen_op6_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGv_i32 a4, - TCGv_i32 a5, TCGv_i32 a6) -{ - tcg_gen_op6(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), tcgv_i32_arg(a4), tcgv_i32_arg(a5), - tcgv_i32_arg(a6)); -} - -static inline void tcg_gen_op6_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGv_i64 a4, - TCGv_i64 a5, TCGv_i64 a6) -{ - tcg_gen_op6(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), tcgv_i64_arg(a4), tcgv_i64_arg(a5), - tcgv_i64_arg(a6)); -} - -static inline void tcg_gen_op6i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGv_i32 a4, - TCGv_i32 a5, TCGArg a6) -{ - tcg_gen_op6(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), tcgv_i32_arg(a4), tcgv_i32_arg(a5), a6); -} - -static inline void tcg_gen_op6i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGv_i64 a4, - TCGv_i64 a5, TCGArg a6) -{ - tcg_gen_op6(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), tcgv_i64_arg(a4), tcgv_i64_arg(a5), a6); -} - -static inline void tcg_gen_op6ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2, - TCGv_i32 a3, TCGv_i32 a4, - TCGArg a5, TCGArg a6) -{ - tcg_gen_op6(opc, tcgv_i32_arg(a1), tcgv_i32_arg(a2), - tcgv_i32_arg(a3), tcgv_i32_arg(a4), a5, a6); -} - -static inline void tcg_gen_op6ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2, - TCGv_i64 a3, TCGv_i64 a4, - TCGArg a5, TCGArg a6) -{ - tcg_gen_op6(opc, tcgv_i64_arg(a1), tcgv_i64_arg(a2), - tcgv_i64_arg(a3), tcgv_i64_arg(a4), a5, a6); -} - - -/* Generic ops. */ - -static inline void gen_set_label(TCGLabel *l) -{ - l->present = 1; - tcg_gen_op1(INDEX_op_set_label, label_arg(l)); -} - -void tcg_gen_br(TCGLabel *l); -void tcg_gen_mb(TCGBar); - -/* Helper calls. */ - -/* 32 bit ops */ - -void tcg_gen_movi_i32(TCGv_i32 ret, int32_t arg); -void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_subfi_i32(TCGv_i32 ret, int32_t arg1, TCGv_i32 arg2); -void tcg_gen_subi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_andi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_ori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_xori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_shli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_shri_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_sari_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_muli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_div_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_rem_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_divu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_remu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_andc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_eqv_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_nand_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_nor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_orc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_clz_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_ctz_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_clzi_i32(TCGv_i32 ret, TCGv_i32 arg1, uint32_t arg2); -void tcg_gen_ctzi_i32(TCGv_i32 ret, TCGv_i32 arg1, uint32_t arg2); -void tcg_gen_clrsb_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_ctpop_i32(TCGv_i32 a1, TCGv_i32 a2); -void tcg_gen_rotl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_rotli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_rotr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_rotri_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2); -void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2, - unsigned int ofs, unsigned int len); -void tcg_gen_deposit_z_i32(TCGv_i32 ret, TCGv_i32 arg, - unsigned int ofs, unsigned int len); -void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg, - unsigned int ofs, unsigned int len); -void tcg_gen_sextract_i32(TCGv_i32 ret, TCGv_i32 arg, - unsigned int ofs, unsigned int len); -void tcg_gen_extract2_i32(TCGv_i32 ret, TCGv_i32 al, TCGv_i32 ah, - unsigned int ofs); -void tcg_gen_brcond_i32(TCGCond cond, TCGv_i32 arg1, TCGv_i32 arg2, TCGLabel *); -void tcg_gen_brcondi_i32(TCGCond cond, TCGv_i32 arg1, int32_t arg2, TCGLabel *); -void tcg_gen_setcond_i32(TCGCond cond, TCGv_i32 ret, - TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_setcondi_i32(TCGCond cond, TCGv_i32 ret, - TCGv_i32 arg1, int32_t arg2); -void tcg_gen_movcond_i32(TCGCond cond, TCGv_i32 ret, TCGv_i32 c1, - TCGv_i32 c2, TCGv_i32 v1, TCGv_i32 v2); -void tcg_gen_add2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al, - TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh); -void tcg_gen_sub2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al, - TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh); -void tcg_gen_mulu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_mulsu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags); -void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); -void tcg_gen_abs_i32(TCGv_i32, TCGv_i32); - -/* Replicate a value of size @vece from @in to all the lanes in @out */ -void tcg_gen_dup_i32(unsigned vece, TCGv_i32 out, TCGv_i32 in); - -static inline void tcg_gen_discard_i32(TCGv_i32 arg) -{ - tcg_gen_op1_i32(INDEX_op_discard, arg); -} - -static inline void tcg_gen_mov_i32(TCGv_i32 ret, TCGv_i32 arg) -{ - if (ret != arg) { - tcg_gen_op2_i32(INDEX_op_mov_i32, ret, arg); - } -} - -static inline void tcg_gen_ld8u_i32(TCGv_i32 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_ld8u_i32, ret, arg2, offset); -} - -static inline void tcg_gen_ld8s_i32(TCGv_i32 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_ld8s_i32, ret, arg2, offset); -} - -static inline void tcg_gen_ld16u_i32(TCGv_i32 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_ld16u_i32, ret, arg2, offset); -} - -static inline void tcg_gen_ld16s_i32(TCGv_i32 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_ld16s_i32, ret, arg2, offset); -} - -static inline void tcg_gen_ld_i32(TCGv_i32 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_ld_i32, ret, arg2, offset); -} - -static inline void tcg_gen_st8_i32(TCGv_i32 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_st8_i32, arg1, arg2, offset); -} - -static inline void tcg_gen_st16_i32(TCGv_i32 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_st16_i32, arg1, arg2, offset); -} - -static inline void tcg_gen_st_i32(TCGv_i32 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i32(INDEX_op_st_i32, arg1, arg2, offset); -} - -static inline void tcg_gen_add_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_add_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_sub_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_sub_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_and_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_and_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_or_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_or_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_xor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_xor_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_shl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_shl_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_shr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_shr_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_sar_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_sar_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_mul_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) -{ - tcg_gen_op3_i32(INDEX_op_mul_i32, ret, arg1, arg2); -} - -static inline void tcg_gen_neg_i32(TCGv_i32 ret, TCGv_i32 arg) -{ - if (TCG_TARGET_HAS_neg_i32) { - tcg_gen_op2_i32(INDEX_op_neg_i32, ret, arg); - } else { - tcg_gen_subfi_i32(ret, 0, arg); - } -} - -static inline void tcg_gen_not_i32(TCGv_i32 ret, TCGv_i32 arg) -{ - if (TCG_TARGET_HAS_not_i32) { - tcg_gen_op2_i32(INDEX_op_not_i32, ret, arg); - } else { - tcg_gen_xori_i32(ret, arg, -1); - } -} - -/* 64 bit ops */ - -void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg); -void tcg_gen_addi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_subfi_i64(TCGv_i64 ret, int64_t arg1, TCGv_i64 arg2); -void tcg_gen_subi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_andi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_ori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_xori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_shli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_shri_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_sari_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_muli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_div_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_rem_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_divu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_remu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_andc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_eqv_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_nand_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_nor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_orc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_clz_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_ctz_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_clzi_i64(TCGv_i64 ret, TCGv_i64 arg1, uint64_t arg2); -void tcg_gen_ctzi_i64(TCGv_i64 ret, TCGv_i64 arg1, uint64_t arg2); -void tcg_gen_clrsb_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ctpop_i64(TCGv_i64 a1, TCGv_i64 a2); -void tcg_gen_rotl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_rotli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_rotr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_rotri_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2); -void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2, - unsigned int ofs, unsigned int len); -void tcg_gen_deposit_z_i64(TCGv_i64 ret, TCGv_i64 arg, - unsigned int ofs, unsigned int len); -void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg, - unsigned int ofs, unsigned int len); -void tcg_gen_sextract_i64(TCGv_i64 ret, TCGv_i64 arg, - unsigned int ofs, unsigned int len); -void tcg_gen_extract2_i64(TCGv_i64 ret, TCGv_i64 al, TCGv_i64 ah, - unsigned int ofs); -void tcg_gen_brcond_i64(TCGCond cond, TCGv_i64 arg1, TCGv_i64 arg2, TCGLabel *); -void tcg_gen_brcondi_i64(TCGCond cond, TCGv_i64 arg1, int64_t arg2, TCGLabel *); -void tcg_gen_setcond_i64(TCGCond cond, TCGv_i64 ret, - TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_setcondi_i64(TCGCond cond, TCGv_i64 ret, - TCGv_i64 arg1, int64_t arg2); -void tcg_gen_movcond_i64(TCGCond cond, TCGv_i64 ret, TCGv_i64 c1, - TCGv_i64 c2, TCGv_i64 v1, TCGv_i64 v2); -void tcg_gen_add2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al, - TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh); -void tcg_gen_sub2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al, - TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh); -void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_mulsu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ext8s_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ext16s_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags); -void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags); -void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_abs_i64(TCGv_i64, TCGv_i64); - -/* Replicate a value of size @vece from @in to all the lanes in @out */ -void tcg_gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in); - -#if TCG_TARGET_REG_BITS == 64 -static inline void tcg_gen_discard_i64(TCGv_i64 arg) -{ - tcg_gen_op1_i64(INDEX_op_discard, arg); -} - -static inline void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg) -{ - if (ret != arg) { - tcg_gen_op2_i64(INDEX_op_mov_i64, ret, arg); - } -} - -static inline void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld8u_i64, ret, arg2, offset); -} - -static inline void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld8s_i64, ret, arg2, offset); -} - -static inline void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld16u_i64, ret, arg2, offset); -} - -static inline void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld16s_i64, ret, arg2, offset); -} - -static inline void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld32u_i64, ret, arg2, offset); -} - -static inline void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld32s_i64, ret, arg2, offset); -} - -static inline void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_ld_i64, ret, arg2, offset); -} - -static inline void tcg_gen_st8_i64(TCGv_i64 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_st8_i64, arg1, arg2, offset); -} - -static inline void tcg_gen_st16_i64(TCGv_i64 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_st16_i64, arg1, arg2, offset); -} - -static inline void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_st32_i64, arg1, arg2, offset); -} - -static inline void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, - tcg_target_long offset) -{ - tcg_gen_ldst_op_i64(INDEX_op_st_i64, arg1, arg2, offset); -} - -static inline void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_add_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_sub_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_and_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_or_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_xor_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_shl_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_shr_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_sar_i64, ret, arg1, arg2); -} - -static inline void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) -{ - tcg_gen_op3_i64(INDEX_op_mul_i64, ret, arg1, arg2); -} -#else /* TCG_TARGET_REG_BITS == 32 */ -void tcg_gen_st8_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_st16_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); - -void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); - -void tcg_gen_discard_i64(TCGv_i64 arg); -void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); -void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2); -#endif /* TCG_TARGET_REG_BITS */ - -static inline void tcg_gen_neg_i64(TCGv_i64 ret, TCGv_i64 arg) -{ - if (TCG_TARGET_HAS_neg_i64) { - tcg_gen_op2_i64(INDEX_op_neg_i64, ret, arg); - } else { - tcg_gen_subfi_i64(ret, 0, arg); - } -} - -/* Size changing operations. */ - -void tcg_gen_extu_i32_i64(TCGv_i64 ret, TCGv_i32 arg); -void tcg_gen_ext_i32_i64(TCGv_i64 ret, TCGv_i32 arg); -void tcg_gen_concat_i32_i64(TCGv_i64 dest, TCGv_i32 low, TCGv_i32 high); -void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg); -void tcg_gen_extrh_i64_i32(TCGv_i32 ret, TCGv_i64 arg); -void tcg_gen_extr_i64_i32(TCGv_i32 lo, TCGv_i32 hi, TCGv_i64 arg); -void tcg_gen_extr32_i64(TCGv_i64 lo, TCGv_i64 hi, TCGv_i64 arg); - -void tcg_gen_mov_i128(TCGv_i128 dst, TCGv_i128 src); -void tcg_gen_extr_i128_i64(TCGv_i64 lo, TCGv_i64 hi, TCGv_i128 arg); -void tcg_gen_concat_i64_i128(TCGv_i128 ret, TCGv_i64 lo, TCGv_i64 hi); - -static inline void tcg_gen_concat32_i64(TCGv_i64 ret, TCGv_i64 lo, TCGv_i64 hi) -{ - tcg_gen_deposit_i64(ret, lo, hi, 32, 32); -} - -/* QEMU specific operations. */ +#include "tcg/tcg-op-common.h" #ifndef TARGET_LONG_BITS #error must include QEMU headers @@ -XXX,XX +XXX,XX @@ static inline void tcg_gen_insn_start(target_ulong pc, target_ulong a1, # error "Unhandled number of operands to insn_start" #endif -/** - * tcg_gen_exit_tb() - output exit_tb TCG operation - * @tb: The TranslationBlock from which we are exiting - * @idx: Direct jump slot index, or exit request - * - * See tcg/README for more info about this TCG operation. - * See also tcg.h and the block comment above TB_EXIT_MASK. - * - * For a normal exit from the TB, back to the main loop, @tb should - * be NULL and @idx should be 0. Otherwise, @tb should be valid and - * @idx should be one of the TB_EXIT_ values. - */ -void tcg_gen_exit_tb(const TranslationBlock *tb, unsigned idx); - -/** - * tcg_gen_goto_tb() - output goto_tb TCG operation - * @idx: Direct jump slot index (0 or 1) - * - * See tcg/README for more info about this TCG operation. - * - * NOTE: In softmmu emulation, direct jumps with goto_tb are only safe within - * the pages this TB resides in because we don't take care of direct jumps when - * address mapping changes, e.g. in tlb_flush(). In user mode, there's only a - * static address translation, so the destination address is always valid, TBs - * are always invalidated properly, and direct jumps are reset when mapping - * changes. - */ -void tcg_gen_goto_tb(unsigned idx); - -/** - * tcg_gen_lookup_and_goto_ptr() - look up the current TB, jump to it if valid - * @addr: Guest address of the target TB - * - * If the TB is not valid, jump to the epilogue. - * - * This operation is optional. If the TCG backend does not implement goto_ptr, - * this op is equivalent to calling tcg_gen_exit_tb() with 0 as the argument. - */ -void tcg_gen_lookup_and_goto_ptr(void); - -static inline void tcg_gen_plugin_cb_start(unsigned from, unsigned type, - unsigned wr) -{ - tcg_gen_op3(INDEX_op_plugin_cb_start, from, type, wr); -} - -static inline void tcg_gen_plugin_cb_end(void) -{ - tcg_emit_op(INDEX_op_plugin_cb_end, 0); -} - #if TARGET_LONG_BITS == 32 typedef TCGv_i32 TCGv; #define tcg_temp_new() tcg_temp_new_i32() @@ -XXX,XX +XXX,XX @@ typedef TCGv_i64 TCGv; #error Unhandled TARGET_LONG_BITS value #endif -void tcg_gen_qemu_ld_i32_chk(TCGv_i32, TCGTemp *, TCGArg, MemOp, TCGType); -void tcg_gen_qemu_st_i32_chk(TCGv_i32, TCGTemp *, TCGArg, MemOp, TCGType); -void tcg_gen_qemu_ld_i64_chk(TCGv_i64, TCGTemp *, TCGArg, MemOp, TCGType); -void tcg_gen_qemu_st_i64_chk(TCGv_i64, TCGTemp *, TCGArg, MemOp, TCGType); -void tcg_gen_qemu_ld_i128_chk(TCGv_i128, TCGTemp *, TCGArg, MemOp, TCGType); -void tcg_gen_qemu_st_i128_chk(TCGv_i128, TCGTemp *, TCGArg, MemOp, TCGType); - static inline void tcg_gen_qemu_ld_i32(TCGv_i32 v, TCGv a, TCGArg i, MemOp m) { @@ -XXX,XX +XXX,XX @@ tcg_gen_qemu_st_i128(TCGv_i128 v, TCGv a, TCGArg i, MemOp m) tcg_gen_qemu_st_i128_chk(v, tcgv_tl_temp(a), i, m, TCG_TYPE_TL); } -void tcg_gen_atomic_cmpxchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_cmpxchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_cmpxchg_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, - TCGv_i128, TCGArg, MemOp, TCGType); - -void tcg_gen_nonatomic_cmpxchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_nonatomic_cmpxchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_nonatomic_cmpxchg_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, - TCGv_i128, TCGArg, MemOp, TCGType); - -void tcg_gen_atomic_xchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_xchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); - -void tcg_gen_atomic_fetch_add_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_add_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_and_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_and_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_or_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_or_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_xor_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_xor_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_smin_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_smin_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_umin_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_umin_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_smax_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_smax_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_umax_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_fetch_umax_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); - -void tcg_gen_atomic_add_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_add_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_and_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_and_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_or_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_or_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_xor_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_xor_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_smin_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_smin_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_umin_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_umin_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_smax_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_smax_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_umax_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, - TCGArg, MemOp, TCGType); -void tcg_gen_atomic_umax_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, - TCGArg, MemOp, TCGType); - #define DEF_ATOMIC2(N, S) \ static inline void N##_##S(TCGv_##S r, TCGv a, TCGv_##S v, \ TCGArg i, MemOp m) \ @@ -XXX,XX +XXX,XX @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64) #undef DEF_ATOMIC2 #undef DEF_ATOMIC3 -void tcg_gen_mov_vec(TCGv_vec, TCGv_vec); -void tcg_gen_dup_i32_vec(unsigned vece, TCGv_vec, TCGv_i32); -void tcg_gen_dup_i64_vec(unsigned vece, TCGv_vec, TCGv_i64); -void tcg_gen_dup_mem_vec(unsigned vece, TCGv_vec, TCGv_ptr, tcg_target_long); -void tcg_gen_dupi_vec(unsigned vece, TCGv_vec, uint64_t); -void tcg_gen_add_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_sub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_mul_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_and_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_or_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_xor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_andc_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_orc_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_nand_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_nor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_eqv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_not_vec(unsigned vece, TCGv_vec r, TCGv_vec a); -void tcg_gen_neg_vec(unsigned vece, TCGv_vec r, TCGv_vec a); -void tcg_gen_abs_vec(unsigned vece, TCGv_vec r, TCGv_vec a); -void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_ussub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_smin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_umin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_smax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); -void tcg_gen_umax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); - -void tcg_gen_shli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); -void tcg_gen_shri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); -void tcg_gen_sari_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); -void tcg_gen_rotli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); -void tcg_gen_rotri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); - -void tcg_gen_shls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); -void tcg_gen_shrs_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); -void tcg_gen_sars_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); -void tcg_gen_rotls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s); - -void tcg_gen_shlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); -void tcg_gen_shrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); -void tcg_gen_sarv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); -void tcg_gen_rotlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); -void tcg_gen_rotrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s); - -void tcg_gen_cmp_vec(TCGCond cond, unsigned vece, TCGv_vec r, - TCGv_vec a, TCGv_vec b); - -void tcg_gen_bitsel_vec(unsigned vece, TCGv_vec r, TCGv_vec a, - TCGv_vec b, TCGv_vec c); -void tcg_gen_cmpsel_vec(TCGCond cond, unsigned vece, TCGv_vec r, - TCGv_vec a, TCGv_vec b, TCGv_vec c, TCGv_vec d); - -void tcg_gen_ld_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset); -void tcg_gen_st_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset); -void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); - #if TARGET_LONG_BITS == 64 #define tcg_gen_movi_tl tcg_gen_movi_i64 #define tcg_gen_mov_tl tcg_gen_mov_i64 @@ -XXX,XX +XXX,XX @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); : (VECE) == MO_32 ? 0x00000001ul * (uint32_t)(C) \ : (qemu_build_not_reached_always(), 0)) \ : (target_long)dup_const(VECE, C)) -#endif - -#if UINTPTR_MAX == UINT32_MAX -# define PTR i32 -# define NAT TCGv_i32 -#else -# define PTR i64 -# define NAT TCGv_i64 -#endif - -static inline void tcg_gen_ld_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t o) -{ - glue(tcg_gen_ld_,PTR)((NAT)r, a, o); -} - -static inline void tcg_gen_st_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t o) -{ - glue(tcg_gen_st_, PTR)((NAT)r, a, o); -} - -static inline void tcg_gen_discard_ptr(TCGv_ptr a) -{ - glue(tcg_gen_discard_,PTR)((NAT)a); -} - -static inline void tcg_gen_add_ptr(TCGv_ptr r, TCGv_ptr a, TCGv_ptr b) -{ - glue(tcg_gen_add_,PTR)((NAT)r, (NAT)a, (NAT)b); -} - -static inline void tcg_gen_addi_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t b) -{ - glue(tcg_gen_addi_,PTR)((NAT)r, (NAT)a, b); -} - -static inline void tcg_gen_mov_ptr(TCGv_ptr d, TCGv_ptr s) -{ - glue(tcg_gen_mov_,PTR)((NAT)d, (NAT)s); -} - -static inline void tcg_gen_movi_ptr(TCGv_ptr d, intptr_t s) -{ - glue(tcg_gen_movi_,PTR)((NAT)d, s); -} - -static inline void tcg_gen_brcondi_ptr(TCGCond cond, TCGv_ptr a, - intptr_t b, TCGLabel *label) -{ - glue(tcg_gen_brcondi_,PTR)(cond, (NAT)a, b, label); -} - -static inline void tcg_gen_ext_i32_ptr(TCGv_ptr r, TCGv_i32 a) -{ -#if UINTPTR_MAX == UINT32_MAX - tcg_gen_mov_i32((NAT)r, a); -#else - tcg_gen_ext_i32_i64((NAT)r, a); -#endif -} - -static inline void tcg_gen_trunc_i64_ptr(TCGv_ptr r, TCGv_i64 a) -{ -#if UINTPTR_MAX == UINT32_MAX - tcg_gen_extrl_i64_i32((NAT)r, a); -#else - tcg_gen_mov_i64((NAT)r, a); -#endif -} - -static inline void tcg_gen_extu_ptr_i64(TCGv_i64 r, TCGv_ptr a) -{ -#if UINTPTR_MAX == UINT32_MAX - tcg_gen_extu_i32_i64(r, (NAT)a); -#else - tcg_gen_mov_i64(r, (NAT)a); -#endif -} - -static inline void tcg_gen_trunc_ptr_i32(TCGv_i32 r, TCGv_ptr a) -{ -#if UINTPTR_MAX == UINT32_MAX - tcg_gen_mov_i32(r, (NAT)a); -#else - tcg_gen_extrl_i64_i32(r, (NAT)a); -#endif -} - -#undef PTR -#undef NAT +#endif /* TARGET_LONG_BITS == 64 */ #endif /* TCG_TCG_OP_H */ diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/int128.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg-op-common.h" #include "tcg-internal.h" #define CASE_OP_32_64(x) \ diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg-op-common.h" #include "tcg/tcg-op-gvec.h" #include "tcg/tcg-gvec-desc.h" diff --git a/tcg/tcg-op-ldst.c b/tcg/tcg-op-ldst.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-ldst.c +++ b/tcg/tcg-op-ldst.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg-op-common.h" #include "tcg/tcg-mo.h" #include "exec/plugin-gen.h" #include "tcg-internal.h" diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-vec.c +++ b/tcg/tcg-op-vec.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg-op-common.h" #include "tcg/tcg-mo.h" #include "tcg-internal.h" diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg-op-common.h" #include "exec/plugin-gen.h" #include "tcg-internal.h" diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "exec/tlb-common.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg-op-common.h" #if UINTPTR_MAX == UINT32_MAX # define ELF_CLASS ELFCLASS32 diff --git a/tcg/tci.c b/tcg/tci.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tci.c +++ b/tcg/tci.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "exec/cpu_ldst.h" -#include "tcg/tcg-op.h" +#include "tcg/tcg.h" #include "tcg/tcg-ldst.h" #include <ffi.h> -- 2.34.1 This had been included via tcg-op-common.h via tcg-op.h, but that is going away. It is needed for inlines within translator.h, so we might as well do it there and not individually in each translator c file. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/translate.h | 1 + target/arm/tcg/translate-a64.c | 2 -- target/arm/tcg/translate-sme.c | 1 - target/arm/tcg/translate-sve.c | 2 -- target/arm/tcg/translate.c | 2 -- 5 files changed, 1 insertion(+), 7 deletions(-) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ #define TARGET_ARM_TRANSLATE_H #include "exec/translator.h" +#include "exec/helper-gen.h" #include "internals.h" diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ #include "qemu/host-utils.h" #include "semihosting/semihost.h" #include "exec/gen-icount.h" -#include "exec/helper-proto.h" -#include "exec/helper-gen.h" #include "exec/log.h" #include "cpregs.h" #include "translate-a64.h" diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sme.c +++ b/target/arm/tcg/translate-sme.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-op-gvec.h" #include "tcg/tcg-gvec-desc.h" #include "translate.h" -#include "exec/helper-gen.h" #include "translate-a64.h" #include "fpu/softfloat.h" diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ #include "arm_ldst.h" #include "translate.h" #include "internals.h" -#include "exec/helper-proto.h" -#include "exec/helper-gen.h" #include "exec/log.h" #include "translate-a64.h" #include "fpu/softfloat.h" diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "qemu/bitops.h" #include "arm_ldst.h" #include "semihosting/semihost.h" -#include "exec/helper-proto.h" -#include "exec/helper-gen.h" #include "exec/log.h" #include "cpregs.h" -- 2.34.1 This had been included via tcg-op-common.h via tcg-op.h, but that is going away. In idef-parser.y, shuffle some tcg related includes into a more logical order. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/genptr.c | 1 + target/hexagon/translate.c | 1 + target/hexagon/idef-parser/idef-parser.y | 3 ++- 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/genptr.c +++ b/target/hexagon/genptr.c @@ -XXX,XX +XXX,XX @@ #include "internal.h" #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" +#include "exec/helper-gen.h" #include "insn.h" #include "opcodes.h" #include "translate.h" diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" +#include "exec/helper-gen.h" #include "exec/cpu_ldst.h" #include "exec/log.h" #include "internal.h" diff --git a/target/hexagon/idef-parser/idef-parser.y b/target/hexagon/idef-parser/idef-parser.y index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/idef-parser/idef-parser.y +++ b/target/hexagon/idef-parser/idef-parser.y @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) fputs("#include \"qemu/log.h\"\n", output_file); fputs("#include \"cpu.h\"\n", output_file); fputs("#include \"internal.h\"\n", output_file); + fputs("#include \"tcg/tcg.h\"\n", output_file); fputs("#include \"tcg/tcg-op.h\"\n", output_file); + fputs("#include \"exec/helper-gen.h\"\n", output_file); fputs("#include \"insn.h\"\n", output_file); fputs("#include \"opcodes.h\"\n", output_file); fputs("#include \"translate.h\"\n", output_file); fputs("#define QEMU_GENERATE\n", output_file); fputs("#include \"genptr.h\"\n", output_file); - fputs("#include \"tcg/tcg.h\"\n", output_file); fputs("#include \"macros.h\"\n", output_file); fprintf(output_file, "#include \"%s\"\n", argv[ARG_INDEX_EMITTER_H]); -- 2.34.1 Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/helper-head.h | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -XXX,XX +XXX,XX @@ -/* Helper file for declaring TCG helper functions. - Used by other helper files. - - Targets should use DEF_HELPER_N and DEF_HELPER_FLAGS_N to declare helper - functions. Names should be specified without the helper_ prefix, and - the return and argument types specified. 3 basic types are understood - (i32, i64 and ptr). Additional aliases are provided for convenience and - to match the types used by the C helper implementation. - - The target helper.h should be included in all files that use/define - helper functions. THis will ensure that function prototypes are - consistent. In addition it should be included an extra two times for - helper.c, defining: - GEN_HELPER 1 to produce op generation functions (gen_helper_*) - GEN_HELPER 2 to do runtime registration helper functions. +/* + * Helper file for declaring TCG helper functions. + * Used by other helper files. */ #ifndef EXEC_HELPER_HEAD_H -- 2.34.1 This will be required outside of tcg-internal.h soon. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/helper-info.h | 59 +++++++++++++++++++++++++++++++++++++++ tcg/tcg-internal.h | 47 +------------------------------ 2 files changed, 60 insertions(+), 46 deletions(-) create mode 100644 include/tcg/helper-info.h diff --git a/include/tcg/helper-info.h b/include/tcg/helper-info.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/tcg/helper-info.h @@ -XXX,XX +XXX,XX @@ +/* + * TCG Helper Infomation Structure + * + * Copyright (c) 2023 Linaro Ltd + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef TCG_HELPER_INFO_H +#define TCG_HELPER_INFO_H + +#ifdef CONFIG_TCG_INTERPRETER +#include <ffi.h> +#endif + +/* + * Describe the calling convention of a given argument type. + */ +typedef enum { + TCG_CALL_RET_NORMAL, /* by registers */ + TCG_CALL_RET_BY_REF, /* for i128, by reference */ + TCG_CALL_RET_BY_VEC, /* for i128, by vector register */ +} TCGCallReturnKind; + +typedef enum { + TCG_CALL_ARG_NORMAL, /* by registers (continuing onto stack) */ + TCG_CALL_ARG_EVEN, /* like normal, but skipping odd slots */ + TCG_CALL_ARG_EXTEND, /* for i32, as a sign/zero-extended i64 */ + TCG_CALL_ARG_EXTEND_U, /* ... as a zero-extended i64 */ + TCG_CALL_ARG_EXTEND_S, /* ... as a sign-extended i64 */ + TCG_CALL_ARG_BY_REF, /* for i128, by reference, first */ + TCG_CALL_ARG_BY_REF_N, /* ... by reference, subsequent */ +} TCGCallArgumentKind; + +typedef struct TCGCallArgumentLoc { + TCGCallArgumentKind kind : 8; + unsigned arg_slot : 8; + unsigned ref_slot : 8; + unsigned arg_idx : 4; + unsigned tmp_subindex : 2; +} TCGCallArgumentLoc; + +typedef struct TCGHelperInfo { + void *func; + const char *name; +#ifdef CONFIG_TCG_INTERPRETER + ffi_cif *cif; +#endif + unsigned typemask : 32; + unsigned flags : 8; + unsigned nr_in : 8; + unsigned nr_out : 8; + TCGCallReturnKind out_kind : 8; + + /* Maximum physical arguments are constrained by TCG_TYPE_I128. */ + TCGCallArgumentLoc in[MAX_CALL_IARGS * (128 / TCG_TARGET_REG_BITS)]; +} TCGHelperInfo; + +#endif /* TCG_HELPER_INFO_H */ diff --git a/tcg/tcg-internal.h b/tcg/tcg-internal.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-internal.h +++ b/tcg/tcg-internal.h @@ -XXX,XX +XXX,XX @@ #ifndef TCG_INTERNAL_H #define TCG_INTERNAL_H -#ifdef CONFIG_TCG_INTERPRETER -#include <ffi.h> -#endif +#include "tcg/helper-info.h" #define TCG_HIGHWATER 1024 -/* - * Describe the calling convention of a given argument type. - */ -typedef enum { - TCG_CALL_RET_NORMAL, /* by registers */ - TCG_CALL_RET_BY_REF, /* for i128, by reference */ - TCG_CALL_RET_BY_VEC, /* for i128, by vector register */ -} TCGCallReturnKind; - -typedef enum { - TCG_CALL_ARG_NORMAL, /* by registers (continuing onto stack) */ - TCG_CALL_ARG_EVEN, /* like normal, but skipping odd slots */ - TCG_CALL_ARG_EXTEND, /* for i32, as a sign/zero-extended i64 */ - TCG_CALL_ARG_EXTEND_U, /* ... as a zero-extended i64 */ - TCG_CALL_ARG_EXTEND_S, /* ... as a sign-extended i64 */ - TCG_CALL_ARG_BY_REF, /* for i128, by reference, first */ - TCG_CALL_ARG_BY_REF_N, /* ... by reference, subsequent */ -} TCGCallArgumentKind; - -typedef struct TCGCallArgumentLoc { - TCGCallArgumentKind kind : 8; - unsigned arg_slot : 8; - unsigned ref_slot : 8; - unsigned arg_idx : 4; - unsigned tmp_subindex : 2; -} TCGCallArgumentLoc; - -typedef struct TCGHelperInfo { - void *func; - const char *name; -#ifdef CONFIG_TCG_INTERPRETER - ffi_cif *cif; -#endif - unsigned typemask : 32; - unsigned flags : 8; - unsigned nr_in : 8; - unsigned nr_out : 8; - TCGCallReturnKind out_kind : 8; - - /* Maximum physical arguments are constrained by TCG_TYPE_I128. */ - TCGCallArgumentLoc in[MAX_CALL_IARGS * (128 / TCG_TARGET_REG_BITS)]; -} TCGHelperInfo; - extern TCGContext tcg_init_ctx; extern TCGContext **tcg_ctxs; extern unsigned int tcg_cur_ctxs; -- 2.34.1 In preparation for compiling tcg/ only once, eliminate the all_helpers array. Instantiate the info structs for the generic helpers in accel/tcg/, and the structs for the target-specific helpers in each translate.c. Since we don't see all of the info structs at startup, initialize at first use, using g_once_init_* to make sure we don't race while doing so. Reviewed-by: Anton Johansson <anjo@rev.ng> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- MAINTAINERS | 1 + include/exec/helper-gen.h | 66 ++++++++++++-------- include/exec/helper-tcg.h | 75 ----------------------- include/qemu/typedefs.h | 1 + include/tcg/helper-info.h | 9 ++- include/tcg/tcg.h | 2 +- accel/tcg/plugin-gen.c | 5 ++ accel/tcg/tcg-runtime.c | 4 ++ target/alpha/translate.c | 3 + target/arm/tcg/translate.c | 3 + target/avr/translate.c | 5 ++ target/cris/translate.c | 6 +- target/hexagon/translate.c | 4 ++ target/hppa/translate.c | 5 ++ target/i386/tcg/translate.c | 5 ++ target/loongarch/translate.c | 4 ++ target/m68k/translate.c | 3 + target/microblaze/translate.c | 4 ++ target/mips/tcg/translate.c | 5 ++ target/nios2/translate.c | 5 ++ target/openrisc/translate.c | 5 ++ target/ppc/translate.c | 4 ++ target/riscv/translate.c | 4 ++ target/rx/translate.c | 5 ++ target/s390x/tcg/translate.c | 4 ++ target/sh4/translate.c | 4 ++ target/sparc/translate.c | 3 + target/tricore/translate.c | 5 ++ target/xtensa/translate.c | 4 ++ tcg/tcg.c | 108 ++++++++++++--------------------- include/exec/helper-info.c.inc | 96 +++++++++++++++++++++++++++++ 31 files changed, 282 insertions(+), 175 deletions(-) delete mode 100644 include/exec/helper-tcg.h create mode 100644 include/exec/helper-info.c.inc diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/exec/exec-all.h F: include/exec/tb-flush.h F: include/exec/target_long.h F: include/exec/helper*.h +F: include/exec/helper-info.c.inc F: include/sysemu/cpus.h F: include/sysemu/tcg.h F: include/hw/core/tcg-cpu-ops.h diff --git a/include/exec/helper-gen.h b/include/exec/helper-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-gen.h +++ b/include/exec/helper-gen.h @@ -XXX,XX +XXX,XX @@ -/* Helper file for declaring TCG helper functions. - This one expands generation functions for tcg opcodes. */ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands generation functions for tcg opcodes. + * Define HELPER_H for the header file to be expanded, + * and static inline to change from global file scope. + */ #ifndef HELPER_GEN_H #define HELPER_GEN_H +#include "tcg/tcg.h" +#include "tcg/helper-info.h" #include "exec/helper-head.h" #define DEF_HELPER_FLAGS_0(name, flags, ret) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl0(ret)) \ { \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 0, NULL); \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 0, NULL); \ } #define DEF_HELPER_FLAGS_1(name, flags, ret, t1) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1)) \ { \ - TCGTemp *args[1] = { dh_arg(t1, 1) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 1, args); \ + TCGTemp *args[1] = { dh_arg(t1, 1) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 1, args); \ } #define DEF_HELPER_FLAGS_2(name, flags, ret, t1, t2) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2)) \ { \ - TCGTemp *args[2] = { dh_arg(t1, 1), dh_arg(t2, 2) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 2, args); \ + TCGTemp *args[2] = { dh_arg(t1, 1), dh_arg(t2, 2) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 2, args); \ } #define DEF_HELPER_FLAGS_3(name, flags, ret, t1, t2, t3) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3)) \ { \ - TCGTemp *args[3] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 3, args); \ + TCGTemp *args[3] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 3, args); \ } #define DEF_HELPER_FLAGS_4(name, flags, ret, t1, t2, t3, t4) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), \ dh_arg_decl(t3, 3), dh_arg_decl(t4, 4)) \ { \ - TCGTemp *args[4] = { dh_arg(t1, 1), dh_arg(t2, 2), \ - dh_arg(t3, 3), dh_arg(t4, 4) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 4, args); \ + TCGTemp *args[4] = { dh_arg(t1, 1), dh_arg(t2, 2), \ + dh_arg(t3, 3), dh_arg(t4, 4) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 4, args); \ } #define DEF_HELPER_FLAGS_5(name, flags, ret, t1, t2, t3, t4, t5) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ dh_arg_decl(t4, 4), dh_arg_decl(t5, 5)) \ { \ - TCGTemp *args[5] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 5, args); \ + TCGTemp *args[5] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 5, args); \ } #define DEF_HELPER_FLAGS_6(name, flags, ret, t1, t2, t3, t4, t5, t6) \ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6)) \ { \ - TCGTemp *args[6] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 6, args); \ + TCGTemp *args[6] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 6, args); \ } #define DEF_HELPER_FLAGS_7(name, flags, ret, t1, t2, t3, t4, t5, t6, t7)\ +extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6), \ dh_arg_decl(t7, 7)) \ { \ - TCGTemp *args[7] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6), \ - dh_arg(t7, 7) }; \ - tcg_gen_callN(HELPER(name), dh_retvar(ret), 7, args); \ + TCGTemp *args[7] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6), \ + dh_arg(t7, 7) }; \ + tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 7, args); \ } #include "helper.h" @@ -XXX,XX +XXX,XX @@ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ #undef DEF_HELPER_FLAGS_5 #undef DEF_HELPER_FLAGS_6 #undef DEF_HELPER_FLAGS_7 -#undef GEN_HELPER #endif /* HELPER_GEN_H */ diff --git a/include/exec/helper-tcg.h b/include/exec/helper-tcg.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/exec/helper-tcg.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* Helper file for declaring TCG helper functions. - This one defines data structures private to tcg.c. */ - -#ifndef HELPER_TCG_H -#define HELPER_TCG_H - -#include "exec/helper-head.h" - -/* Need one more level of indirection before stringification - to get all the macros expanded first. */ -#define str(s) #s - -#define DEF_HELPER_FLAGS_0(NAME, FLAGS, ret) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) }, - -#define DEF_HELPER_FLAGS_1(NAME, FLAGS, ret, t1) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) }, - -#define DEF_HELPER_FLAGS_2(NAME, FLAGS, ret, t1, t2) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ - | dh_typemask(t2, 2) }, - -#define DEF_HELPER_FLAGS_3(NAME, FLAGS, ret, t1, t2, t3) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ - | dh_typemask(t2, 2) | dh_typemask(t3, 3) }, - -#define DEF_HELPER_FLAGS_4(NAME, FLAGS, ret, t1, t2, t3, t4) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ - | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) }, - -#define DEF_HELPER_FLAGS_5(NAME, FLAGS, ret, t1, t2, t3, t4, t5) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ - | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) \ - | dh_typemask(t5, 5) }, - -#define DEF_HELPER_FLAGS_6(NAME, FLAGS, ret, t1, t2, t3, t4, t5, t6) \ - { .func = HELPER(NAME), .name = str(NAME), \ - .flags = FLAGS | dh_callflag(ret), \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ - | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) \ - | dh_typemask(t5, 5) | dh_typemask(t6, 6) }, - -#define DEF_HELPER_FLAGS_7(NAME, FLAGS, ret, t1, t2, t3, t4, t5, t6, t7) \ - { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \ - .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ - | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) \ - | dh_typemask(t5, 5) | dh_typemask(t6, 6) | dh_typemask(t7, 7) }, - -#include "helper.h" -#include "accel/tcg/tcg-runtime.h" -#include "accel/tcg/plugin-helpers.h" - -#undef str -#undef DEF_HELPER_FLAGS_0 -#undef DEF_HELPER_FLAGS_1 -#undef DEF_HELPER_FLAGS_2 -#undef DEF_HELPER_FLAGS_3 -#undef DEF_HELPER_FLAGS_4 -#undef DEF_HELPER_FLAGS_5 -#undef DEF_HELPER_FLAGS_6 -#undef DEF_HELPER_FLAGS_7 - -#endif /* HELPER_TCG_H */ diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -XXX,XX +XXX,XX @@ typedef struct ReservedRegion ReservedRegion; typedef struct SavedIOTLB SavedIOTLB; typedef struct SHPCDevice SHPCDevice; typedef struct SSIBus SSIBus; +typedef struct TCGHelperInfo TCGHelperInfo; typedef struct TranslationBlock TranslationBlock; typedef struct VirtIODevice VirtIODevice; typedef struct Visitor Visitor; diff --git a/include/tcg/helper-info.h b/include/tcg/helper-info.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/helper-info.h +++ b/include/tcg/helper-info.h @@ -XXX,XX +XXX,XX @@ typedef struct TCGCallArgumentLoc { unsigned tmp_subindex : 2; } TCGCallArgumentLoc; -typedef struct TCGHelperInfo { +struct TCGHelperInfo { void *func; const char *name; + + /* Used with g_once_init_enter. */ #ifdef CONFIG_TCG_INTERPRETER ffi_cif *cif; +#else + uintptr_t init; #endif + unsigned typemask : 32; unsigned flags : 8; unsigned nr_in : 8; @@ -XXX,XX +XXX,XX @@ typedef struct TCGHelperInfo { /* Maximum physical arguments are constrained by TCG_TYPE_I128. */ TCGCallArgumentLoc in[MAX_CALL_IARGS * (128 / TCG_TARGET_REG_BITS)]; -} TCGHelperInfo; +}; #endif /* TCG_HELPER_INFO_H */ diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ typedef struct TCGTargetOpDef { bool tcg_op_supported(TCGOpcode op); -void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args); +void tcg_gen_callN(TCGHelperInfo *, TCGTemp *ret, int nargs, TCGTemp **args); TCGOp *tcg_emit_op(TCGOpcode opc, unsigned nargs); void tcg_op_remove(TCGContext *s, TCGOp *op); diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "exec/plugin-gen.h" #include "exec/translator.h" +#include "exec/helper-proto.h" + +#define HELPER_H "accel/tcg/plugin-helpers.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H #ifdef CONFIG_SOFTMMU # define CONFIG_SOFTMMU_GATE 1 diff --git a/accel/tcg/tcg-runtime.c b/accel/tcg/tcg-runtime.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-runtime.c +++ b/accel/tcg/tcg-runtime.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "tcg/tcg.h" +#define HELPER_H "accel/tcg/tcg-runtime.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + /* 32-bit helpers */ int32_t HELPER(div_i32)(int32_t arg1, int32_t arg2) diff --git a/target/alpha/translate.c b/target/alpha/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/translate.c +++ b/target/alpha/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H #undef ALPHA_DEBUG_DISAS #define CONFIG_SOFTFLOAT_INLINE diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "cpregs.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H #define ENABLE_ARCH_4T arm_dc_feature(s, ARM_FEATURE_V4T) #define ENABLE_ARCH_5 arm_dc_feature(s, ARM_FEATURE_V5) diff --git a/target/avr/translate.c b/target/avr/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/translate.c +++ b/target/avr/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "exec/gen-icount.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + /* * Define if you want a BREAK instruction translated to a breakpoint * Active debugging connection is assumed diff --git a/target/cris/translate.c b/target/cris/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/cris/translate.c +++ b/target/cris/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "crisv32-decode.h" #include "qemu/qemu-print.h" - #include "exec/helper-gen.h" - #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + #define DISAS_CRIS 0 #if DISAS_CRIS diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -XXX,XX +XXX,XX @@ #include "genptr.h" #include "printinsn.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + #include "analyze_funcs_generated.c.inc" typedef void (*AnalyzeInsn)(DisasContext *ctx); diff --git a/target/hppa/translate.c b/target/hppa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/translate.c +++ b/target/hppa/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + /* Since we have a distinction between register size and address size, we need to redefine all of these. */ diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + #define PREFIX_REPZ 0x01 #define PREFIX_REPNZ 0x02 #define PREFIX_LOCK 0x04 diff --git a/target/loongarch/translate.c b/target/loongarch/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/translate.c +++ b/target/loongarch/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_lladdr, cpu_llval; #include "exec/gen-icount.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + #define DISAS_STOP DISAS_TARGET_0 #define DISAS_EXIT DISAS_TARGET_1 #define DISAS_EXIT_UPDATE DISAS_TARGET_2 diff --git a/target/m68k/translate.c b/target/m68k/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "fpu/softfloat.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H //#define DEBUG_DISPATCH 1 diff --git a/target/microblaze/translate.c b/target/microblaze/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/translate.c +++ b/target/microblaze/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + #define EXTRACT_FIELD(src, start, end) \ (((src) >> start) & ((1 << (end - start + 1)) - 1)) diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.c +++ b/target/mips/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "fpu_helper.h" #include "translate.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + /* * Many sysemu-only helpers are not reachable for user-only. * Define stub generators here, so that we need not either sprinkle diff --git a/target/nios2/translate.c b/target/nios2/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/translate.c +++ b/target/nios2/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/gen-icount.h" #include "semihosting/semihost.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + /* is_jmp field values */ #define DISAS_UPDATE DISAS_TARGET_1 /* cpu state was modified dynamically */ diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/translate.c +++ b/target/openrisc/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + /* is_jmp field values */ #define DISAS_EXIT DISAS_TARGET_0 /* force exit to main loop */ #define DISAS_JUMP DISAS_TARGET_1 /* exit via jmp_pc/jmp_pc_imm */ diff --git a/target/ppc/translate.c b/target/ppc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -XXX,XX +XXX,XX @@ #include "qemu/qemu-print.h" #include "qapi/error.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + #define CPU_SINGLE_STEP 0x1 #define CPU_BRANCH_STEP 0x2 diff --git a/target/riscv/translate.c b/target/riscv/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -XXX,XX +XXX,XX @@ #include "instmap.h" #include "internals.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + /* global register indices */ static TCGv cpu_gpr[32], cpu_gprh[32], cpu_pc, cpu_vl, cpu_vstart; static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */ diff --git a/target/rx/translate.c b/target/rx/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/translate.c +++ b/target/rx/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + typedef struct DisasContext { DisasContextBase base; CPURXState *env; diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/tcg/translate.c +++ b/target/s390x/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "qemu/atomic128.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + /* Information that (most) every instruction needs to manipulate. */ typedef struct DisasContext DisasContext; diff --git a/target/sh4/translate.c b/target/sh4/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "qemu/qemu-print.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + typedef struct DisasContext { DisasContextBase base; diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "asi.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H #define DYNAMIC_PC 1 /* dynamic pc value */ #define JUMP_PC 2 /* dynamic pc value which takes only two values diff --git a/target/tricore/translate.c b/target/tricore/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/translate.c +++ b/target/tricore/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + + /* * TCG registers */ diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/translate.c +++ b/target/xtensa/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" +#define HELPER_H "helper.h" +#include "exec/helper-info.c.inc" +#undef HELPER_H + struct DisasContext { DisasContextBase base; diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ void tcg_pool_reset(TCGContext *s) s->pool_current = NULL; } -#include "exec/helper-proto.h" - -static TCGHelperInfo all_helpers[] = { -#include "exec/helper-tcg.h" -}; -static GHashTable *helper_table; - /* * Create TCGHelperInfo structures for "tcg/tcg-ldst.h" functions, * akin to what "exec/helper-tcg.h" does with DEF_HELPER_FLAGS_N. @@ -XXX,XX +XXX,XX @@ static ffi_type *typecode_to_ffi(int argmask) g_assert_not_reached(); } -static void init_ffi_layouts(void) +static ffi_cif *init_ffi_layout(TCGHelperInfo *info) { - /* g_direct_hash/equal for direct comparisons on uint32_t. */ - GHashTable *ffi_table = g_hash_table_new(NULL, NULL); + unsigned typemask = info->typemask; + struct { + ffi_cif cif; + ffi_type *args[]; + } *ca; + ffi_status status; + int nargs; - for (int i = 0; i < ARRAY_SIZE(all_helpers); ++i) { - TCGHelperInfo *info = &all_helpers[i]; - unsigned typemask = info->typemask; - gpointer hash = (gpointer)(uintptr_t)typemask; - struct { - ffi_cif cif; - ffi_type *args[]; - } *ca; - ffi_status status; - int nargs; - ffi_cif *cif; + /* Ignoring the return type, find the last non-zero field. */ + nargs = 32 - clz32(typemask >> 3); + nargs = DIV_ROUND_UP(nargs, 3); + assert(nargs <= MAX_CALL_IARGS); - cif = g_hash_table_lookup(ffi_table, hash); - if (cif) { - info->cif = cif; - continue; + ca = g_malloc0(sizeof(*ca) + nargs * sizeof(ffi_type *)); + ca->cif.rtype = typecode_to_ffi(typemask & 7); + ca->cif.nargs = nargs; + + if (nargs != 0) { + ca->cif.arg_types = ca->args; + for (int j = 0; j < nargs; ++j) { + int typecode = extract32(typemask, (j + 1) * 3, 3); + ca->args[j] = typecode_to_ffi(typecode); } - - /* Ignoring the return type, find the last non-zero field. */ - nargs = 32 - clz32(typemask >> 3); - nargs = DIV_ROUND_UP(nargs, 3); - assert(nargs <= MAX_CALL_IARGS); - - ca = g_malloc0(sizeof(*ca) + nargs * sizeof(ffi_type *)); - ca->cif.rtype = typecode_to_ffi(typemask & 7); - ca->cif.nargs = nargs; - - if (nargs != 0) { - ca->cif.arg_types = ca->args; - for (int j = 0; j < nargs; ++j) { - int typecode = extract32(typemask, (j + 1) * 3, 3); - ca->args[j] = typecode_to_ffi(typecode); - } - } - - status = ffi_prep_cif(&ca->cif, FFI_DEFAULT_ABI, nargs, - ca->cif.rtype, ca->cif.arg_types); - assert(status == FFI_OK); - - cif = &ca->cif; - info->cif = cif; - g_hash_table_insert(ffi_table, hash, (gpointer)cif); } - g_hash_table_destroy(ffi_table); + status = ffi_prep_cif(&ca->cif, FFI_DEFAULT_ABI, nargs, + ca->cif.rtype, ca->cif.arg_types); + assert(status == FFI_OK); + + return &ca->cif; } + +#define HELPER_INFO_INIT(I) (&(I)->cif) +#define HELPER_INFO_INIT_VAL(I) init_ffi_layout(I) +#else +#define HELPER_INFO_INIT(I) (&(I)->init) +#define HELPER_INFO_INIT_VAL(I) 1 #endif /* CONFIG_TCG_INTERPRETER */ static inline bool arg_slot_reg_p(unsigned arg_slot) @@ -XXX,XX +XXX,XX @@ static void tcg_context_init(unsigned max_cpus) args_ct += n; } - /* Register helpers. */ - /* Use g_direct_hash/equal for direct pointer comparisons on func. */ - helper_table = g_hash_table_new(NULL, NULL); - - for (i = 0; i < ARRAY_SIZE(all_helpers); ++i) { - init_call_layout(&all_helpers[i]); - g_hash_table_insert(helper_table, (gpointer)all_helpers[i].func, - (gpointer)&all_helpers[i]); - } - init_call_layout(&info_helper_ld32_mmu); init_call_layout(&info_helper_ld64_mmu); init_call_layout(&info_helper_ld128_mmu); @@ -XXX,XX +XXX,XX @@ static void tcg_context_init(unsigned max_cpus) init_call_layout(&info_helper_st64_mmu); init_call_layout(&info_helper_st128_mmu); -#ifdef CONFIG_TCG_INTERPRETER - init_ffi_layouts(); -#endif - tcg_target_init(s); process_op_defs(s); @@ -XXX,XX +XXX,XX @@ bool tcg_op_supported(TCGOpcode op) static TCGOp *tcg_op_alloc(TCGOpcode opc, unsigned nargs); -void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args) +void tcg_gen_callN(TCGHelperInfo *info, TCGTemp *ret, int nargs, TCGTemp **args) { - const TCGHelperInfo *info; TCGv_i64 extend_free[MAX_CALL_IARGS]; int n_extend = 0; TCGOp *op; int i, n, pi = 0, total_args; - info = g_hash_table_lookup(helper_table, (gpointer)func); + if (unlikely(g_once_init_enter(HELPER_INFO_INIT(info)))) { + init_call_layout(info); + g_once_init_leave(HELPER_INFO_INIT(info), HELPER_INFO_INIT_VAL(info)); + } + total_args = info->nr_out + info->nr_in + 2; op = tcg_op_alloc(INDEX_op_call, total_args); @@ -XXX,XX +XXX,XX @@ void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args) g_assert_not_reached(); } } - op->args[pi++] = (uintptr_t)func; + op->args[pi++] = (uintptr_t)info->func; op->args[pi++] = (uintptr_t)info; tcg_debug_assert(pi == total_args); diff --git a/include/exec/helper-info.c.inc b/include/exec/helper-info.c.inc new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/helper-info.c.inc @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands info structures for tcg helpers. + * Define HELPER_H for the header file to be expanded. + */ + +#include "tcg/tcg.h" +#include "tcg/helper-info.h" +#include "exec/helper-head.h" + +/* + * Need one more level of indirection before stringification + * to get all the macros expanded first. + */ +#define str(s) #s + +#define DEF_HELPER_FLAGS_0(NAME, FLAGS, RET) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) \ + }; + +#define DEF_HELPER_FLAGS_1(NAME, FLAGS, RET, T1) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + }; + +#define DEF_HELPER_FLAGS_2(NAME, FLAGS, RET, T1, T2) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + | dh_typemask(T2, 2) \ + }; + +#define DEF_HELPER_FLAGS_3(NAME, FLAGS, RET, T1, T2, T3) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + | dh_typemask(T2, 2) | dh_typemask(T3, 3) \ + }; + +#define DEF_HELPER_FLAGS_4(NAME, FLAGS, RET, T1, T2, T3, T4) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + | dh_typemask(T2, 2) | dh_typemask(T3, 3) \ + | dh_typemask(T4, 4) \ + }; + +#define DEF_HELPER_FLAGS_5(NAME, FLAGS, RET, T1, T2, T3, T4, T5) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + | dh_typemask(T2, 2) | dh_typemask(T3, 3) \ + | dh_typemask(T4, 4) | dh_typemask(T5, 5) \ + }; + +#define DEF_HELPER_FLAGS_6(NAME, FLAGS, RET, T1, T2, T3, T4, T5, T6) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + | dh_typemask(T2, 2) | dh_typemask(T3, 3) \ + | dh_typemask(T4, 4) | dh_typemask(T5, 5) \ + | dh_typemask(T6, 6) \ + }; + +#define DEF_HELPER_FLAGS_7(NAME, FLAGS, RET, T1, T2, T3, T4, T5, T6, T7) \ + TCGHelperInfo glue(helper_info_, NAME) = { \ + .func = HELPER(NAME), .name = str(NAME), \ + .flags = FLAGS | dh_callflag(RET), \ + .typemask = dh_typemask(RET, 0) | dh_typemask(T1, 1) \ + | dh_typemask(T2, 2) | dh_typemask(T3, 3) \ + | dh_typemask(T4, 4) | dh_typemask(T5, 5) \ + | dh_typemask(T6, 6) | dh_typemask(T7, 7) \ + }; + +#include HELPER_H + +#undef str +#undef DEF_HELPER_FLAGS_0 +#undef DEF_HELPER_FLAGS_1 +#undef DEF_HELPER_FLAGS_2 +#undef DEF_HELPER_FLAGS_3 +#undef DEF_HELPER_FLAGS_4 +#undef DEF_HELPER_FLAGS_5 +#undef DEF_HELPER_FLAGS_6 +#undef DEF_HELPER_FLAGS_7 -- 2.34.1 Removes a multiplicity of calls to __assert_fail, saving up to 360kiB of .text space as measured on an x86_64 host. Old New Less %Change 9257272 8888680 368592 3.98% qemu-system-aarch64 6100968 5911832 189136 3.10% qemu-system-riscv64 5839112 5707032 132080 2.26% qemu-system-mips 4447608 4341752 105856 2.38% qemu-system-s390x Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg.h | 30 ++++++++++++++++-------------- tcg/tcg.c | 19 +++++++++++++++++++ 2 files changed, 35 insertions(+), 14 deletions(-) diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ static inline void *tcg_splitwx_to_rw(const void *rx) } #endif -static inline size_t temp_idx(TCGTemp *ts) -{ - ptrdiff_t n = ts - tcg_ctx->temps; - tcg_debug_assert(n >= 0 && n < tcg_ctx->nb_temps); - return n; -} - static inline TCGArg temp_arg(TCGTemp *ts) { return (uintptr_t)ts; @@ -XXX,XX +XXX,XX @@ static inline TCGTemp *arg_temp(TCGArg a) return (TCGTemp *)(uintptr_t)a; } -/* Using the offset of a temporary, relative to TCGContext, rather than - its index means that we don't use 0. That leaves offset 0 free for - a NULL representation without having to leave index 0 unused. */ +#ifdef CONFIG_DEBUG_TCG +size_t temp_idx(TCGTemp *ts); +TCGTemp *tcgv_i32_temp(TCGv_i32 v); +#else +static inline size_t temp_idx(TCGTemp *ts) +{ + return ts - tcg_ctx->temps; +} + +/* + * Using the offset of a temporary, relative to TCGContext, rather than + * its index means that we don't use 0. That leaves offset 0 free for + * a NULL representation without having to leave index 0 unused. + */ static inline TCGTemp *tcgv_i32_temp(TCGv_i32 v) { - uintptr_t o = (uintptr_t)v; - TCGTemp *t = (void *)tcg_ctx + o; - tcg_debug_assert(offsetof(TCGContext, temps[temp_idx(t)]) == o); - return t; + return (void *)tcg_ctx + (uintptr_t)v; } +#endif static inline TCGTemp *tcgv_i64_temp(TCGv_i64 v) { diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ TCGv_vec tcg_constant_vec_matching(TCGv_vec match, unsigned vece, int64_t val) return tcg_constant_vec(t->base_type, vece, val); } +#ifdef CONFIG_DEBUG_TCG +size_t temp_idx(TCGTemp *ts) +{ + ptrdiff_t n = ts - tcg_ctx->temps; + assert(n >= 0 && n < tcg_ctx->nb_temps); + return n; +} + +TCGTemp *tcgv_i32_temp(TCGv_i32 v) +{ + uintptr_t o = (uintptr_t)v - offsetof(TCGContext, temps); + + assert(o < sizeof(TCGTemp) * tcg_ctx->nb_temps); + assert(o % sizeof(TCGTemp) == 0); + + return (void *)tcg_ctx + (uintptr_t)v; +} +#endif /* CONFIG_DEBUG_TCG */ + /* Return true if OP may appear in the opcode stream. Test the runtime variable that controls each opcode. */ bool tcg_op_supported(TCGOpcode op) -- 2.34.1 Make tcg_gen_callN a static function. Create tcg_gen_call[0-7] functions for use by helper-gen.h.inc. Removes a multiplicty of calls to __stack_chk_fail, saving up to 143kiB of .text space as measured on an x86_64 host. Old New Less %Change 8888680 8741816 146864 1.65% qemu-system-aarch64 5911832 5856152 55680 0.94% qemu-system-riscv64 5816728 5767512 49216 0.85% qemu-system-mips64 6707832 6659144 48688 0.73% qemu-system-ppc64 Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/helper-gen.h | 40 ++++++++++++++--------------- include/tcg/tcg.h | 14 +++++++++- tcg/tcg.c | 54 ++++++++++++++++++++++++++++++++++++++- 3 files changed, 86 insertions(+), 22 deletions(-) diff --git a/include/exec/helper-gen.h b/include/exec/helper-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-gen.h +++ b/include/exec/helper-gen.h @@ -XXX,XX +XXX,XX @@ extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl0(ret)) \ { \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 0, NULL); \ + tcg_gen_call0(&glue(helper_info_, name), dh_retvar(ret)); \ } #define DEF_HELPER_FLAGS_1(name, flags, ret, t1) \ @@ -XXX,XX +XXX,XX @@ extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1)) \ { \ - TCGTemp *args[1] = { dh_arg(t1, 1) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 1, args); \ + tcg_gen_call1(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1)); \ } #define DEF_HELPER_FLAGS_2(name, flags, ret, t1, t2) \ @@ -XXX,XX +XXX,XX @@ extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2)) \ { \ - TCGTemp *args[2] = { dh_arg(t1, 1), dh_arg(t2, 2) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 2, args); \ + tcg_gen_call2(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2)); \ } #define DEF_HELPER_FLAGS_3(name, flags, ret, t1, t2, t3) \ @@ -XXX,XX +XXX,XX @@ extern TCGHelperInfo glue(helper_info_, name); \ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3)) \ { \ - TCGTemp *args[3] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 3, args); \ + tcg_gen_call3(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3)); \ } #define DEF_HELPER_FLAGS_4(name, flags, ret, t1, t2, t3, t4) \ @@ -XXX,XX +XXX,XX @@ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), \ dh_arg_decl(t3, 3), dh_arg_decl(t4, 4)) \ { \ - TCGTemp *args[4] = { dh_arg(t1, 1), dh_arg(t2, 2), \ - dh_arg(t3, 3), dh_arg(t4, 4) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 4, args); \ + tcg_gen_call4(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), \ + dh_arg(t3, 3), dh_arg(t4, 4)); \ } #define DEF_HELPER_FLAGS_5(name, flags, ret, t1, t2, t3, t4, t5) \ @@ -XXX,XX +XXX,XX @@ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ dh_arg_decl(t4, 4), dh_arg_decl(t5, 5)) \ { \ - TCGTemp *args[5] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 5, args); \ + tcg_gen_call5(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5)); \ } #define DEF_HELPER_FLAGS_6(name, flags, ret, t1, t2, t3, t4, t5, t6) \ @@ -XXX,XX +XXX,XX @@ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6)) \ { \ - TCGTemp *args[6] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 6, args); \ + tcg_gen_call6(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6)); \ } #define DEF_HELPER_FLAGS_7(name, flags, ret, t1, t2, t3, t4, t5, t6, t7)\ @@ -XXX,XX +XXX,XX @@ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6), \ dh_arg_decl(t7, 7)) \ { \ - TCGTemp *args[7] = { dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6), \ - dh_arg(t7, 7) }; \ - tcg_gen_callN(&glue(helper_info_, name), dh_retvar(ret), 7, args); \ + tcg_gen_call7(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6), \ + dh_arg(t7, 7)); \ } #include "helper.h" diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ typedef struct TCGTargetOpDef { bool tcg_op_supported(TCGOpcode op); -void tcg_gen_callN(TCGHelperInfo *, TCGTemp *ret, int nargs, TCGTemp **args); +void tcg_gen_call0(TCGHelperInfo *, TCGTemp *ret); +void tcg_gen_call1(TCGHelperInfo *, TCGTemp *ret, TCGTemp *); +void tcg_gen_call2(TCGHelperInfo *, TCGTemp *ret, TCGTemp *, TCGTemp *); +void tcg_gen_call3(TCGHelperInfo *, TCGTemp *ret, TCGTemp *, + TCGTemp *, TCGTemp *); +void tcg_gen_call4(TCGHelperInfo *, TCGTemp *ret, TCGTemp *, TCGTemp *, + TCGTemp *, TCGTemp *); +void tcg_gen_call5(TCGHelperInfo *, TCGTemp *ret, TCGTemp *, TCGTemp *, + TCGTemp *, TCGTemp *, TCGTemp *); +void tcg_gen_call6(TCGHelperInfo *, TCGTemp *ret, TCGTemp *, TCGTemp *, + TCGTemp *, TCGTemp *, TCGTemp *, TCGTemp *); +void tcg_gen_call7(TCGHelperInfo *, TCGTemp *ret, TCGTemp *, TCGTemp *, + TCGTemp *, TCGTemp *, TCGTemp *, TCGTemp *, TCGTemp *); TCGOp *tcg_emit_op(TCGOpcode opc, unsigned nargs); void tcg_op_remove(TCGContext *s, TCGOp *op); diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ bool tcg_op_supported(TCGOpcode op) static TCGOp *tcg_op_alloc(TCGOpcode opc, unsigned nargs); -void tcg_gen_callN(TCGHelperInfo *info, TCGTemp *ret, int nargs, TCGTemp **args) +static void tcg_gen_callN(TCGHelperInfo *info, TCGTemp *ret, TCGTemp **args) { TCGv_i64 extend_free[MAX_CALL_IARGS]; int n_extend = 0; @@ -XXX,XX +XXX,XX @@ void tcg_gen_callN(TCGHelperInfo *info, TCGTemp *ret, int nargs, TCGTemp **args) } } +void tcg_gen_call0(TCGHelperInfo *info, TCGTemp *ret) +{ + tcg_gen_callN(info, ret, NULL); +} + +void tcg_gen_call1(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1) +{ + tcg_gen_callN(info, ret, &t1); +} + +void tcg_gen_call2(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1, TCGTemp *t2) +{ + TCGTemp *args[2] = { t1, t2 }; + tcg_gen_callN(info, ret, args); +} + +void tcg_gen_call3(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1, + TCGTemp *t2, TCGTemp *t3) +{ + TCGTemp *args[3] = { t1, t2, t3 }; + tcg_gen_callN(info, ret, args); +} + +void tcg_gen_call4(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1, + TCGTemp *t2, TCGTemp *t3, TCGTemp *t4) +{ + TCGTemp *args[4] = { t1, t2, t3, t4 }; + tcg_gen_callN(info, ret, args); +} + +void tcg_gen_call5(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1, + TCGTemp *t2, TCGTemp *t3, TCGTemp *t4, TCGTemp *t5) +{ + TCGTemp *args[5] = { t1, t2, t3, t4, t5 }; + tcg_gen_callN(info, ret, args); +} + +void tcg_gen_call6(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1, TCGTemp *t2, + TCGTemp *t3, TCGTemp *t4, TCGTemp *t5, TCGTemp *t6) +{ + TCGTemp *args[6] = { t1, t2, t3, t4, t5, t6 }; + tcg_gen_callN(info, ret, args); +} + +void tcg_gen_call7(TCGHelperInfo *info, TCGTemp *ret, TCGTemp *t1, + TCGTemp *t2, TCGTemp *t3, TCGTemp *t4, + TCGTemp *t5, TCGTemp *t6, TCGTemp *t7) +{ + TCGTemp *args[7] = { t1, t2, t3, t4, t5, t6, t7 }; + tcg_gen_callN(info, ret, args); +} + static void tcg_reg_alloc_start(TCGContext *s) { int i, n; -- 2.34.1 Create helper-gen-common.h without the target specific portion. Use that in tcg-op-common.h. Reorg headers in target/arm to ensure that helper-gen.h is included before helper-info.c.inc. All other targets are already correct in this regard. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- MAINTAINERS | 1 + include/exec/helper-gen-common.h | 18 ++++++ include/exec/helper-gen.h | 101 ++---------------------------- include/tcg/tcg-op-common.h | 2 +- include/exec/helper-gen.h.inc | 102 +++++++++++++++++++++++++++++++ target/arm/tcg/translate.c | 8 +-- 6 files changed, 129 insertions(+), 103 deletions(-) create mode 100644 include/exec/helper-gen-common.h create mode 100644 include/exec/helper-gen.h.inc diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/exec/exec-all.h F: include/exec/tb-flush.h F: include/exec/target_long.h F: include/exec/helper*.h +F: include/exec/helper*.h.inc F: include/exec/helper-info.c.inc F: include/sysemu/cpus.h F: include/sysemu/tcg.h diff --git a/include/exec/helper-gen-common.h b/include/exec/helper-gen-common.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/helper-gen-common.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands generation functions for tcg opcodes. + */ + +#ifndef HELPER_GEN_COMMON_H +#define HELPER_GEN_COMMON_H + +#define HELPER_H "accel/tcg/tcg-runtime.h" +#include "exec/helper-gen.h.inc" +#undef HELPER_H + +#define HELPER_H "accel/tcg/plugin-helpers.h" +#include "exec/helper-gen.h.inc" +#undef HELPER_H + +#endif /* HELPER_GEN_COMMON_H */ diff --git a/include/exec/helper-gen.h b/include/exec/helper-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-gen.h +++ b/include/exec/helper-gen.h @@ -XXX,XX +XXX,XX @@ /* * Helper file for declaring TCG helper functions. * This one expands generation functions for tcg opcodes. - * Define HELPER_H for the header file to be expanded, - * and static inline to change from global file scope. */ #ifndef HELPER_GEN_H #define HELPER_GEN_H -#include "tcg/tcg.h" -#include "tcg/helper-info.h" -#include "exec/helper-head.h" +#include "exec/helper-gen-common.h" -#define DEF_HELPER_FLAGS_0(name, flags, ret) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl0(ret)) \ -{ \ - tcg_gen_call0(&glue(helper_info_, name), dh_retvar(ret)); \ -} - -#define DEF_HELPER_FLAGS_1(name, flags, ret, t1) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1)) \ -{ \ - tcg_gen_call1(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1)); \ -} - -#define DEF_HELPER_FLAGS_2(name, flags, ret, t1, t2) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2)) \ -{ \ - tcg_gen_call2(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1), dh_arg(t2, 2)); \ -} - -#define DEF_HELPER_FLAGS_3(name, flags, ret, t1, t2, t3) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3)) \ -{ \ - tcg_gen_call3(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3)); \ -} - -#define DEF_HELPER_FLAGS_4(name, flags, ret, t1, t2, t3, t4) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), \ - dh_arg_decl(t3, 3), dh_arg_decl(t4, 4)) \ -{ \ - tcg_gen_call4(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1), dh_arg(t2, 2), \ - dh_arg(t3, 3), dh_arg(t4, 4)); \ -} - -#define DEF_HELPER_FLAGS_5(name, flags, ret, t1, t2, t3, t4, t5) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ - dh_arg_decl(t4, 4), dh_arg_decl(t5, 5)) \ -{ \ - tcg_gen_call5(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5)); \ -} - -#define DEF_HELPER_FLAGS_6(name, flags, ret, t1, t2, t3, t4, t5, t6) \ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ - dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6)) \ -{ \ - tcg_gen_call6(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6)); \ -} - -#define DEF_HELPER_FLAGS_7(name, flags, ret, t1, t2, t3, t4, t5, t6, t7)\ -extern TCGHelperInfo glue(helper_info_, name); \ -static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ - dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ - dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6), \ - dh_arg_decl(t7, 7)) \ -{ \ - tcg_gen_call7(&glue(helper_info_, name), dh_retvar(ret), \ - dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ - dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6), \ - dh_arg(t7, 7)); \ -} - -#include "helper.h" -#include "accel/tcg/tcg-runtime.h" -#include "accel/tcg/plugin-helpers.h" - -#undef DEF_HELPER_FLAGS_0 -#undef DEF_HELPER_FLAGS_1 -#undef DEF_HELPER_FLAGS_2 -#undef DEF_HELPER_FLAGS_3 -#undef DEF_HELPER_FLAGS_4 -#undef DEF_HELPER_FLAGS_5 -#undef DEF_HELPER_FLAGS_6 -#undef DEF_HELPER_FLAGS_7 +#define HELPER_H "helper.h" +#include "exec/helper-gen.h.inc" +#undef HELPER_H #endif /* HELPER_GEN_H */ diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op-common.h +++ b/include/tcg/tcg-op-common.h @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg.h" #include "exec/helper-proto.h" -#include "exec/helper-gen.h" +#include "exec/helper-gen-common.h" /* Basic output routines. Not for general consumption. */ diff --git a/include/exec/helper-gen.h.inc b/include/exec/helper-gen.h.inc new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/helper-gen.h.inc @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands generation functions for tcg opcodes. + * Define HELPER_H for the header file to be expanded, + * and static inline to change from global file scope. + */ + +#include "tcg/tcg.h" +#include "tcg/helper-info.h" +#include "exec/helper-head.h" + +#define DEF_HELPER_FLAGS_0(name, flags, ret) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl0(ret)) \ +{ \ + tcg_gen_call0(&glue(helper_info_, name), dh_retvar(ret)); \ +} + +#define DEF_HELPER_FLAGS_1(name, flags, ret, t1) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1)) \ +{ \ + tcg_gen_call1(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1)); \ +} + +#define DEF_HELPER_FLAGS_2(name, flags, ret, t1, t2) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2)) \ +{ \ + tcg_gen_call2(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2)); \ +} + +#define DEF_HELPER_FLAGS_3(name, flags, ret, t1, t2, t3) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3)) \ +{ \ + tcg_gen_call3(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3)); \ +} + +#define DEF_HELPER_FLAGS_4(name, flags, ret, t1, t2, t3, t4) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), \ + dh_arg_decl(t3, 3), dh_arg_decl(t4, 4)) \ +{ \ + tcg_gen_call4(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), \ + dh_arg(t3, 3), dh_arg(t4, 4)); \ +} + +#define DEF_HELPER_FLAGS_5(name, flags, ret, t1, t2, t3, t4, t5) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ + dh_arg_decl(t4, 4), dh_arg_decl(t5, 5)) \ +{ \ + tcg_gen_call5(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5)); \ +} + +#define DEF_HELPER_FLAGS_6(name, flags, ret, t1, t2, t3, t4, t5, t6) \ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ + dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6)) \ +{ \ + tcg_gen_call6(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6)); \ +} + +#define DEF_HELPER_FLAGS_7(name, flags, ret, t1, t2, t3, t4, t5, t6, t7)\ +extern TCGHelperInfo glue(helper_info_, name); \ +static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ + dh_arg_decl(t1, 1), dh_arg_decl(t2, 2), dh_arg_decl(t3, 3), \ + dh_arg_decl(t4, 4), dh_arg_decl(t5, 5), dh_arg_decl(t6, 6), \ + dh_arg_decl(t7, 7)) \ +{ \ + tcg_gen_call7(&glue(helper_info_, name), dh_retvar(ret), \ + dh_arg(t1, 1), dh_arg(t2, 2), dh_arg(t3, 3), \ + dh_arg(t4, 4), dh_arg(t5, 5), dh_arg(t6, 6), \ + dh_arg(t7, 7)); \ +} + +#include HELPER_H + +#undef DEF_HELPER_FLAGS_0 +#undef DEF_HELPER_FLAGS_1 +#undef DEF_HELPER_FLAGS_2 +#undef DEF_HELPER_FLAGS_3 +#undef DEF_HELPER_FLAGS_4 +#undef DEF_HELPER_FLAGS_5 +#undef DEF_HELPER_FLAGS_6 +#undef DEF_HELPER_FLAGS_7 diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "semihosting/semihost.h" #include "exec/log.h" #include "cpregs.h" +#include "translate.h" +#include "translate-a32.h" +#include "exec/gen-icount.h" #define HELPER_H "helper.h" #include "exec/helper-info.c.inc" @@ -XXX,XX +XXX,XX @@ #define ENABLE_ARCH_7 arm_dc_feature(s, ARM_FEATURE_V7) #define ENABLE_ARCH_8 arm_dc_feature(s, ARM_FEATURE_V8) -#include "translate.h" -#include "translate-a32.h" - /* These are TCG temporaries used only by the legacy iwMMXt decoder */ static TCGv_i64 cpu_V0, cpu_V1, cpu_M0; /* These are TCG globals which alias CPUARMState fields */ @@ -XXX,XX +XXX,XX @@ TCGv_i32 cpu_CF, cpu_NF, cpu_VF, cpu_ZF; TCGv_i64 cpu_exclusive_addr; TCGv_i64 cpu_exclusive_val; -#include "exec/gen-icount.h" - static const char * const regnames[] = { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" }; -- 2.34.1 Create helper-proto-common.h without the target specific portion. Use that in tcg-op-common.h. Include helper-proto.h in target/arm and target/hexagon before helper-info.c.inc; all other targets are already correct in this regard. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/helper-proto-common.h | 18 ++++++++ include/exec/helper-proto.h | 73 ++++-------------------------- include/tcg/tcg-op-common.h | 2 +- include/exec/helper-proto.h.inc | 68 ++++++++++++++++++++++++++++ accel/tcg/cputlb.c | 3 +- accel/tcg/plugin-gen.c | 2 +- accel/tcg/tcg-runtime-gvec.c | 2 +- accel/tcg/tcg-runtime.c | 2 +- target/arm/tcg/translate.c | 1 + target/hexagon/translate.c | 1 + 10 files changed, 102 insertions(+), 70 deletions(-) create mode 100644 include/exec/helper-proto-common.h create mode 100644 include/exec/helper-proto.h.inc diff --git a/include/exec/helper-proto-common.h b/include/exec/helper-proto-common.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/helper-proto-common.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands prototypes for the helper functions. + */ + +#ifndef HELPER_PROTO_COMMON_H +#define HELPER_PROTO_COMMON_H + +#define HELPER_H "accel/tcg/tcg-runtime.h" +#include "exec/helper-proto.h.inc" +#undef HELPER_H + +#define HELPER_H "accel/tcg/plugin-helpers.h" +#include "exec/helper-proto.h.inc" +#undef HELPER_H + +#endif /* HELPER_PROTO_COMMON_H */ diff --git a/include/exec/helper-proto.h b/include/exec/helper-proto.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-proto.h +++ b/include/exec/helper-proto.h @@ -XXX,XX +XXX,XX @@ -/* Helper file for declaring TCG helper functions. - This one expands prototypes for the helper functions. */ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands prototypes for the helper functions. + */ #ifndef HELPER_PROTO_H #define HELPER_PROTO_H -#include "exec/helper-head.h" +#include "exec/helper-proto-common.h" -/* - * Work around an issue with --enable-lto, in which GCC's ipa-split pass - * decides to split out the noreturn code paths that raise an exception, - * taking the __builtin_return_address() along into the new function, - * where it no longer computes a value that returns to TCG generated code. - * Despite the name, the noinline attribute affects splitter, so this - * prevents the optimization in question. Given that helpers should not - * otherwise be called directly, this should have any other visible effect. - * - * See https://gitlab.com/qemu-project/qemu/-/issues/1454 - */ -#define DEF_HELPER_ATTR __attribute__((noinline)) - -#define DEF_HELPER_FLAGS_0(name, flags, ret) \ -dh_ctype(ret) HELPER(name) (void) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_1(name, flags, ret, t1) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1)) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_2(name, flags, ret, t1, t2) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2)) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_3(name, flags, ret, t1, t2, t3) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), \ - dh_ctype(t3)) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_4(name, flags, ret, t1, t2, t3, t4) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ - dh_ctype(t4)) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_5(name, flags, ret, t1, t2, t3, t4, t5) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ - dh_ctype(t4), dh_ctype(t5)) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_6(name, flags, ret, t1, t2, t3, t4, t5, t6) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ - dh_ctype(t4), dh_ctype(t5), \ - dh_ctype(t6)) DEF_HELPER_ATTR; - -#define DEF_HELPER_FLAGS_7(name, flags, ret, t1, t2, t3, t4, t5, t6, t7) \ -dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ - dh_ctype(t4), dh_ctype(t5), dh_ctype(t6), \ - dh_ctype(t7)) DEF_HELPER_ATTR; - -#define IN_HELPER_PROTO - -#include "helper.h" -#include "accel/tcg/tcg-runtime.h" -#include "accel/tcg/plugin-helpers.h" - -#undef IN_HELPER_PROTO - -#undef DEF_HELPER_FLAGS_0 -#undef DEF_HELPER_FLAGS_1 -#undef DEF_HELPER_FLAGS_2 -#undef DEF_HELPER_FLAGS_3 -#undef DEF_HELPER_FLAGS_4 -#undef DEF_HELPER_FLAGS_5 -#undef DEF_HELPER_FLAGS_6 -#undef DEF_HELPER_FLAGS_7 -#undef DEF_HELPER_ATTR +#define HELPER_H "helper.h" +#include "exec/helper-proto.h.inc" +#undef HELPER_H #endif /* HELPER_PROTO_H */ diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op-common.h +++ b/include/tcg/tcg-op-common.h @@ -XXX,XX +XXX,XX @@ #define TCG_TCG_OP_COMMON_H #include "tcg/tcg.h" -#include "exec/helper-proto.h" +#include "exec/helper-proto-common.h" #include "exec/helper-gen-common.h" /* Basic output routines. Not for general consumption. */ diff --git a/include/exec/helper-proto.h.inc b/include/exec/helper-proto.h.inc new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/helper-proto.h.inc @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper file for declaring TCG helper functions. + * This one expands prototypes for the helper functions. + * Define HELPER_H for the header file to be expanded. + */ + +#include "exec/helper-head.h" + +/* + * Work around an issue with --enable-lto, in which GCC's ipa-split pass + * decides to split out the noreturn code paths that raise an exception, + * taking the __builtin_return_address() along into the new function, + * where it no longer computes a value that returns to TCG generated code. + * Despite the name, the noinline attribute affects splitter, so this + * prevents the optimization in question. Given that helpers should not + * otherwise be called directly, this should not have any other visible effect. + * + * See https://gitlab.com/qemu-project/qemu/-/issues/1454 + */ +#define DEF_HELPER_ATTR __attribute__((noinline)) + +#define DEF_HELPER_FLAGS_0(name, flags, ret) \ +dh_ctype(ret) HELPER(name) (void) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_1(name, flags, ret, t1) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1)) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_2(name, flags, ret, t1, t2) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2)) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_3(name, flags, ret, t1, t2, t3) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), \ + dh_ctype(t3)) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_4(name, flags, ret, t1, t2, t3, t4) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ + dh_ctype(t4)) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_5(name, flags, ret, t1, t2, t3, t4, t5) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ + dh_ctype(t4), dh_ctype(t5)) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_6(name, flags, ret, t1, t2, t3, t4, t5, t6) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ + dh_ctype(t4), dh_ctype(t5), \ + dh_ctype(t6)) DEF_HELPER_ATTR; + +#define DEF_HELPER_FLAGS_7(name, flags, ret, t1, t2, t3, t4, t5, t6, t7) \ +dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ + dh_ctype(t4), dh_ctype(t5), dh_ctype(t6), \ + dh_ctype(t7)) DEF_HELPER_ATTR; + +#define IN_HELPER_PROTO + +#include HELPER_H + +#undef IN_HELPER_PROTO + +#undef DEF_HELPER_FLAGS_0 +#undef DEF_HELPER_FLAGS_1 +#undef DEF_HELPER_FLAGS_2 +#undef DEF_HELPER_FLAGS_3 +#undef DEF_HELPER_FLAGS_4 +#undef DEF_HELPER_FLAGS_5 +#undef DEF_HELPER_FLAGS_6 +#undef DEF_HELPER_FLAGS_7 +#undef DEF_HELPER_ATTR diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg.h" #include "qemu/error-report.h" #include "exec/log.h" -#include "exec/helper-proto.h" +#include "exec/helper-proto-common.h" #include "qemu/atomic.h" #include "qemu/atomic128.h" #include "exec/translate-all.h" @@ -XXX,XX +XXX,XX @@ #endif #include "tcg/tcg-ldst.h" #include "tcg/oversized-guest.h" -#include "exec/helper-proto.h" /* DEBUG defines, enable DEBUG_TLB_LOG to log to the CPU_LOG_MMU target */ /* #define DEBUG_TLB */ diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "exec/plugin-gen.h" #include "exec/translator.h" -#include "exec/helper-proto.h" +#include "exec/helper-proto-common.h" #define HELPER_H "accel/tcg/plugin-helpers.h" #include "exec/helper-info.c.inc" diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-runtime-gvec.c +++ b/accel/tcg/tcg-runtime-gvec.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/host-utils.h" #include "cpu.h" -#include "exec/helper-proto.h" +#include "exec/helper-proto-common.h" #include "tcg/tcg-gvec-desc.h" diff --git a/accel/tcg/tcg-runtime.c b/accel/tcg/tcg-runtime.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-runtime.c +++ b/accel/tcg/tcg-runtime.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/host-utils.h" #include "cpu.h" -#include "exec/helper-proto.h" +#include "exec/helper-proto-common.h" #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "disas/disas.h" diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "translate-a32.h" #include "exec/gen-icount.h" +#include "exec/helper-proto.h" #define HELPER_H "helper.h" #include "exec/helper-info.c.inc" diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" #include "exec/helper-gen.h" +#include "exec/helper-proto.h" #include "exec/cpu_ldst.h" #include "exec/log.h" #include "internal.h" -- 2.34.1 Fixes an assert in tcg_gen_code that we don't accidentally eliminate an insn_start during optimization. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sh4/translate.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/target/sh4/translate.c b/target/sh4/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -XXX,XX +XXX,XX @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) /* The entire region has been translated. */ ctx->envflags &= ~TB_FLAG_GUSA_MASK; - ctx->base.pc_next = pc_end; - ctx->base.num_insns += max_insns - 1; - return; + goto done; fail: qemu_log_mask(LOG_UNIMP, "Unrecognized gUSA sequence %08x-%08x\n", @@ -XXX,XX +XXX,XX @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) purposes of accounting within the TB. We might as well report the entire region consumed via ctx->base.pc_next so that it's immediately available in the disassembly dump. */ + + done: ctx->base.pc_next = pc_end; ctx->base.num_insns += max_insns - 1; + + /* + * Emit insn_start to cover each of the insns in the region. + * This matches an assert in tcg.c making sure that we have + * tb->icount * insn_start. + */ + for (i = 1; i < max_insns; ++i) { + tcg_gen_insn_start(pc + i * 2, ctx->envflags); + } } #endif -- 2.34.1 This will enable replacement of TARGET_INSN_START_WORDS in tcg.c. Split out "tcg/insn-start-words.h" and use it in target/. Reviewed-by: Anton Johansson <anjo@rev.ng> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/insn-start-words.h | 17 +++++++++++++++++ include/tcg/tcg-op.h | 8 ++++---- include/tcg/tcg-opc.h | 6 +++--- include/tcg/tcg.h | 9 ++------- accel/tcg/perf.c | 8 ++++++-- accel/tcg/translate-all.c | 20 +++++++++++++------- target/i386/helper.c | 2 +- target/openrisc/sys_helper.c | 2 +- tcg/tcg.c | 16 +++++++++++----- 9 files changed, 58 insertions(+), 30 deletions(-) create mode 100644 include/tcg/insn-start-words.h diff --git a/include/tcg/insn-start-words.h b/include/tcg/insn-start-words.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/tcg/insn-start-words.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define TARGET_INSN_START_WORDS + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef TARGET_INSN_START_WORDS + +#include "cpu.h" + +#ifndef TARGET_INSN_START_EXTRA_WORDS +# define TARGET_INSN_START_WORDS 1 +#else +# define TARGET_INSN_START_WORDS (1 + TARGET_INSN_START_EXTRA_WORDS) +#endif + +#endif /* TARGET_INSN_START_WORDS */ diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -XXX,XX +XXX,XX @@ # error #endif -#if TARGET_INSN_START_WORDS == 1 +#ifndef TARGET_INSN_START_EXTRA_WORDS static inline void tcg_gen_insn_start(target_ulong pc) { TCGOp *op = tcg_emit_op(INDEX_op_insn_start, 64 / TCG_TARGET_REG_BITS); tcg_set_insn_start_param(op, 0, pc); } -#elif TARGET_INSN_START_WORDS == 2 +#elif TARGET_INSN_START_EXTRA_WORDS == 1 static inline void tcg_gen_insn_start(target_ulong pc, target_ulong a1) { TCGOp *op = tcg_emit_op(INDEX_op_insn_start, 2 * 64 / TCG_TARGET_REG_BITS); tcg_set_insn_start_param(op, 0, pc); tcg_set_insn_start_param(op, 1, a1); } -#elif TARGET_INSN_START_WORDS == 3 +#elif TARGET_INSN_START_EXTRA_WORDS == 2 static inline void tcg_gen_insn_start(target_ulong pc, target_ulong a1, target_ulong a2) { @@ -XXX,XX +XXX,XX @@ static inline void tcg_gen_insn_start(target_ulong pc, target_ulong a1, tcg_set_insn_start_param(op, 2, a2); } #else -# error "Unhandled number of operands to insn_start" +#error Unhandled TARGET_INSN_START_EXTRA_WORDS value #endif #if TARGET_LONG_BITS == 32 diff --git a/include/tcg/tcg-opc.h b/include/tcg/tcg-opc.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-opc.h +++ b/include/tcg/tcg-opc.h @@ -XXX,XX +XXX,XX @@ DEF(mulsh_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_mulsh_i64)) #define DATA64_ARGS (TCG_TARGET_REG_BITS == 64 ? 1 : 2) -/* QEMU specific */ -DEF(insn_start, 0, 0, DATA64_ARGS * TARGET_INSN_START_WORDS, - TCG_OPF_NOT_PRESENT) +/* There are tcg_ctx->insn_start_words here, not just one. */ +DEF(insn_start, 0, 0, DATA64_ARGS, TCG_OPF_NOT_PRESENT) + DEF(exit_tb, 0, 0, 1, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) DEF(goto_tb, 0, 0, 1, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) DEF(goto_ptr, 0, 1, 0, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ typedef uint64_t TCGRegSet; #define TCG_TARGET_HAS_v256 0 #endif -#ifndef TARGET_INSN_START_EXTRA_WORDS -# define TARGET_INSN_START_WORDS 1 -#else -# define TARGET_INSN_START_WORDS (1 + TARGET_INSN_START_EXTRA_WORDS) -#endif - typedef enum TCGOpcode { #define DEF(name, oargs, iargs, cargs, flags) INDEX_op_ ## name, #include "tcg/tcg-opc.h" @@ -XXX,XX +XXX,XX @@ struct TCGContext { uint8_t page_bits; uint8_t tlb_dyn_max_bits; #endif + uint8_t insn_start_words; TCGRegSet reserved_regs; intptr_t current_frame_offset; @@ -XXX,XX +XXX,XX @@ struct TCGContext { TCGTemp *reg_to_temp[TCG_TARGET_NB_REGS]; uint16_t gen_insn_end_off[TCG_MAX_INSNS]; - uint64_t gen_insn_data[TCG_MAX_INSNS][TARGET_INSN_START_WORDS]; + uint64_t *gen_insn_data; /* Exit to translator on overflow. */ sigjmp_buf jmp_trans; diff --git a/accel/tcg/perf.c b/accel/tcg/perf.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/perf.c +++ b/accel/tcg/perf.c @@ -XXX,XX +XXX,XX @@ void perf_report_code(uint64_t guest_pc, TranslationBlock *tb, const void *start) { struct debuginfo_query *q; - size_t insn; + size_t insn, start_words; + uint64_t *gen_insn_data; if (!perfmap && !jitdump) { return; @@ -XXX,XX +XXX,XX @@ void perf_report_code(uint64_t guest_pc, TranslationBlock *tb, debuginfo_lock(); /* Query debuginfo for each guest instruction. */ + gen_insn_data = tcg_ctx->gen_insn_data; + start_words = tcg_ctx->insn_start_words; + for (insn = 0; insn < tb->icount; insn++) { /* FIXME: This replicates the restore_state_to_opc() logic. */ - q[insn].address = tcg_ctx->gen_insn_data[insn][0]; + q[insn].address = gen_insn_data[insn * start_words + 0]; if (tb_cflags(tb) & CF_PCREL) { q[insn].address |= (guest_pc & TARGET_PAGE_MASK); } else { diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ #include "tb-context.h" #include "internal.h" #include "perf.h" +#include "tcg/insn-start-words.h" TBContext tb_ctx; @@ -XXX,XX +XXX,XX @@ static int64_t decode_sleb128(const uint8_t **pp) static int encode_search(TranslationBlock *tb, uint8_t *block) { uint8_t *highwater = tcg_ctx->code_gen_highwater; + uint64_t *insn_data = tcg_ctx->gen_insn_data; + uint16_t *insn_end_off = tcg_ctx->gen_insn_end_off; uint8_t *p = block; int i, j, n; for (i = 0, n = tb->icount; i < n; ++i) { - uint64_t prev; + uint64_t prev, curr; for (j = 0; j < TARGET_INSN_START_WORDS; ++j) { if (i == 0) { prev = (!(tb_cflags(tb) & CF_PCREL) && j == 0 ? tb->pc : 0); } else { - prev = tcg_ctx->gen_insn_data[i - 1][j]; + prev = insn_data[(i - 1) * TARGET_INSN_START_WORDS + j]; } - p = encode_sleb128(p, tcg_ctx->gen_insn_data[i][j] - prev); + curr = insn_data[i * TARGET_INSN_START_WORDS + j]; + p = encode_sleb128(p, curr - prev); } - prev = (i == 0 ? 0 : tcg_ctx->gen_insn_end_off[i - 1]); - p = encode_sleb128(p, tcg_ctx->gen_insn_end_off[i] - prev); + prev = (i == 0 ? 0 : insn_end_off[i - 1]); + curr = insn_end_off[i]; + p = encode_sleb128(p, curr - prev); /* Test for (pending) buffer overflow. The assumption is that any one row beginning below the high water mark cannot overrun @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, tcg_ctx->tlb_fast_offset = (int)offsetof(ArchCPU, neg.tlb.f) - (int)offsetof(ArchCPU, env); #endif + tcg_ctx->insn_start_words = TARGET_INSN_START_WORDS; tb_overflow: @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, fprintf(logfile, "OUT: [size=%d]\n", gen_code_size); fprintf(logfile, " -- guest addr 0x%016" PRIx64 " + tb prologue\n", - tcg_ctx->gen_insn_data[insn][0]); + tcg_ctx->gen_insn_data[insn * TARGET_INSN_START_WORDS]); chunk_start = tcg_ctx->gen_insn_end_off[insn]; disas(logfile, tb->tc.ptr, chunk_start); @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, size_t chunk_end = tcg_ctx->gen_insn_end_off[insn]; if (chunk_end > chunk_start) { fprintf(logfile, " -- guest addr 0x%016" PRIx64 "\n", - tcg_ctx->gen_insn_data[insn][0]); + tcg_ctx->gen_insn_data[insn * TARGET_INSN_START_WORDS]); disas(logfile, tb->tc.ptr + chunk_start, chunk_end - chunk_start); chunk_start = chunk_end; diff --git a/target/i386/helper.c b/target/i386/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/helper.c +++ b/target/i386/helper.c @@ -XXX,XX +XXX,XX @@ #endif #include "qemu/log.h" #ifdef CONFIG_TCG -#include "tcg/tcg.h" +#include "tcg/insn-start-words.h" #endif void cpu_sync_avx_hflag(CPUX86State *env) diff --git a/target/openrisc/sys_helper.c b/target/openrisc/sys_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/sys_helper.c +++ b/target/openrisc/sys_helper.c @@ -XXX,XX +XXX,XX @@ #ifndef CONFIG_USER_ONLY #include "hw/boards.h" #endif -#include "tcg/tcg.h" +#include "tcg/insn-start-words.h" #define TO_SPR(group, number) (((group) << 11) + (number)) diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ void tcg_func_start(TCGContext *s) tcg_debug_assert(s->tlb_fast_offset < 0); tcg_debug_assert(s->tlb_fast_offset >= MIN_TLB_MASK_TABLE_OFS); #endif + + tcg_debug_assert(s->insn_start_words > 0); } static TCGTemp *tcg_temp_alloc(TCGContext *s) @@ -XXX,XX +XXX,XX @@ static void tcg_dump_ops(TCGContext *s, FILE *f, bool have_prefs) nb_oargs = 0; col += ne_fprintf(f, "\n ----"); - for (i = 0; i < TARGET_INSN_START_WORDS; ++i) { + for (i = 0, k = s->insn_start_words; i < k; ++i) { col += ne_fprintf(f, " %016" PRIx64, tcg_get_insn_start_param(op, i)); } @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) #ifdef CONFIG_PROFILER TCGProfile *prof = &s->prof; #endif - int i, num_insns; + int i, start_words, num_insns; TCGOp *op; #ifdef CONFIG_PROFILER @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) s->pool_labels = NULL; #endif + start_words = s->insn_start_words; + s->gen_insn_data = + tcg_malloc(sizeof(uint64_t) * s->gen_tb->icount * start_words); + num_insns = -1; QTAILQ_FOREACH(op, &s->ops, link) { TCGOpcode opc = op->opc; @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) assert(s->gen_insn_end_off[num_insns] == off); } num_insns++; - for (i = 0; i < TARGET_INSN_START_WORDS; ++i) { - s->gen_insn_data[num_insns][i] = + for (i = 0; i < start_words; ++i) { + s->gen_insn_data[num_insns * start_words + i] = tcg_get_insn_start_param(op, i); } break; @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) return -2; } } - tcg_debug_assert(num_insns >= 0); + tcg_debug_assert(num_insns + 1 == s->gen_tb->icount); s->gen_insn_end_off[num_insns] = tcg_current_code_size(s); /* Generate TB finalization at the end of block */ -- 2.34.1 This replaces of TCG_GUEST_DEFAULT_MO in tcg-op-ldst.c. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg.h | 1 + accel/tcg/translate-all.c | 5 +++++ tcg/tcg-op-ldst.c | 4 +--- 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ struct TCGContext { uint8_t tlb_dyn_max_bits; #endif uint8_t insn_start_words; + TCGBar guest_mo; TCGRegSet reserved_regs; intptr_t current_frame_offset; diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, (int)offsetof(ArchCPU, neg.tlb.f) - (int)offsetof(ArchCPU, env); #endif tcg_ctx->insn_start_words = TARGET_INSN_START_WORDS; +#ifdef TCG_GUEST_DEFAULT_MO + tcg_ctx->guest_mo = TCG_GUEST_DEFAULT_MO; +#else + tcg_ctx->guest_mo = TCG_MO_ALL; +#endif tb_overflow: diff --git a/tcg/tcg-op-ldst.c b/tcg/tcg-op-ldst.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-ldst.c +++ b/tcg/tcg-op-ldst.c @@ -XXX,XX +XXX,XX @@ static void gen_ldst_i64(TCGOpcode opc, TCGv_i64 v, TCGTemp *addr, MemOpIdx oi) static void tcg_gen_req_mo(TCGBar type) { -#ifdef TCG_GUEST_DEFAULT_MO - type &= TCG_GUEST_DEFAULT_MO; -#endif + type &= tcg_ctx->guest_mo; type &= ~TCG_TARGET_DEFAULT_MO; if (type) { tcg_gen_mb(type | TCG_BAR_SC); -- 2.34.1 The replacement isn't ideal, as the raw count of bits is not easily synced with exec/cpu-all.h, but it does remove from tcg.h the target dependency on TARGET_PAGE_BITS_MIN which is built into TLB_FLAGS_MASK. Reviewed-by: Anton Johansson <anjo@rev.ng> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-all.h | 3 +++ include/tcg/tcg.h | 4 ---- tcg/tcg-op-ldst.c | 18 ++++++++++++++++-- 3 files changed, 19 insertions(+), 6 deletions(-) diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-all.h +++ b/include/exec/cpu-all.h @@ -XXX,XX +XXX,XX @@ CPUArchState *cpu_copy(CPUArchState *env); * * Use TARGET_PAGE_BITS_MIN so that these bits are constant * when TARGET_PAGE_BITS_VARY is in effect. + * + * The count, if not the placement of these bits is known + * to tcg/tcg-op-ldst.c, check_max_alignment(). */ /* Zero if TLB entry is valid. */ #define TLB_INVALID_MASK (1 << (TARGET_PAGE_BITS_MIN - 1)) diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ static inline unsigned get_alignment_bits(MemOp memop) /* A specific alignment requirement. */ a = a >> MO_ASHIFT; } -#if defined(CONFIG_SOFTMMU) - /* The requested alignment cannot overlap the TLB flags. */ - tcg_debug_assert((TLB_FLAGS_MASK & ((1 << a) - 1)) == 0); -#endif return a; } diff --git a/tcg/tcg-op-ldst.c b/tcg/tcg-op-ldst.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-ldst.c +++ b/tcg/tcg-op-ldst.c @@ -XXX,XX +XXX,XX @@ #include "tcg-internal.h" -static inline MemOp tcg_canonicalize_memop(MemOp op, bool is64, bool st) +static void check_max_alignment(unsigned a_bits) +{ +#if defined(CONFIG_SOFTMMU) + /* + * The requested alignment cannot overlap the TLB flags. + * FIXME: Must keep the count up-to-date with "exec/cpu-all.h". + */ + tcg_debug_assert(a_bits + 6 <= tcg_ctx->page_bits); +#endif +} + +static MemOp tcg_canonicalize_memop(MemOp op, bool is64, bool st) { - /* Trigger the asserts within as early as possible. */ unsigned a_bits = get_alignment_bits(op); + check_max_alignment(a_bits); + /* Prefer MO_ALIGN+MO_XX over MO_ALIGN_XX+MO_XX */ if (a_bits == (op & MO_SIZE)) { op = (op & ~MO_AMASK) | MO_ALIGN; @@ -XXX,XX +XXX,XX @@ static void tcg_gen_qemu_ld_i128_int(TCGv_i128 val, TCGTemp *addr, TCGv_i64 ext_addr = NULL; TCGOpcode opc; + check_max_alignment(get_alignment_bits(memop)); tcg_gen_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD); /* TODO: For now, force 32-bit hosts to use the helper. */ @@ -XXX,XX +XXX,XX @@ static void tcg_gen_qemu_st_i128_int(TCGv_i128 val, TCGTemp *addr, TCGv_i64 ext_addr = NULL; TCGOpcode opc; + check_max_alignment(get_alignment_bits(memop)); tcg_gen_req_mo(TCG_MO_ST_LD | TCG_MO_ST_ST); /* TODO: For now, force 32-bit hosts to use the helper. */ -- 2.34.1 Create tcg/tcg-op-gvec-common.h, moving everything that does not concern TARGET_LONG_BITS. Adjust tcg-op-gvec.c to use the new header. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg-op-gvec-common.h | 426 +++++++++++++++++++++++++++++ include/tcg/tcg-op-gvec.h | 444 +------------------------------ tcg/tcg-op-gvec.c | 2 +- 3 files changed, 437 insertions(+), 435 deletions(-) create mode 100644 include/tcg/tcg-op-gvec-common.h diff --git a/include/tcg/tcg-op-gvec-common.h b/include/tcg/tcg-op-gvec-common.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/tcg/tcg-op-gvec-common.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Target independent generic vector operation expansion + * + * Copyright (c) 2018 Linaro + */ + +#ifndef TCG_TCG_OP_GVEC_COMMON_H +#define TCG_TCG_OP_GVEC_COMMON_H + +/* + * "Generic" vectors. All operands are given as offsets from ENV, + * and therefore cannot also be allocated via tcg_global_mem_new_*. + * OPRSZ is the byte size of the vector upon which the operation is performed. + * MAXSZ is the byte size of the full vector; bytes beyond OPSZ are cleared. + * + * All sizes must be 8 or any multiple of 16. + * When OPRSZ is 8, the alignment may be 8, otherwise must be 16. + * Operands may completely, but not partially, overlap. + */ + +/* Expand a call to a gvec-style helper, with pointers to two vector + operands, and a descriptor (see tcg-gvec-desc.h). */ +typedef void gen_helper_gvec_2(TCGv_ptr, TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_2_ool(uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz, int32_t data, + gen_helper_gvec_2 *fn); + +/* Similarly, passing an extra data value. */ +typedef void gen_helper_gvec_2i(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32); +void tcg_gen_gvec_2i_ool(uint32_t dofs, uint32_t aofs, TCGv_i64 c, + uint32_t oprsz, uint32_t maxsz, int32_t data, + gen_helper_gvec_2i *fn); + +/* Similarly, passing an extra pointer (e.g. env or float_status). */ +typedef void gen_helper_gvec_2_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_2_ptr(uint32_t dofs, uint32_t aofs, + TCGv_ptr ptr, uint32_t oprsz, uint32_t maxsz, + int32_t data, gen_helper_gvec_2_ptr *fn); + +/* Similarly, with three vector operands. */ +typedef void gen_helper_gvec_3(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_3_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz, int32_t data, + gen_helper_gvec_3 *fn); + +/* Similarly, with four vector operands. */ +typedef void gen_helper_gvec_4(TCGv_ptr, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_4_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t cofs, uint32_t oprsz, uint32_t maxsz, + int32_t data, gen_helper_gvec_4 *fn); + +/* Similarly, with five vector operands. */ +typedef void gen_helper_gvec_5(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_5_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t cofs, uint32_t xofs, uint32_t oprsz, + uint32_t maxsz, int32_t data, gen_helper_gvec_5 *fn); + +typedef void gen_helper_gvec_3_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_3_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs, + TCGv_ptr ptr, uint32_t oprsz, uint32_t maxsz, + int32_t data, gen_helper_gvec_3_ptr *fn); + +typedef void gen_helper_gvec_4_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_4_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t cofs, TCGv_ptr ptr, uint32_t oprsz, + uint32_t maxsz, int32_t data, + gen_helper_gvec_4_ptr *fn); + +typedef void gen_helper_gvec_5_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_ptr, TCGv_i32); +void tcg_gen_gvec_5_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t cofs, uint32_t eofs, TCGv_ptr ptr, + uint32_t oprsz, uint32_t maxsz, int32_t data, + gen_helper_gvec_5_ptr *fn); + +/* Expand a gvec operation. Either inline or out-of-line depending on + the actual vector size and the operations supported by the host. */ +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); + void (*fni4)(TCGv_i32, TCGv_i32); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec); + /* Expand out-of-line helper w/descriptor. */ + gen_helper_gvec_2 *fno; + /* The optional opcodes, if any, utilized by .fniv. */ + const TCGOpcode *opt_opc; + /* The data argument to the out-of-line helper. */ + int32_t data; + /* The vector element size, if applicable. */ + uint8_t vece; + /* Prefer i64 to v64. */ + bool prefer_i64; + /* Load dest as a 2nd source operand. */ + bool load_dest; +} GVecGen2; + +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, int64_t); + void (*fni4)(TCGv_i32, TCGv_i32, int32_t); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec, int64_t); + /* Expand out-of-line helper w/descriptor, data in descriptor. */ + gen_helper_gvec_2 *fno; + /* Expand out-of-line helper w/descriptor, data as argument. */ + gen_helper_gvec_2i *fnoi; + /* 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; + /* Load dest as a 3rd source operand. */ + bool load_dest; +} GVecGen2i; + +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); + void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec); + /* Expand out-of-line helper w/descriptor. */ + gen_helper_gvec_2i *fno; + /* The optional opcodes, if any, utilized by .fniv. */ + const TCGOpcode *opt_opc; + /* The data argument to the out-of-line helper. */ + uint32_t data; + /* The vector element size, if applicable. */ + uint8_t vece; + /* Prefer i64 to v64. */ + bool prefer_i64; + /* Load scalar as 1st source operand. */ + bool scalar_first; +} GVecGen2s; + +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); + void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec); + /* Expand out-of-line helper w/descriptor. */ + gen_helper_gvec_3 *fno; + /* The optional opcodes, if any, utilized by .fniv. */ + const TCGOpcode *opt_opc; + /* The data argument to the out-of-line helper. */ + int32_t data; + /* The vector element size, if applicable. */ + uint8_t vece; + /* Prefer i64 to v64. */ + bool prefer_i64; + /* Load dest as a 3rd source operand. */ + bool load_dest; +} GVecGen3; + +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, int64_t); + void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32, int32_t); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, int64_t); + /* Expand out-of-line helper w/descriptor, data in descriptor. */ + gen_helper_gvec_3 *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; + /* Load dest as a 3rd source operand. */ + bool load_dest; +} GVecGen3i; + +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); + void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32); + /* Expand inline with a host vector type. */ + void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, TCGv_vec); + /* Expand out-of-line helper w/descriptor. */ + gen_helper_gvec_4 *fno; + /* The optional opcodes, if any, utilized by .fniv. */ + const TCGOpcode *opt_opc; + /* The data argument to the out-of-line helper. */ + int32_t data; + /* The vector element size, if applicable. */ + uint8_t vece; + /* Prefer i64 to v64. */ + bool prefer_i64; + /* Write aofs as a 2nd dest operand. */ + 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, + uint32_t maxsz, int64_t c, const GVecGen2i *); +void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz, + uint32_t maxsz, TCGv_i64 c, const GVecGen2s *); +void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz, const GVecGen3 *); +void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz, int64_t c, + 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. */ + +void tcg_gen_gvec_mov(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_neg(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_abs(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_adds(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_subs(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_muls(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); + +/* Saturated arithmetic. */ +void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_sssub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); + +/* Min/max. */ +void tcg_gen_gvec_smin(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_umin(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_smax(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_umax(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_and(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_or(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_xor(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_nand(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_nor(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_eqv(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_andi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_xori(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_ands(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_andcs(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_xors(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t s, uint32_t m); +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t s, + uint32_t m, uint64_t imm); +void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s, + uint32_t m, TCGv_i32); +void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s, + uint32_t m, TCGv_i64); + +void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_sari(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_rotli(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_rotri(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_shls(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_shrs(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_sars(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_rotls(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_rotrs(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); + +/* + * Perform vector shift by vector element, modulo the element size. + * E.g. D[i] = A[i] << (B[i] % (8 << vece)). + */ +void tcg_gen_gvec_shlv(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_shrv(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_sarv(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_rotlv(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_rotrv(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); + +void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs, + uint32_t aofs, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz); + +/* + * Perform vector bit select: d = (b & a) | (c & ~a). + */ +void tcg_gen_gvec_bitsel(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t cofs, + uint32_t oprsz, uint32_t maxsz); + +/* + * 64-bit vector operations. Use these when the register has been allocated + * with tcg_global_mem_new_i64, and so we cannot also address it via pointer. + * OPRSZ = MAXSZ = 8. + */ + +void tcg_gen_vec_neg8_i64(TCGv_i64 d, TCGv_i64 a); +void tcg_gen_vec_neg16_i64(TCGv_i64 d, TCGv_i64 a); +void tcg_gen_vec_neg32_i64(TCGv_i64 d, TCGv_i64 a); + +void tcg_gen_vec_add8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void tcg_gen_vec_add16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void tcg_gen_vec_add32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); + +void tcg_gen_vec_sub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void tcg_gen_vec_sub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void tcg_gen_vec_sub32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); + +void tcg_gen_vec_shl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); +void tcg_gen_vec_shl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); +void tcg_gen_vec_shr8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); +void tcg_gen_vec_shr16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); +void tcg_gen_vec_sar8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); +void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); +void tcg_gen_vec_rotl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c); +void tcg_gen_vec_rotl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c); + +/* 32-bit vector operations. */ +void tcg_gen_vec_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); +void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); + +void tcg_gen_vec_sub8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); +void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); + +void tcg_gen_vec_shl8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_shl16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_shr8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_shr16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_sar8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); + +#endif diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-op-gvec.h +++ b/include/tcg/tcg-op-gvec.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * Generic vector operation expansion + * Target dependent generic vector operation expansion * * Copyright (c) 2018 Linaro - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ #ifndef TCG_TCG_OP_GVEC_H #define TCG_TCG_OP_GVEC_H -/* - * "Generic" vectors. All operands are given as offsets from ENV, - * and therefore cannot also be allocated via tcg_global_mem_new_*. - * OPRSZ is the byte size of the vector upon which the operation is performed. - * MAXSZ is the byte size of the full vector; bytes beyond OPSZ are cleared. - * - * All sizes must be 8 or any multiple of 16. - * When OPRSZ is 8, the alignment may be 8, otherwise must be 16. - * Operands may completely, but not partially, overlap. - */ +#include "tcg/tcg-op-gvec-common.h" -/* Expand a call to a gvec-style helper, with pointers to two vector - operands, and a descriptor (see tcg-gvec-desc.h). */ -typedef void gen_helper_gvec_2(TCGv_ptr, TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_2_ool(uint32_t dofs, uint32_t aofs, - uint32_t oprsz, uint32_t maxsz, int32_t data, - gen_helper_gvec_2 *fn); - -/* Similarly, passing an extra data value. */ -typedef void gen_helper_gvec_2i(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32); -void tcg_gen_gvec_2i_ool(uint32_t dofs, uint32_t aofs, TCGv_i64 c, - uint32_t oprsz, uint32_t maxsz, int32_t data, - gen_helper_gvec_2i *fn); - -/* Similarly, passing an extra pointer (e.g. env or float_status). */ -typedef void gen_helper_gvec_2_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_2_ptr(uint32_t dofs, uint32_t aofs, - TCGv_ptr ptr, uint32_t oprsz, uint32_t maxsz, - int32_t data, gen_helper_gvec_2_ptr *fn); - -/* Similarly, with three vector operands. */ -typedef void gen_helper_gvec_3(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_3_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t oprsz, uint32_t maxsz, int32_t data, - gen_helper_gvec_3 *fn); - -/* Similarly, with four vector operands. */ -typedef void gen_helper_gvec_4(TCGv_ptr, TCGv_ptr, TCGv_ptr, - TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_4_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t oprsz, uint32_t maxsz, - int32_t data, gen_helper_gvec_4 *fn); - -/* Similarly, with five vector operands. */ -typedef void gen_helper_gvec_5(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, - TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_5_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t xofs, uint32_t oprsz, - uint32_t maxsz, int32_t data, gen_helper_gvec_5 *fn); - -typedef void gen_helper_gvec_3_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, - TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_3_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs, - TCGv_ptr ptr, uint32_t oprsz, uint32_t maxsz, - int32_t data, gen_helper_gvec_3_ptr *fn); - -typedef void gen_helper_gvec_4_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, - TCGv_ptr, TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_4_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, TCGv_ptr ptr, uint32_t oprsz, - uint32_t maxsz, int32_t data, - gen_helper_gvec_4_ptr *fn); - -typedef void gen_helper_gvec_5_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, - TCGv_ptr, TCGv_ptr, TCGv_i32); -void tcg_gen_gvec_5_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t eofs, TCGv_ptr ptr, - uint32_t oprsz, uint32_t maxsz, int32_t data, - gen_helper_gvec_5_ptr *fn); - -/* Expand a gvec operation. Either inline or out-of-line depending on - the actual vector size and the operations supported by the host. */ -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); - void (*fni4)(TCGv_i32, TCGv_i32); - /* Expand inline with a host vector type. */ - void (*fniv)(unsigned, TCGv_vec, TCGv_vec); - /* Expand out-of-line helper w/descriptor. */ - gen_helper_gvec_2 *fno; - /* The optional opcodes, if any, utilized by .fniv. */ - const TCGOpcode *opt_opc; - /* The data argument to the out-of-line helper. */ - int32_t data; - /* The vector element size, if applicable. */ - uint8_t vece; - /* Prefer i64 to v64. */ - bool prefer_i64; - /* Load dest as a 2nd source operand. */ - bool load_dest; -} GVecGen2; - -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, int64_t); - void (*fni4)(TCGv_i32, TCGv_i32, int32_t); - /* Expand inline with a host vector type. */ - void (*fniv)(unsigned, TCGv_vec, TCGv_vec, int64_t); - /* Expand out-of-line helper w/descriptor, data in descriptor. */ - gen_helper_gvec_2 *fno; - /* Expand out-of-line helper w/descriptor, data as argument. */ - gen_helper_gvec_2i *fnoi; - /* 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; - /* Load dest as a 3rd source operand. */ - bool load_dest; -} GVecGen2i; - -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); - void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32); - /* Expand inline with a host vector type. */ - void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec); - /* Expand out-of-line helper w/descriptor. */ - gen_helper_gvec_2i *fno; - /* The optional opcodes, if any, utilized by .fniv. */ - const TCGOpcode *opt_opc; - /* The data argument to the out-of-line helper. */ - uint32_t data; - /* The vector element size, if applicable. */ - uint8_t vece; - /* Prefer i64 to v64. */ - bool prefer_i64; - /* Load scalar as 1st source operand. */ - bool scalar_first; -} GVecGen2s; - -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); - void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32); - /* Expand inline with a host vector type. */ - void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec); - /* Expand out-of-line helper w/descriptor. */ - gen_helper_gvec_3 *fno; - /* The optional opcodes, if any, utilized by .fniv. */ - const TCGOpcode *opt_opc; - /* The data argument to the out-of-line helper. */ - int32_t data; - /* The vector element size, if applicable. */ - uint8_t vece; - /* Prefer i64 to v64. */ - bool prefer_i64; - /* Load dest as a 3rd source operand. */ - bool load_dest; -} GVecGen3; - -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, int64_t); - void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32, int32_t); - /* Expand inline with a host vector type. */ - void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, int64_t); - /* Expand out-of-line helper w/descriptor, data in descriptor. */ - gen_helper_gvec_3 *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; - /* Load dest as a 3rd source operand. */ - bool load_dest; -} GVecGen3i; - -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); - void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32); - /* Expand inline with a host vector type. */ - void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, TCGv_vec); - /* Expand out-of-line helper w/descriptor. */ - gen_helper_gvec_4 *fno; - /* The optional opcodes, if any, utilized by .fniv. */ - const TCGOpcode *opt_opc; - /* The data argument to the out-of-line helper. */ - int32_t data; - /* The vector element size, if applicable. */ - uint8_t vece; - /* Prefer i64 to v64. */ - bool prefer_i64; - /* Write aofs as a 2nd dest operand. */ - 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, - uint32_t maxsz, int64_t c, const GVecGen2i *); -void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz, - uint32_t maxsz, TCGv_i64 c, const GVecGen2s *); -void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t oprsz, uint32_t maxsz, const GVecGen3 *); -void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t oprsz, uint32_t maxsz, int64_t c, - 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. */ - -void tcg_gen_gvec_mov(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_neg(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_abs(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t c, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_adds(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_subs(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_muls(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); - -/* Saturated arithmetic. */ -void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_sssub(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); - -/* Min/max. */ -void tcg_gen_gvec_smin(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_umin(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_smax(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_umax(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_and(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_or(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_xor(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_nand(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_nor(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_eqv(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_andi(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_xori(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t c, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_ands(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_andcs(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_xors(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i64 c, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t s, uint32_t m); -void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t s, - uint32_t m, uint64_t imm); -void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s, - uint32_t m, TCGv_i32); -void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s, - uint32_t m, TCGv_i64); - -#if TARGET_LONG_BITS == 64 -# define tcg_gen_gvec_dup_tl tcg_gen_gvec_dup_i64 -#else -# define tcg_gen_gvec_dup_tl tcg_gen_gvec_dup_i32 +#ifndef TARGET_LONG_BITS +#error must include QEMU headers #endif -void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_sari(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_rotli(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_rotri(unsigned vece, uint32_t dofs, uint32_t aofs, - int64_t shift, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_shls(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_shrs(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_sars(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_rotls(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_rotrs(unsigned vece, uint32_t dofs, uint32_t aofs, - TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz); - -/* - * Perform vector shift by vector element, modulo the element size. - * E.g. D[i] = A[i] << (B[i] % (8 << vece)). - */ -void tcg_gen_gvec_shlv(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_shrv(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_sarv(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_rotlv(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); -void tcg_gen_gvec_rotrv(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t oprsz, uint32_t maxsz); - -void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs, - uint32_t aofs, uint32_t bofs, - uint32_t oprsz, uint32_t maxsz); - -/* - * Perform vector bit select: d = (b & a) | (c & ~a). - */ -void tcg_gen_gvec_bitsel(unsigned vece, uint32_t dofs, uint32_t aofs, - uint32_t bofs, uint32_t cofs, - uint32_t oprsz, uint32_t maxsz); - -/* - * 64-bit vector operations. Use these when the register has been allocated - * with tcg_global_mem_new_i64, and so we cannot also address it via pointer. - * OPRSZ = MAXSZ = 8. - */ - -void tcg_gen_vec_neg8_i64(TCGv_i64 d, TCGv_i64 a); -void tcg_gen_vec_neg16_i64(TCGv_i64 d, TCGv_i64 a); -void tcg_gen_vec_neg32_i64(TCGv_i64 d, TCGv_i64 a); - -void tcg_gen_vec_add8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); -void tcg_gen_vec_add16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); -void tcg_gen_vec_add32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); - -void tcg_gen_vec_sub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); -void tcg_gen_vec_sub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); -void tcg_gen_vec_sub32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); - -void tcg_gen_vec_shl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); -void tcg_gen_vec_shl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); -void tcg_gen_vec_shr8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); -void tcg_gen_vec_shr16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); -void tcg_gen_vec_sar8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); -void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); -void tcg_gen_vec_rotl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c); -void tcg_gen_vec_rotl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c); - -/* 32-bit vector operations. */ -void tcg_gen_vec_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); -void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); - -void tcg_gen_vec_sub8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); -void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); - -void tcg_gen_vec_shl8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); -void tcg_gen_vec_shl16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); -void tcg_gen_vec_shr8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); -void tcg_gen_vec_shr16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); -void tcg_gen_vec_sar8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); -void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); - #if TARGET_LONG_BITS == 64 +#define tcg_gen_gvec_dup_tl tcg_gen_gvec_dup_i64 #define tcg_gen_vec_add8_tl tcg_gen_vec_add8_i64 #define tcg_gen_vec_sub8_tl tcg_gen_vec_sub8_i64 #define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i64 @@ -XXX,XX +XXX,XX @@ void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); #define tcg_gen_vec_shl16i_tl tcg_gen_vec_shl16i_i64 #define tcg_gen_vec_shr16i_tl tcg_gen_vec_shr16i_i64 #define tcg_gen_vec_sar16i_tl tcg_gen_vec_sar16i_i64 - -#else +#elif TARGET_LONG_BITS == 32 +#define tcg_gen_gvec_dup_tl tcg_gen_gvec_dup_i32 #define tcg_gen_vec_add8_tl tcg_gen_vec_add8_i32 #define tcg_gen_vec_sub8_tl tcg_gen_vec_sub8_i32 #define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i32 @@ -XXX,XX +XXX,XX @@ void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); #define tcg_gen_vec_shl16i_tl tcg_gen_vec_shl16i_i32 #define tcg_gen_vec_shr16i_tl tcg_gen_vec_shr16i_i32 #define tcg_gen_vec_sar16i_tl tcg_gen_vec_sar16i_i32 +#else +# error #endif #endif diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" #include "tcg/tcg-op-common.h" -#include "tcg/tcg-op-gvec.h" +#include "tcg/tcg-op-gvec-common.h" #include "tcg/tcg-gvec-desc.h" #define MAX_UNROLL 4 -- 2.34.1 From this remove, it's no longer clear what this is attempting to protect. The last time a use of this define was added to the source tree, as opposed to merely moved around, was 2008. There have been many cleanups since that time and this is no longer required for the build to succeed. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/ppc/cpu.h | 2 -- target/sparc/cpu.h | 2 -- accel/tcg/translate-all.c | 1 - tcg/tcg.c | 6 ------ 4 files changed, 11 deletions(-) diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -XXX,XX +XXX,XX @@ void ppc_store_msr(CPUPPCState *env, target_ulong value); void ppc_cpu_list(void); /* Time-base and decrementer management */ -#ifndef NO_CPU_IO_DEFS uint64_t cpu_ppc_load_tbl(CPUPPCState *env); uint32_t cpu_ppc_load_tbu(CPUPPCState *env); void cpu_ppc_store_tbu(CPUPPCState *env, uint32_t value); @@ -XXX,XX +XXX,XX @@ int ppcemb_tlb_check(CPUPPCState *env, ppcemb_tlb_t *tlb, hwaddr booke206_tlb_to_page_size(CPUPPCState *env, ppcmas_tlb_t *tlb); #endif -#endif void ppc_store_fpscr(CPUPPCState *env, target_ulong val); void helper_hfscr_facility_check(CPUPPCState *env, uint32_t bit, diff --git a/target/sparc/cpu.h b/target/sparc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.h +++ b/target/sparc/cpu.h @@ -XXX,XX +XXX,XX @@ G_NORETURN void sparc_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, uintptr_t retaddr); G_NORETURN void cpu_raise_exception_ra(CPUSPARCState *, int, uintptr_t); -#ifndef NO_CPU_IO_DEFS /* cpu_init.c */ void cpu_sparc_set_id(CPUSPARCState *env, unsigned int cpu); void sparc_cpu_list(void); @@ -XXX,XX +XXX,XX @@ static inline int tlb_compare_context(const SparcTLBEntry *tlb, return compare_masked(context, tlb->tag, MMU_CONTEXT_MASK); } -#endif #endif /* cpu-exec.c */ diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" -#define NO_CPU_IO_DEFS #include "trace.h" #include "disas/disas.h" #include "exec/exec-all.h" diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ #include "qemu/cacheflush.h" #include "qemu/cacheinfo.h" #include "qemu/timer.h" - -/* Note: the long term plan is to reduce the dependencies on the QEMU - CPU definitions. Currently they are used for qemu_ld/st - instructions */ -#define NO_CPU_IO_DEFS - #include "exec/exec-all.h" #include "exec/tlb-common.h" #include "tcg/tcg-op-common.h" -- 2.34.1 This is a step toward making TranslationBlock agnostic to the address size of the guest. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ addresses in userspace mode. Define tb_page_addr_t to be an appropriate type. */ #if defined(CONFIG_USER_ONLY) -typedef abi_ulong tb_page_addr_t; -#define TB_PAGE_ADDR_FMT TARGET_ABI_FMT_lx +typedef vaddr tb_page_addr_t; +#define TB_PAGE_ADDR_FMT "%" VADDR_PRIx #else typedef ram_addr_t tb_page_addr_t; #define TB_PAGE_ADDR_FMT RAM_ADDR_FMT -- 2.34.1 This makes TranslationBlock agnostic to the address size of the guest. Use vaddr for pc, since that's always a virtual address. Use uint64_t for cs_base, since usage varies between guests. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 4 ++-- accel/tcg/cpu-exec.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ struct TranslationBlock { * Unwind information is taken as offsets from the page, to be * deposited into the "current" PC. */ - target_ulong pc; + vaddr pc; /* * Target-specific data associated with the TranslationBlock, e.g.: @@ -XXX,XX +XXX,XX @@ struct TranslationBlock { * s390x: instruction data for EXECUTE, * sparc: the next pc of the instruction queue (for delay slots). */ - target_ulong cs_base; + uint64_t cs_base; uint32_t flags; /* flags defining in which context the code was generated */ uint32_t cflags; /* compile flags */ diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ static void log_cpu_exec(target_ulong pc, CPUState *cpu, { if (qemu_log_in_addr_range(pc)) { qemu_log_mask(CPU_LOG_EXEC, - "Trace %d: %p [" TARGET_FMT_lx + "Trace %d: %p [%08" PRIx64 "/" TARGET_FMT_lx "/%08x/%08x] %s\n", cpu->cpu_index, tb->tc.ptr, tb->cs_base, pc, tb->flags, tb->cflags, lookup_symbol(pc)); -- 2.34.1 This is all that is required by tcg/ from exec-all.h. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 132 +-------------------------- include/exec/translation-block.h | 149 +++++++++++++++++++++++++++++++ tcg/tcg-op-ldst.c | 2 +- 3 files changed, 151 insertions(+), 132 deletions(-) create mode 100644 include/exec/translation-block.h diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ #ifdef CONFIG_TCG #include "exec/cpu_ldst.h" #endif -#include "qemu/interval-tree.h" +#include "exec/translation-block.h" #include "qemu/clang-tsa.h" -/* Page tracking code uses ram addresses in system mode, and virtual - addresses in userspace mode. Define tb_page_addr_t to be an appropriate - type. */ -#if defined(CONFIG_USER_ONLY) -typedef vaddr tb_page_addr_t; -#define TB_PAGE_ADDR_FMT "%" VADDR_PRIx -#else -typedef ram_addr_t tb_page_addr_t; -#define TB_PAGE_ADDR_FMT RAM_ADDR_FMT -#endif - /** * cpu_unwind_state_data: * @cpu: the cpu context @@ -XXX,XX +XXX,XX @@ int probe_access_full(CPUArchState *env, target_ulong addr, int size, CPUTLBEntryFull **pfull, uintptr_t retaddr); #endif -#define CODE_GEN_ALIGN 16 /* must be >= of the size of a icache line */ - /* Estimated block size for TB allocation. */ /* ??? The following is based on a 2015 survey of x86_64 host output. Better would seem to be some sort of dynamically sized TB array, @@ -XXX,XX +XXX,XX @@ int probe_access_full(CPUArchState *env, target_ulong addr, int size, #define CODE_GEN_AVG_BLOCK_SIZE 150 #endif -/* - * Translation Cache-related fields of a TB. - * This struct exists just for convenience; we keep track of TB's in a binary - * search tree, and the only fields needed to compare TB's in the tree are - * @ptr and @size. - * Note: the address of search data can be obtained by adding @size to @ptr. - */ -struct tb_tc { - const void *ptr; /* pointer to the translated code */ - size_t size; -}; - -struct TranslationBlock { - /* - * Guest PC corresponding to this block. This must be the true - * virtual address. Therefore e.g. x86 stores EIP + CS_BASE, and - * targets like Arm, MIPS, HP-PA, which reuse low bits for ISA or - * privilege, must store those bits elsewhere. - * - * If CF_PCREL, the opcodes for the TranslationBlock are written - * such that the TB is associated only with the physical page and - * may be run in any virtual address context. In this case, PC - * must always be taken from ENV in a target-specific manner. - * Unwind information is taken as offsets from the page, to be - * deposited into the "current" PC. - */ - vaddr pc; - - /* - * Target-specific data associated with the TranslationBlock, e.g.: - * x86: the original user, the Code Segment virtual base, - * arm: an extension of tb->flags, - * s390x: instruction data for EXECUTE, - * sparc: the next pc of the instruction queue (for delay slots). - */ - uint64_t cs_base; - - uint32_t flags; /* flags defining in which context the code was generated */ - uint32_t cflags; /* compile flags */ - -/* Note that TCG_MAX_INSNS is 512; we validate this match elsewhere. */ -#define CF_COUNT_MASK 0x000001ff -#define CF_NO_GOTO_TB 0x00000200 /* Do not chain with goto_tb */ -#define CF_NO_GOTO_PTR 0x00000400 /* Do not chain with goto_ptr */ -#define CF_SINGLE_STEP 0x00000800 /* gdbstub single-step in effect */ -#define CF_LAST_IO 0x00008000 /* Last insn may be an IO access. */ -#define CF_MEMI_ONLY 0x00010000 /* Only instrument memory ops */ -#define CF_USE_ICOUNT 0x00020000 -#define CF_INVALID 0x00040000 /* TB is stale. Set with @jmp_lock held */ -#define CF_PARALLEL 0x00080000 /* Generate code for a parallel context */ -#define CF_NOIRQ 0x00100000 /* Generate an uninterruptible TB */ -#define CF_PCREL 0x00200000 /* Opcodes in TB are PC-relative */ -#define CF_CLUSTER_MASK 0xff000000 /* Top 8 bits are cluster ID */ -#define CF_CLUSTER_SHIFT 24 - - /* - * Above fields used for comparing - */ - - /* size of target code for this block (1 <= size <= TARGET_PAGE_SIZE) */ - uint16_t size; - uint16_t icount; - - struct tb_tc tc; - - /* - * Track tb_page_addr_t intervals that intersect this TB. - * For user-only, the virtual addresses are always contiguous, - * and we use a unified interval tree. For system, we use a - * linked list headed in each PageDesc. Within the list, the lsb - * of the previous pointer tells the index of page_next[], and the - * list is protected by the PageDesc lock(s). - */ -#ifdef CONFIG_USER_ONLY - IntervalTreeNode itree; -#else - uintptr_t page_next[2]; - tb_page_addr_t page_addr[2]; -#endif - - /* jmp_lock placed here to fill a 4-byte hole. Its documentation is below */ - QemuSpin jmp_lock; - - /* The following data are used to directly call another TB from - * the code of this one. This can be done either by emitting direct or - * indirect native jump instructions. These jumps are reset so that the TB - * just continues its execution. The TB can be linked to another one by - * setting one of the jump targets (or patching the jump instruction). Only - * two of such jumps are supported. - */ -#define TB_JMP_OFFSET_INVALID 0xffff /* indicates no jump generated */ - uint16_t jmp_reset_offset[2]; /* offset of original jump target */ - uint16_t jmp_insn_offset[2]; /* offset of direct jump insn */ - uintptr_t jmp_target_addr[2]; /* target address */ - - /* - * Each TB has a NULL-terminated list (jmp_list_head) of incoming jumps. - * Each TB can have two outgoing jumps, and therefore can participate - * in two lists. The list entries are kept in jmp_list_next[2]. The least - * significant bit (LSB) of the pointers in these lists is used to encode - * which of the two list entries is to be used in the pointed TB. - * - * List traversals are protected by jmp_lock. The destination TB of each - * outgoing jump is kept in jmp_dest[] so that the appropriate jmp_lock - * can be acquired from any origin TB. - * - * jmp_dest[] are tagged pointers as well. The LSB is set when the TB is - * being invalidated, so that no further outgoing jumps from it can be set. - * - * jmp_lock also protects the CF_INVALID cflag; a jump must not be chained - * to a destination TB that has CF_INVALID set. - */ - uintptr_t jmp_list_head; - uintptr_t jmp_list_next[2]; - uintptr_t jmp_dest[2]; -}; - /* Hide the qatomic_read to make code a little easier on the eyes */ static inline uint32_t tb_cflags(const TranslationBlock *tb) { diff --git a/include/exec/translation-block.h b/include/exec/translation-block.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/exec/translation-block.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: LGPL-2.1-or-later */ +/* + * Definition of TranslationBlock. + * Copyright (c) 2003 Fabrice Bellard + */ + +#ifndef EXEC_TRANSLATION_BLOCK_H +#define EXEC_TRANSLATION_BLOCK_H + +#include "qemu/atomic.h" +#include "qemu/thread.h" +#include "qemu/interval-tree.h" +#include "exec/cpu-common.h" +#include "exec/target_page.h" + +/* + * Page tracking code uses ram addresses in system mode, and virtual + * addresses in userspace mode. Define tb_page_addr_t to be an + * appropriate type. + */ +#if defined(CONFIG_USER_ONLY) +typedef vaddr tb_page_addr_t; +#define TB_PAGE_ADDR_FMT "%" VADDR_PRIx +#else +typedef ram_addr_t tb_page_addr_t; +#define TB_PAGE_ADDR_FMT RAM_ADDR_FMT +#endif + +/* + * Translation Cache-related fields of a TB. + * This struct exists just for convenience; we keep track of TB's in a binary + * search tree, and the only fields needed to compare TB's in the tree are + * @ptr and @size. + * Note: the address of search data can be obtained by adding @size to @ptr. + */ +struct tb_tc { + const void *ptr; /* pointer to the translated code */ + size_t size; +}; + +struct TranslationBlock { + /* + * Guest PC corresponding to this block. This must be the true + * virtual address. Therefore e.g. x86 stores EIP + CS_BASE, and + * targets like Arm, MIPS, HP-PA, which reuse low bits for ISA or + * privilege, must store those bits elsewhere. + * + * If CF_PCREL, the opcodes for the TranslationBlock are written + * such that the TB is associated only with the physical page and + * may be run in any virtual address context. In this case, PC + * must always be taken from ENV in a target-specific manner. + * Unwind information is taken as offsets from the page, to be + * deposited into the "current" PC. + */ + vaddr pc; + + /* + * Target-specific data associated with the TranslationBlock, e.g.: + * x86: the original user, the Code Segment virtual base, + * arm: an extension of tb->flags, + * s390x: instruction data for EXECUTE, + * sparc: the next pc of the instruction queue (for delay slots). + */ + uint64_t cs_base; + + uint32_t flags; /* flags defining in which context the code was generated */ + uint32_t cflags; /* compile flags */ + +/* Note that TCG_MAX_INSNS is 512; we validate this match elsewhere. */ +#define CF_COUNT_MASK 0x000001ff +#define CF_NO_GOTO_TB 0x00000200 /* Do not chain with goto_tb */ +#define CF_NO_GOTO_PTR 0x00000400 /* Do not chain with goto_ptr */ +#define CF_SINGLE_STEP 0x00000800 /* gdbstub single-step in effect */ +#define CF_LAST_IO 0x00008000 /* Last insn may be an IO access. */ +#define CF_MEMI_ONLY 0x00010000 /* Only instrument memory ops */ +#define CF_USE_ICOUNT 0x00020000 +#define CF_INVALID 0x00040000 /* TB is stale. Set with @jmp_lock held */ +#define CF_PARALLEL 0x00080000 /* Generate code for a parallel context */ +#define CF_NOIRQ 0x00100000 /* Generate an uninterruptible TB */ +#define CF_PCREL 0x00200000 /* Opcodes in TB are PC-relative */ +#define CF_CLUSTER_MASK 0xff000000 /* Top 8 bits are cluster ID */ +#define CF_CLUSTER_SHIFT 24 + + /* + * Above fields used for comparing + */ + + /* size of target code for this block (1 <= size <= TARGET_PAGE_SIZE) */ + uint16_t size; + uint16_t icount; + + struct tb_tc tc; + + /* + * Track tb_page_addr_t intervals that intersect this TB. + * For user-only, the virtual addresses are always contiguous, + * and we use a unified interval tree. For system, we use a + * linked list headed in each PageDesc. Within the list, the lsb + * of the previous pointer tells the index of page_next[], and the + * list is protected by the PageDesc lock(s). + */ +#ifdef CONFIG_USER_ONLY + IntervalTreeNode itree; +#else + uintptr_t page_next[2]; + tb_page_addr_t page_addr[2]; +#endif + + /* jmp_lock placed here to fill a 4-byte hole. Its documentation is below */ + QemuSpin jmp_lock; + + /* The following data are used to directly call another TB from + * the code of this one. This can be done either by emitting direct or + * indirect native jump instructions. These jumps are reset so that the TB + * just continues its execution. The TB can be linked to another one by + * setting one of the jump targets (or patching the jump instruction). Only + * two of such jumps are supported. + */ +#define TB_JMP_OFFSET_INVALID 0xffff /* indicates no jump generated */ + uint16_t jmp_reset_offset[2]; /* offset of original jump target */ + uint16_t jmp_insn_offset[2]; /* offset of direct jump insn */ + uintptr_t jmp_target_addr[2]; /* target address */ + + /* + * Each TB has a NULL-terminated list (jmp_list_head) of incoming jumps. + * Each TB can have two outgoing jumps, and therefore can participate + * in two lists. The list entries are kept in jmp_list_next[2]. The least + * significant bit (LSB) of the pointers in these lists is used to encode + * which of the two list entries is to be used in the pointed TB. + * + * List traversals are protected by jmp_lock. The destination TB of each + * outgoing jump is kept in jmp_dest[] so that the appropriate jmp_lock + * can be acquired from any origin TB. + * + * jmp_dest[] are tagged pointers as well. The LSB is set when the TB is + * being invalidated, so that no further outgoing jumps from it can be set. + * + * jmp_lock also protects the CF_INVALID cflag; a jump must not be chained + * to a destination TB that has CF_INVALID set. + */ + uintptr_t jmp_list_head; + uintptr_t jmp_list_next[2]; + uintptr_t jmp_dest[2]; +}; + +/* The alignment given to TranslationBlock during allocation. */ +#define CODE_GEN_ALIGN 16 + +#endif /* EXEC_TRANSLATION_BLOCK_H */ diff --git a/tcg/tcg-op-ldst.c b/tcg/tcg-op-ldst.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-ldst.c +++ b/tcg/tcg-op-ldst.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "exec/exec-all.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" #include "tcg/tcg-op-common.h" #include "tcg/tcg-mo.h" +#include "exec/translation-block.h" #include "exec/plugin-gen.h" #include "tcg-internal.h" -- 2.34.1 The last use was removed with 2ac01d6dafab. Fixes: 2ac01d6dafab ("translate-all: use a binary search tree to track TBs in TBContext") Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ int probe_access_full(CPUArchState *env, target_ulong addr, int size, CPUTLBEntryFull **pfull, uintptr_t retaddr); #endif -/* Estimated block size for TB allocation. */ -/* ??? The following is based on a 2015 survey of x86_64 host output. - Better would seem to be some sort of dynamically sized TB array, - adapting to the block sizes actually being produced. */ -#if defined(CONFIG_SOFTMMU) -#define CODE_GEN_AVG_BLOCK_SIZE 400 -#else -#define CODE_GEN_AVG_BLOCK_SIZE 150 -#endif - /* Hide the qatomic_read to make code a little easier on the eyes */ static inline uint32_t tb_cflags(const TranslationBlock *tb) { -- 2.34.1 The only usage of gen_tb_start and gen_tb_end are here. Move the static icount_start_insn variable into a local within translator_loop. Simplify the two subroutines by passing in the existing local cflags variable. Leave only the declaration of gen_io_start in gen-icount.h. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/gen-icount.h | 79 +------------------------------------ accel/tcg/translator.c | 83 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 82 insertions(+), 80 deletions(-) diff --git a/include/exec/gen-icount.h b/include/exec/gen-icount.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/gen-icount.h +++ b/include/exec/gen-icount.h @@ -XXX,XX +XXX,XX @@ #ifndef GEN_ICOUNT_H #define GEN_ICOUNT_H -#include "exec/exec-all.h" - -/* Helpers for instruction counting code generation. */ - -static TCGOp *icount_start_insn; - -static inline void gen_io_start(void) -{ - tcg_gen_st_i32(tcg_constant_i32(1), cpu_env, - offsetof(ArchCPU, parent_obj.can_do_io) - - offsetof(ArchCPU, env)); -} - -static inline void gen_tb_start(const TranslationBlock *tb) -{ - TCGv_i32 count = tcg_temp_new_i32(); - - tcg_gen_ld_i32(count, cpu_env, - offsetof(ArchCPU, neg.icount_decr.u32) - - offsetof(ArchCPU, env)); - - if (tb_cflags(tb) & CF_USE_ICOUNT) { - /* - * We emit a sub with a dummy immediate argument. Keep the insn index - * of the sub so that we later (when we know the actual insn count) - * can update the argument with the actual insn count. - */ - tcg_gen_sub_i32(count, count, tcg_constant_i32(0)); - icount_start_insn = tcg_last_op(); - } - - /* - * Emit the check against icount_decr.u32 to see if we should exit - * unless we suppress the check with CF_NOIRQ. If we are using - * icount and have suppressed interruption the higher level code - * should have ensured we don't run more instructions than the - * budget. - */ - if (tb_cflags(tb) & CF_NOIRQ) { - tcg_ctx->exitreq_label = NULL; - } else { - tcg_ctx->exitreq_label = gen_new_label(); - tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, tcg_ctx->exitreq_label); - } - - if (tb_cflags(tb) & CF_USE_ICOUNT) { - tcg_gen_st16_i32(count, cpu_env, - offsetof(ArchCPU, neg.icount_decr.u16.low) - - offsetof(ArchCPU, env)); - /* - * cpu->can_do_io is cleared automatically here at the beginning of - * each translation block. The cost is minimal and only paid for - * -icount, plus it would be very easy to forget doing it in the - * translator. Doing it here means we don't need a gen_io_end() to - * go with gen_io_start(). - */ - tcg_gen_st_i32(tcg_constant_i32(0), cpu_env, - offsetof(ArchCPU, parent_obj.can_do_io) - - offsetof(ArchCPU, env)); - } -} - -static inline void gen_tb_end(const TranslationBlock *tb, int num_insns) -{ - if (tb_cflags(tb) & CF_USE_ICOUNT) { - /* - * Update the num_insn immediate parameter now that we know - * the actual insn count. - */ - tcg_set_insn_param(icount_start_insn, 2, - tcgv_i32_arg(tcg_constant_i32(num_insns))); - } - - if (tcg_ctx->exitreq_label) { - gen_set_label(tcg_ctx->exitreq_label); - tcg_gen_exit_tb(tb, TB_EXIT_REQUESTED); - } -} +void gen_io_start(void); #endif diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ #include "exec/plugin-gen.h" #include "exec/replay-core.h" + +void gen_io_start(void) +{ + tcg_gen_st_i32(tcg_constant_i32(1), cpu_env, + offsetof(ArchCPU, parent_obj.can_do_io) - + offsetof(ArchCPU, env)); +} + +static TCGOp *gen_tb_start(uint32_t cflags) +{ + TCGv_i32 count = tcg_temp_new_i32(); + TCGOp *icount_start_insn = NULL; + + tcg_gen_ld_i32(count, cpu_env, + offsetof(ArchCPU, neg.icount_decr.u32) - + offsetof(ArchCPU, env)); + + if (cflags & CF_USE_ICOUNT) { + /* + * We emit a sub with a dummy immediate argument. Keep the insn index + * of the sub so that we later (when we know the actual insn count) + * can update the argument with the actual insn count. + */ + tcg_gen_sub_i32(count, count, tcg_constant_i32(0)); + icount_start_insn = tcg_last_op(); + } + + /* + * Emit the check against icount_decr.u32 to see if we should exit + * unless we suppress the check with CF_NOIRQ. If we are using + * icount and have suppressed interruption the higher level code + * should have ensured we don't run more instructions than the + * budget. + */ + if (cflags & CF_NOIRQ) { + tcg_ctx->exitreq_label = NULL; + } else { + tcg_ctx->exitreq_label = gen_new_label(); + tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, tcg_ctx->exitreq_label); + } + + if (cflags & CF_USE_ICOUNT) { + tcg_gen_st16_i32(count, cpu_env, + offsetof(ArchCPU, neg.icount_decr.u16.low) - + offsetof(ArchCPU, env)); + /* + * cpu->can_do_io is cleared automatically here at the beginning of + * each translation block. The cost is minimal and only paid for + * -icount, plus it would be very easy to forget doing it in the + * translator. Doing it here means we don't need a gen_io_end() to + * go with gen_io_start(). + */ + tcg_gen_st_i32(tcg_constant_i32(0), cpu_env, + offsetof(ArchCPU, parent_obj.can_do_io) - + offsetof(ArchCPU, env)); + } + + return icount_start_insn; +} + +static void gen_tb_end(const TranslationBlock *tb, uint32_t cflags, + TCGOp *icount_start_insn, int num_insns) +{ + if (cflags & CF_USE_ICOUNT) { + /* + * Update the num_insn immediate parameter now that we know + * the actual insn count. + */ + tcg_set_insn_param(icount_start_insn, 2, + tcgv_i32_arg(tcg_constant_i32(num_insns))); + } + + if (tcg_ctx->exitreq_label) { + gen_set_label(tcg_ctx->exitreq_label); + tcg_gen_exit_tb(tb, TB_EXIT_REQUESTED); + } +} + bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest) { /* Suppress goto_tb if requested. */ @@ -XXX,XX +XXX,XX @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, const TranslatorOps *ops, DisasContextBase *db) { uint32_t cflags = tb_cflags(tb); + TCGOp *icount_start_insn; bool plugin_enabled; /* Initialize DisasContext */ @@ -XXX,XX +XXX,XX @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ /* Start translating. */ - gen_tb_start(db->tb); + icount_start_insn = gen_tb_start(cflags); ops->tb_start(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ @@ -XXX,XX +XXX,XX @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, /* Emit code to exit the TB, as indicated by db->is_jmp. */ ops->tb_stop(db, cpu); - gen_tb_end(db->tb, db->num_insns); + gen_tb_end(tb, cflags, icount_start_insn, db->num_insns); if (plugin_enabled) { plugin_gen_tb_end(cpu); -- 2.34.1 New wrapper around gen_io_start which takes care of the USE_ICOUNT check, as well as marking the DisasContext to end the TB. Remove exec/gen-icount.h. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- MAINTAINERS | 1 - include/exec/gen-icount.h | 6 -- include/exec/translator.h | 10 +++ target/arm/cpregs.h | 4 +- accel/tcg/translator.c | 27 ++++++- target/alpha/translate.c | 15 +--- target/arm/tcg/translate-a64.c | 23 +++--- target/arm/tcg/translate-mve.c | 1 - target/arm/tcg/translate-neon.c | 1 - target/arm/tcg/translate-vfp.c | 4 +- target/arm/tcg/translate.c | 20 ++--- target/avr/translate.c | 1 - target/cris/translate.c | 2 - target/hppa/translate.c | 5 +- target/i386/tcg/translate.c | 52 +++---------- target/loongarch/translate.c | 2 - target/m68k/translate.c | 2 - target/microblaze/translate.c | 2 - target/mips/tcg/translate.c | 29 +++---- target/nios2/translate.c | 1 - target/openrisc/translate.c | 9 +-- target/ppc/translate.c | 13 +--- target/riscv/translate.c | 2 - target/rx/translate.c | 2 - target/s390x/tcg/translate.c | 6 +- target/sh4/translate.c | 2 - target/sparc/translate.c | 75 +++++-------------- target/tricore/translate.c | 2 - target/xtensa/translate.c | 27 ++----- target/loongarch/insn_trans/trans_extra.c.inc | 4 +- .../insn_trans/trans_privileged.c.inc | 4 +- .../riscv/insn_trans/trans_privileged.c.inc | 8 +- target/riscv/insn_trans/trans_rvi.c.inc | 24 ++---- 33 files changed, 117 insertions(+), 269 deletions(-) delete mode 100644 include/exec/gen-icount.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: ui/cocoa.m Main loop M: Paolo Bonzini <pbonzini@redhat.com> S: Maintained -F: include/exec/gen-icount.h F: include/qemu/main-loop.h F: include/sysemu/runstate.h F: include/sysemu/runstate-action.h diff --git a/include/exec/gen-icount.h b/include/exec/gen-icount.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/exec/gen-icount.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -#ifndef GEN_ICOUNT_H -#define GEN_ICOUNT_H - -void gen_io_start(void); - -#endif diff --git a/include/exec/translator.h b/include/exec/translator.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -XXX,XX +XXX,XX @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, */ bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest); +/** + * translator_io_start + * @db: Disassembly context + * + * If icount is enabled, set cpu->can_to_io, adjust db->is_jmp to + * DISAS_TOO_MANY if it is still DISAS_NEXT, and return true. + * Otherwise return false. + */ +bool translator_io_start(DisasContextBase *db); + /* * Translator Load Functions * diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -XXX,XX +XXX,XX @@ enum { ARM_CP_ALIAS = 1 << 8, /* * Flag: Register does I/O and therefore its accesses need to be marked - * with gen_io_start() and also end the TB. In particular, registers which - * implement clocks or timers require this. + * with translator_io_start() and also end the TB. In particular, + * registers which implement clocks or timers require this. */ ARM_CP_IO = 1 << 9, /* diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg.h" #include "tcg/tcg-op.h" #include "exec/exec-all.h" -#include "exec/gen-icount.h" #include "exec/log.h" #include "exec/translator.h" #include "exec/plugin-gen.h" #include "exec/replay-core.h" -void gen_io_start(void) +static void gen_io_start(void) { tcg_gen_st_i32(tcg_constant_i32(1), cpu_env, offsetof(ArchCPU, parent_obj.can_do_io) - offsetof(ArchCPU, env)); } +bool translator_io_start(DisasContextBase *db) +{ + uint32_t cflags = tb_cflags(db->tb); + + if (!(cflags & CF_USE_ICOUNT)) { + return false; + } + if (db->num_insns == db->max_insns && (cflags & CF_LAST_IO)) { + /* Already started in translator_loop. */ + return true; + } + + gen_io_start(); + + /* + * Ensure that this instruction will be the last in the TB. + * The target may override this to something more forceful. + */ + if (db->is_jmp == DISAS_NEXT) { + db->is_jmp = DISAS_TOO_MANY; + } + return true; +} + static TCGOp *gen_tb_start(uint32_t cflags) { TCGv_i32 count = tcg_temp_new_i32(); diff --git a/target/alpha/translate.c b/target/alpha/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/translate.c +++ b/target/alpha/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_lock_value; static TCGv cpu_pal_ir[31]; #endif -#include "exec/gen-icount.h" - void alpha_translate_init(void) { #define DEF_VAR(V) { &cpu_##V, #V, offsetof(CPUAlphaState, V) } @@ -XXX,XX +XXX,XX @@ static DisasJumpType gen_mfpr(DisasContext *ctx, TCGv va, int regno) case 249: /* VMTIME */ helper = gen_helper_get_vmtime; do_helper: - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&ctx->base)) { helper(va); return DISAS_PC_STALE; } else { @@ -XXX,XX +XXX,XX @@ static DisasJumpType gen_mtpr(DisasContext *ctx, TCGv vb, int regno) case 251: /* ALARM */ - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&ctx->base)) { ret = DISAS_PC_STALE; } gen_helper_set_alarm(cpu_env, vb); @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) case 0xC000: /* RPCC */ va = dest_gpr(ctx, ra); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - gen_helper_load_pcc(va, cpu_env); + if (translator_io_start(&ctx->base)) { ret = DISAS_PC_STALE; - } else { - gen_helper_load_pcc(va, cpu_env); } + gen_helper_load_pcc(va, cpu_env); break; case 0xE000: /* RC */ diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ #include "internals.h" #include "qemu/host-utils.h" #include "semihosting/semihost.h" -#include "exec/gen-icount.h" #include "exec/log.h" #include "cpregs.h" #include "translate-a64.h" @@ -XXX,XX +XXX,XX @@ static bool trans_ERET(DisasContext *s, arg_ERET *a) tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUARMState, elr_el[s->current_el])); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&s->base); gen_helper_exception_return(cpu_env, dst); /* Must exit loop to check un-masked IRQs */ @@ -XXX,XX +XXX,XX @@ static bool trans_ERETA(DisasContext *s, arg_reta *a) offsetof(CPUARMState, elr_el[s->current_el])); dst = auth_branch_target(s, dst, cpu_X[31], !a->m); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + + translator_io_start(&s->base); gen_helper_exception_return(cpu_env, dst); /* Must exit loop to check un-masked IRQs */ @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, uint32_t key = ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP, crn, crm, op0, op1, op2); const ARMCPRegInfo *ri = get_arm_cp_reginfo(s->cp_regs, key); + bool need_exit_tb = false; TCGv_ptr tcg_ri = NULL; TCGv_i64 tcg_rt; @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, return; } - if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { - gen_io_start(); + if (ri->type & ARM_CP_IO) { + /* I/O operations must end the TB here (whether read or write) */ + need_exit_tb = translator_io_start(&s->base); } tcg_rt = cpu_reg(s, rt); @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, } } - if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { - /* I/O operations must end the TB here (whether read or write) */ - s->base.is_jmp = DISAS_UPDATE_EXIT; - } if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { /* * A write to any coprocessor regiser that ends a TB @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, * but allow this to be suppressed by the register definition * (usually only necessary to work around guest bugs). */ + need_exit_tb = true; + } + if (need_exit_tb) { s->base.is_jmp = DISAS_UPDATE_EXIT; } } diff --git a/target/arm/tcg/translate-mve.c b/target/arm/tcg/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-mve.c +++ b/target/arm/tcg/translate-mve.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" #include "exec/exec-all.h" -#include "exec/gen-icount.h" #include "translate.h" #include "translate-a32.h" diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" #include "exec/exec-all.h" -#include "exec/gen-icount.h" #include "translate.h" #include "translate-a32.h" diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" #include "exec/exec-all.h" -#include "exec/gen-icount.h" #include "translate.h" #include "translate-a32.h" @@ -XXX,XX +XXX,XX @@ static void gen_preserve_fp_state(DisasContext *s, bool skip_context_update) * so we must mark it as an IO operation for icount (and cause * this to be the last insn in the TB). */ - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { + if (translator_io_start(&s->base)) { s->base.is_jmp = DISAS_UPDATE_EXIT; - gen_io_start(); } gen_helper_v7m_preserve_fp_state(cpu_env); /* diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpregs.h" #include "translate.h" #include "translate-a32.h" -#include "exec/gen-icount.h" #include "exec/helper-proto.h" #define HELPER_H "helper.h" @@ -XXX,XX +XXX,XX @@ static void gen_rfe(DisasContext *s, TCGv_i32 pc, TCGv_i32 cpsr) * appropriately depending on the new Thumb bit, so it must * be called after storing the new PC. */ - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&s->base); gen_helper_cpsr_write_eret(cpu_env, cpsr); /* Must exit loop to check un-masked IRQs */ s->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, uint32_t key = ENCODE_CP_REG(cpnum, is64, s->ns, crn, crm, opc1, opc2); const ARMCPRegInfo *ri = get_arm_cp_reginfo(s->cp_regs, key); TCGv_ptr tcg_ri = NULL; - bool need_exit_tb; + bool need_exit_tb = false; uint32_t syndrome; /* @@ -XXX,XX +XXX,XX @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, g_assert_not_reached(); } - if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { - gen_io_start(); + if (ri->type & ARM_CP_IO) { + /* I/O operations must end the TB here (whether read or write) */ + need_exit_tb = translator_io_start(&s->base); } if (isread) { @@ -XXX,XX +XXX,XX @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, } } - /* I/O operations must end the TB here (whether read or write) */ - need_exit_tb = ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && - (ri->type & ARM_CP_IO)); - if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { /* * A write to any coprocessor register that ends a TB @@ -XXX,XX +XXX,XX @@ static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n) if (exc_return) { /* Restore CPSR from SPSR. */ tmp = load_cpu_field(spsr); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&s->base); gen_helper_cpsr_write_eret(cpu_env, tmp); /* Must exit loop to check un-masked IRQs */ s->base.is_jmp = DISAS_EXIT; diff --git a/target/avr/translate.c b/target/avr/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/translate.c +++ b/target/avr/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-gen.h" #include "exec/log.h" #include "exec/translator.h" -#include "exec/gen-icount.h" #define HELPER_H "helper.h" #include "exec/helper-info.c.inc" diff --git a/target/cris/translate.c b/target/cris/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/cris/translate.c +++ b/target/cris/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv env_btaken; static TCGv env_btarget; static TCGv env_pc; -#include "exec/gen-icount.h" - /* This is the state at translation time. */ typedef struct DisasContext { DisasContextBase base; diff --git a/target/hppa/translate.c b/target/hppa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/translate.c +++ b/target/hppa/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_reg cpu_psw_v; static TCGv_reg cpu_psw_cb; static TCGv_reg cpu_psw_cb_msb; -#include "exec/gen-icount.h" - void hppa_translate_init(void) { #define DEF_VAR(V) { &cpu_##V, #V, offsetof(CPUHPPAState, V) } @@ -XXX,XX +XXX,XX @@ static bool trans_mfctl(DisasContext *ctx, arg_mfctl *a) /* FIXME: Respect PSW_S bit. */ nullify_over(ctx); tmp = dest_gpr(ctx, rt); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&ctx->base)) { gen_helper_read_interval_timer(tmp); ctx->base.is_jmp = DISAS_IAQ_N_STALE; } else { diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_seg_base[6]; static TCGv_i64 cpu_bndl[4]; static TCGv_i64 cpu_bndu[4]; -#include "exec/gen-icount.h" - typedef struct DisasContext { DisasContextBase base; @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) !(s->cpuid_ext_features & CPUID_EXT_RDRAND)) { goto illegal_op; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_helper_rdrand(s->T0, cpu_env); rm = (modrm & 7) | REX_B(s); gen_op_mov_reg_v(s, dflag, rm, s->T0); @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) SVM_IOIO_TYPE_MASK | SVM_IOIO_STR_MASK)) { break; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); if (prefixes & (PREFIX_REPZ | PREFIX_REPNZ)) { gen_repz_ins(s, ot); } else { @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) if (!gen_check_io(s, ot, s->tmp2_i32, SVM_IOIO_STR_MASK)) { break; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); if (prefixes & (PREFIX_REPZ | PREFIX_REPNZ)) { gen_repz_outs(s, ot); } else { @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) if (!gen_check_io(s, ot, s->tmp2_i32, SVM_IOIO_TYPE_MASK)) { break; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_helper_in_func(ot, s->T1, s->tmp2_i32); gen_op_mov_reg_v(s, ot, R_EAX, s->T1); gen_bpt_io(s, s->tmp2_i32, ot); @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) if (!gen_check_io(s, ot, s->tmp2_i32, 0)) { break; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_op_mov_v_reg(s, ot, s->T1, R_EAX); tcg_gen_trunc_tl_i32(s->tmp3_i32, s->T1); gen_helper_out_func(ot, s->tmp2_i32, s->tmp3_i32); @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) if (!gen_check_io(s, ot, s->tmp2_i32, SVM_IOIO_TYPE_MASK)) { break; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_helper_in_func(ot, s->T1, s->tmp2_i32); gen_op_mov_reg_v(s, ot, R_EAX, s->T1); gen_bpt_io(s, s->tmp2_i32, ot); @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) if (!gen_check_io(s, ot, s->tmp2_i32, 0)) { break; } - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_op_mov_v_reg(s, ot, s->T1, R_EAX); tcg_gen_trunc_tl_i32(s->tmp3_i32, s->T1); gen_helper_out_func(ot, s->tmp2_i32, s->tmp3_i32); @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) case 0x131: /* rdtsc */ gen_update_cc_op(s); gen_update_eip_cur(s); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_helper_rdtsc(cpu_env); break; case 0x133: /* rdpmc */ @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) } gen_update_cc_op(s); gen_update_eip_cur(s); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); gen_helper_rdtscp(cpu_env); break; @@ -XXX,XX +XXX,XX @@ static bool disas_insn(DisasContext *s, CPUState *cpu) } ot = (CODE64(s) ? MO_64 : MO_32); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - s->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&s->base); if (b & 2) { gen_svm_check_intercept(s, SVM_EXIT_WRITE_CR0 + reg); gen_op_mov_v_reg(s, ot, s->T0, rm); diff --git a/target/loongarch/translate.c b/target/loongarch/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/translate.c +++ b/target/loongarch/translate.c @@ -XXX,XX +XXX,XX @@ TCGv cpu_gpr[32], cpu_pc; static TCGv cpu_lladdr, cpu_llval; -#include "exec/gen-icount.h" - #define HELPER_H "helper.h" #include "exec/helper-info.c.inc" #undef HELPER_H diff --git a/target/m68k/translate.c b/target/m68k/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv NULL_QREG; /* Used to distinguish stores from bad addressing modes. */ static TCGv store_dummy; -#include "exec/gen-icount.h" - void m68k_tcg_init(void) { char *p; diff --git a/target/microblaze/translate.c b/target/microblaze/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/translate.c +++ b/target/microblaze/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 cpu_iflags; static TCGv cpu_res_addr; static TCGv_i32 cpu_res_val; -#include "exec/gen-icount.h" - /* This is the state at translation time. */ typedef struct DisasContext { DisasContextBase base; diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.c +++ b/target/mips/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 hflags; TCGv_i32 fpu_fcr0, fpu_fcr31; TCGv_i64 fpu_f64[32]; -#include "exec/gen-icount.h" - static const char regnames_HI[][4] = { "HI0", "HI1", "HI2", "HI3", }; @@ -XXX,XX +XXX,XX @@ static void gen_mfc0(DisasContext *ctx, TCGv arg, int reg, int sel) switch (sel) { case CP0_REG09__COUNT: /* Mark as an IO operation because we read the time. */ - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); + gen_helper_mfc0_count(arg, cpu_env); /* * Break the TB to be able to take timer interrupts immediately @@ -XXX,XX +XXX,XX @@ cp0_unimplemented: static void gen_mtc0(DisasContext *ctx, TCGv arg, int reg, int sel) { const char *register_name = "invalid"; + bool icount; if (sel != 0) { check_insn(ctx, ISA_MIPS_R1); } - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + icount = translator_io_start(&ctx->base); switch (reg) { case CP0_REGISTER_00: @@ -XXX,XX +XXX,XX @@ static void gen_mtc0(DisasContext *ctx, TCGv arg, int reg, int sel) trace_mips_translate_c0("mtc0", register_name, reg, sel); /* For simplicity assume that all writes can cause interrupts. */ - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + if (icount) { /* * DISAS_STOP isn't sufficient, we need to ensure we break out of * translated code to check for pending interrupts. @@ -XXX,XX +XXX,XX @@ static void gen_dmfc0(DisasContext *ctx, TCGv arg, int reg, int sel) switch (sel) { case CP0_REG09__COUNT: /* Mark as an IO operation because we read the time. */ - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_mfc0_count(arg, cpu_env); /* * Break the TB to be able to take timer interrupts immediately @@ -XXX,XX +XXX,XX @@ cp0_unimplemented: static void gen_dmtc0(DisasContext *ctx, TCGv arg, int reg, int sel) { const char *register_name = "invalid"; + bool icount; if (sel != 0) { check_insn(ctx, ISA_MIPS_R1); } - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + icount = translator_io_start(&ctx->base); switch (reg) { case CP0_REGISTER_00: @@ -XXX,XX +XXX,XX @@ static void gen_dmtc0(DisasContext *ctx, TCGv arg, int reg, int sel) trace_mips_translate_c0("dmtc0", register_name, reg, sel); /* For simplicity assume that all writes can cause interrupts. */ - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + if (icount) { /* * DISAS_STOP isn't sufficient, we need to ensure we break out of * translated code to check for pending interrupts. @@ -XXX,XX +XXX,XX @@ void gen_rdhwr(DisasContext *ctx, int rt, int rd, int sel) gen_store_gpr(t0, rt); break; case 2: - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_rdhwr_cc(t0, cpu_env); gen_store_gpr(t0, rt); /* diff --git a/target/nios2/translate.c b/target/nios2/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/translate.c +++ b/target/nios2/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "exec/translator.h" #include "qemu/qemu-print.h" -#include "exec/gen-icount.h" #include "semihosting/semihost.h" #define HELPER_H "helper.h" diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/translate.c +++ b/target/openrisc/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "exec/helper-gen.h" -#include "exec/gen-icount.h" #include "exec/log.h" @@ -XXX,XX +XXX,XX @@ static bool trans_l_mfspr(DisasContext *dc, arg_l_mfspr *a) check_r0_write(dc, a->d); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&dc->base)) { if (dc->delayed_branch) { tcg_gen_mov_tl(cpu_pc, jmp_pc); tcg_gen_discard_tl(jmp_pc); @@ -XXX,XX +XXX,XX @@ static bool trans_l_mtspr(DisasContext *dc, arg_l_mtspr *a) { TCGv spr = tcg_temp_new(); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); + /* * For SR, we will need to exit the TB to recognize the new * exception state. For NPC, in theory this counts as a branch diff --git a/target/ppc/translate.c b/target/ppc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_reserve_val2; static TCGv cpu_fpscr; static TCGv_i32 cpu_access_type; -#include "exec/gen-icount.h" - void ppc_translate_init(void) { int i; @@ -XXX,XX +XXX,XX @@ static void gen_exception_nip(DisasContext *ctx, uint32_t excp, static void gen_icount_io_start(DisasContext *ctx) { - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - /* - * An I/O instruction must be last in the TB. - * Chain to the next TB, and let the code from gen_tb_start - * decide if we need to return to the main loop. - * Doing this first also allows this value to be overridden. - */ - ctx->base.is_jmp = DISAS_TOO_MANY; - } + translator_io_start(&ctx->base); } #if !defined(CONFIG_USER_ONLY) diff --git a/target/riscv/translate.c b/target/riscv/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv load_val; static TCGv pm_mask; static TCGv pm_base; -#include "exec/gen-icount.h" - /* * If an operation is being performed on less than TARGET_LONG_BITS, * it may require the inputs to be sign- or zero-extended; which will diff --git a/target/rx/translate.c b/target/rx/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/translate.c +++ b/target/rx/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i64 cpu_acc; #define cpu_sp cpu_regs[0] -#include "exec/gen-icount.h" - /* decoder helper */ static uint32_t decode_load_bytes(DisasContext *ctx, uint32_t insn, int i, int n) diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/tcg/translate.c +++ b/target/s390x/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "qemu/host-utils.h" #include "exec/cpu_ldst.h" -#include "exec/gen-icount.h" #include "exec/helper-proto.h" #include "exec/helper-gen.h" @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(CPUS390XState *env, DisasContext *s) /* input/output is the special case for icount mode */ if (unlikely(insn->flags & IF_IO)) { - icount = tb_cflags(s->base.tb) & CF_USE_ICOUNT; - if (icount) { - gen_io_start(); - } + icount = translator_io_start(&s->base); } } diff --git a/target/sh4/translate.c b/target/sh4/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_fregs[32]; /* internal register indexes */ static TCGv cpu_flags, cpu_delayed_pc, cpu_delayed_cond; -#include "exec/gen-icount.h" - void sh4_translate_init(void) { int i; diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_wim; /* Floating point registers */ static TCGv_i64 cpu_fpr[TARGET_DPREGS]; -#include "exec/gen-icount.h" - typedef struct DisasContext { DisasContextBase base; target_ulong pc; /* current Program Counter: integer or DYNAMIC_PC */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_const = tcg_constant_i32(dc->mem_idx); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, tick)); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&dc->base)) { + dc->base.is_jmp = DISAS_EXIT; } gen_helper_tick_get_count(cpu_dst, cpu_env, r_tickptr, r_const); gen_store_gpr(dc, rd, cpu_dst); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - /* I/O operations in icount mode must end the TB */ - dc->base.is_jmp = DISAS_EXIT; - } } break; case 0x5: /* V9 rdpc */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_const = tcg_constant_i32(dc->mem_idx); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, stick)); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&dc->base)) { + dc->base.is_jmp = DISAS_EXIT; } gen_helper_tick_get_count(cpu_dst, cpu_env, r_tickptr, r_const); gen_store_gpr(dc, rd, cpu_dst); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - /* I/O operations in icount mode must end the TB */ - dc->base.is_jmp = DISAS_EXIT; - } } break; case 0x19: /* System tick compare */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_const = tcg_constant_i32(dc->mem_idx); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, tick)); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); + if (translator_io_start(&dc->base)) { + dc->base.is_jmp = DISAS_EXIT; } gen_helper_tick_get_count(cpu_tmp0, cpu_env, r_tickptr, r_const); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - /* I/O operations in icount mode must end the TB */ - dc->base.is_jmp = DISAS_EXIT; - } } break; case 5: // tba @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_tickptr = tcg_temp_new_ptr(); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, tick)); - if (tb_cflags(dc->base.tb) & - CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_tick_set_limit(r_tickptr, cpu_tick_cmpr); /* End TB to handle timer interrupt */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_tickptr = tcg_temp_new_ptr(); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, stick)); - if (tb_cflags(dc->base.tb) & - CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_tick_set_count(r_tickptr, cpu_tmp0); /* End TB to handle timer interrupt */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_tickptr = tcg_temp_new_ptr(); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, stick)); - if (tb_cflags(dc->base.tb) & - CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_tick_set_limit(r_tickptr, cpu_stick_cmpr); /* End TB to handle timer interrupt */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_tickptr = tcg_temp_new_ptr(); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, tick)); - if (tb_cflags(dc->base.tb) & - CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_tick_set_count(r_tickptr, cpu_tmp0); /* End TB to handle timer interrupt */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) break; case 6: // pstate save_state(dc); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } - gen_helper_wrpstate(cpu_env, cpu_tmp0); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - /* I/O ops in icount mode must end the TB */ + if (translator_io_start(&dc->base)) { dc->base.is_jmp = DISAS_EXIT; } + gen_helper_wrpstate(cpu_env, cpu_tmp0); dc->npc = DYNAMIC_PC; break; case 7: // tl @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) dc->npc = DYNAMIC_PC; break; case 8: // pil - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } - gen_helper_wrpil(cpu_env, cpu_tmp0); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - /* I/O ops in icount mode must end the TB */ + if (translator_io_start(&dc->base)) { dc->base.is_jmp = DISAS_EXIT; } + gen_helper_wrpil(cpu_env, cpu_tmp0); break; case 9: // cwp gen_helper_wrcwp(cpu_env, cpu_tmp0); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) r_tickptr = tcg_temp_new_ptr(); tcg_gen_ld_ptr(r_tickptr, cpu_env, offsetof(CPUSPARCState, hstick)); - if (tb_cflags(dc->base.tb) & - CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_tick_set_limit(r_tickptr, cpu_hstick_cmpr); /* End TB to handle timer interrupt */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) goto priv_insn; dc->npc = DYNAMIC_PC; dc->pc = DYNAMIC_PC; - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_done(cpu_env); goto jmp_insn; case 1: @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) goto priv_insn; dc->npc = DYNAMIC_PC; dc->pc = DYNAMIC_PC; - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_retry(cpu_env); goto jmp_insn; default: diff --git a/target/tricore/translate.c b/target/tricore/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/translate.c +++ b/target/tricore/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv cpu_PSW_SV; static TCGv cpu_PSW_AV; static TCGv cpu_PSW_SAV; -#include "exec/gen-icount.h" - static const char *regnames_a[] = { "a0" , "a1" , "a2" , "a3" , "a4" , "a5" , "a6" , "a7" , "a8" , "a9" , "sp" , "a11" , diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/translate.c +++ b/target/xtensa/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 cpu_exclusive_val; static GHashTable *xtensa_regfile_table; -#include "exec/gen-icount.h" - static char *sr_name[256]; static char *ur_name[256]; @@ -XXX,XX +XXX,XX @@ static int gen_postprocess(DisasContext *dc, int slot) #ifndef CONFIG_USER_ONLY if (op_flags & XTENSA_OP_CHECK_INTERRUPTS) { - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_check_interrupts(cpu_env); } #endif @@ -XXX,XX +XXX,XX @@ static void translate_rsr_ccount(DisasContext *dc, const OpcodeArg arg[], const uint32_t par[]) { #ifndef CONFIG_USER_ONLY - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_update_ccount(cpu_env); tcg_gen_mov_i32(arg[0].out, cpu_SR[par[0]]); #endif @@ -XXX,XX +XXX,XX @@ static void translate_waiti(DisasContext *dc, const OpcodeArg arg[], #ifndef CONFIG_USER_ONLY TCGv_i32 pc = tcg_constant_i32(dc->base.pc_next); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_waiti(cpu_env, pc, tcg_constant_i32(arg[0].imm)); #endif } @@ -XXX,XX +XXX,XX @@ static void translate_wsr_ccompare(DisasContext *dc, const OpcodeArg arg[], uint32_t id = par[0] - CCOMPARE; assert(id < dc->config->nccompare); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); tcg_gen_mov_i32(cpu_SR[par[0]], arg[0].in); gen_helper_update_ccompare(cpu_env, tcg_constant_i32(id)); #endif @@ -XXX,XX +XXX,XX @@ static void translate_wsr_ccount(DisasContext *dc, const OpcodeArg arg[], const uint32_t par[]) { #ifndef CONFIG_USER_ONLY - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&dc->base); gen_helper_wsr_ccount(cpu_env, arg[0].in); #endif } @@ -XXX,XX +XXX,XX @@ static void translate_xsr_ccount(DisasContext *dc, const OpcodeArg arg[], #ifndef CONFIG_USER_ONLY TCGv_i32 tmp = tcg_temp_new_i32(); - if (tb_cflags(dc->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } - + translator_io_start(&dc->base); gen_helper_update_ccount(cpu_env); tcg_gen_mov_i32(tmp, cpu_SR[par[0]]); gen_helper_wsr_ccount(cpu_env, arg[0].in); diff --git a/target/loongarch/insn_trans/trans_extra.c.inc b/target/loongarch/insn_trans/trans_extra.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/insn_trans/trans_extra.c.inc +++ b/target/loongarch/insn_trans/trans_extra.c.inc @@ -XXX,XX +XXX,XX @@ static bool gen_rdtime(DisasContext *ctx, arg_rr *a, TCGv dst1 = gpr_dst(ctx, a->rd, EXT_NONE); TCGv dst2 = gpr_dst(ctx, a->rj, EXT_NONE); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_rdtime_d(dst1, cpu_env); if (word) { tcg_gen_sextract_tl(dst1, dst1, high ? 32 : 0, 32); diff --git a/target/loongarch/insn_trans/trans_privileged.c.inc b/target/loongarch/insn_trans/trans_privileged.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/insn_trans/trans_privileged.c.inc +++ b/target/loongarch/insn_trans/trans_privileged.c.inc @@ -XXX,XX +XXX,XX @@ static bool check_csr_flags(DisasContext *ctx, const CSRInfo *csr, bool write) if ((csr->flags & CSRFL_READONLY) && write) { return false; } - if ((csr->flags & CSRFL_IO) && - (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT)) { - gen_io_start(); + if ((csr->flags & CSRFL_IO) && translator_io_start(&ctx->base)) { ctx->base.is_jmp = DISAS_EXIT_UPDATE; } else if ((csr->flags & CSRFL_EXITTB) && write) { ctx->base.is_jmp = DISAS_EXIT_UPDATE; diff --git a/target/riscv/insn_trans/trans_privileged.c.inc b/target/riscv/insn_trans/trans_privileged.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/insn_trans/trans_privileged.c.inc +++ b/target/riscv/insn_trans/trans_privileged.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_sret(DisasContext *ctx, arg_sret *a) #ifndef CONFIG_USER_ONLY if (has_ext(ctx, RVS)) { decode_save_opc(ctx); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_sret(cpu_pc, cpu_env); exit_tb(ctx); /* no chaining */ ctx->base.is_jmp = DISAS_NORETURN; @@ -XXX,XX +XXX,XX @@ static bool trans_mret(DisasContext *ctx, arg_mret *a) { #ifndef CONFIG_USER_ONLY decode_save_opc(ctx); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_mret(cpu_pc, cpu_env); exit_tb(ctx); /* no chaining */ ctx->base.is_jmp = DISAS_NORETURN; diff --git a/target/riscv/insn_trans/trans_rvi.c.inc b/target/riscv/insn_trans/trans_rvi.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/insn_trans/trans_rvi.c.inc +++ b/target/riscv/insn_trans/trans_rvi.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_csrr(DisasContext *ctx, int rd, int rc) TCGv dest = dest_gpr(ctx, rd); TCGv_i32 csr = tcg_constant_i32(rc); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_csrr(dest, cpu_env, csr); gen_set_gpr(ctx, rd, dest); return do_csr_post(ctx); @@ -XXX,XX +XXX,XX @@ static bool do_csrw(DisasContext *ctx, int rc, TCGv src) { TCGv_i32 csr = tcg_constant_i32(rc); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_csrw(cpu_env, csr, src); return do_csr_post(ctx); } @@ -XXX,XX +XXX,XX @@ static bool do_csrrw(DisasContext *ctx, int rd, int rc, TCGv src, TCGv mask) TCGv dest = dest_gpr(ctx, rd); TCGv_i32 csr = tcg_constant_i32(rc); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_csrrw(dest, cpu_env, csr, src, mask); gen_set_gpr(ctx, rd, dest); return do_csr_post(ctx); @@ -XXX,XX +XXX,XX @@ static bool do_csrr_i128(DisasContext *ctx, int rd, int rc) TCGv desth = dest_gprh(ctx, rd); TCGv_i32 csr = tcg_constant_i32(rc); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_csrr_i128(destl, cpu_env, csr); tcg_gen_ld_tl(desth, cpu_env, offsetof(CPURISCVState, retxh)); gen_set_gpr128(ctx, rd, destl, desth); @@ -XXX,XX +XXX,XX @@ static bool do_csrw_i128(DisasContext *ctx, int rc, TCGv srcl, TCGv srch) { TCGv_i32 csr = tcg_constant_i32(rc); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_csrw_i128(cpu_env, csr, srcl, srch); return do_csr_post(ctx); } @@ -XXX,XX +XXX,XX @@ static bool do_csrrw_i128(DisasContext *ctx, int rd, int rc, TCGv desth = dest_gprh(ctx, rd); TCGv_i32 csr = tcg_constant_i32(rc); - if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { - gen_io_start(); - } + translator_io_start(&ctx->base); gen_helper_csrrw_i128(destl, cpu_env, csr, srcl, srch, maskl, maskh); tcg_gen_ld_tl(desth, cpu_env, offsetof(CPURISCVState, retxh)); gen_set_gpr128(ctx, rd, destl, desth); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Now that gen_icount_io_start() is a simple wrapper to translator_io_start(), inline it. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-Id: <20230602095439.48102-1-philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/ppc/translate.c | 63 ++++++++++++-------------- target/ppc/power8-pmu-regs.c.inc | 10 ++-- target/ppc/translate/branch-impl.c.inc | 2 +- 3 files changed, 35 insertions(+), 40 deletions(-) diff --git a/target/ppc/translate.c b/target/ppc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_exception_nip(DisasContext *ctx, uint32_t excp, ctx->base.is_jmp = DISAS_NORETURN; } -static void gen_icount_io_start(DisasContext *ctx) -{ - translator_io_start(&ctx->base); -} - #if !defined(CONFIG_USER_ONLY) static void gen_ppc_maybe_interrupt(DisasContext *ctx) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_ppc_maybe_interrupt(cpu_env); } #endif @@ -XXX,XX +XXX,XX @@ void spr_write_ureg(DisasContext *ctx, int sprn, int gprn) #if !defined(CONFIG_USER_ONLY) void spr_read_decr(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_decr(cpu_gpr[gprn], cpu_env); } void spr_write_decr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_decr(cpu_env, cpu_gpr[gprn]); } #endif @@ -XXX,XX +XXX,XX @@ void spr_write_decr(DisasContext *ctx, int sprn, int gprn) /* Time base */ void spr_read_tbl(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_tbl(cpu_gpr[gprn], cpu_env); } void spr_read_tbu(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_tbu(cpu_gpr[gprn], cpu_env); } @@ -XXX,XX +XXX,XX @@ void spr_read_atbu(DisasContext *ctx, int gprn, int sprn) #if !defined(CONFIG_USER_ONLY) void spr_write_tbl(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_tbl(cpu_env, cpu_gpr[gprn]); } void spr_write_tbu(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_tbu(cpu_env, cpu_gpr[gprn]); } @@ -XXX,XX +XXX,XX @@ void spr_write_atbu(DisasContext *ctx, int sprn, int gprn) #if defined(TARGET_PPC64) void spr_read_purr(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_purr(cpu_gpr[gprn], cpu_env); } void spr_write_purr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_purr(cpu_env, cpu_gpr[gprn]); } /* HDECR */ void spr_read_hdecr(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_hdecr(cpu_gpr[gprn], cpu_env); } void spr_write_hdecr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_hdecr(cpu_env, cpu_gpr[gprn]); } void spr_read_vtb(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_vtb(cpu_gpr[gprn], cpu_env); } void spr_write_vtb(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_vtb(cpu_env, cpu_gpr[gprn]); } void spr_write_tbu40(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_tbu40(cpu_env, cpu_gpr[gprn]); } @@ -XXX,XX +XXX,XX @@ void spr_write_dpdes(DisasContext *ctx, int sprn, int gprn) #if !defined(CONFIG_USER_ONLY) void spr_read_40x_pit(DisasContext *ctx, int gprn, int sprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_load_40x_pit(cpu_gpr[gprn], cpu_env); } void spr_write_40x_pit(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_40x_pit(cpu_env, cpu_gpr[gprn]); } void spr_write_40x_dbcr0(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_store_spr(sprn, cpu_gpr[gprn]); gen_helper_store_40x_dbcr0(cpu_env, cpu_gpr[gprn]); /* We must stop translation as we may have rebooted */ @@ -XXX,XX +XXX,XX @@ void spr_write_40x_dbcr0(DisasContext *ctx, int sprn, int gprn) void spr_write_40x_sler(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_40x_sler(cpu_env, cpu_gpr[gprn]); } void spr_write_40x_tcr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_40x_tcr(cpu_env, cpu_gpr[gprn]); } void spr_write_40x_tsr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_40x_tsr(cpu_env, cpu_gpr[gprn]); } @@ -XXX,XX +XXX,XX @@ void spr_write_40x_pid(DisasContext *ctx, int sprn, int gprn) void spr_write_booke_tcr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_booke_tcr(cpu_env, cpu_gpr[gprn]); } void spr_write_booke_tsr(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_booke_tsr(cpu_env, cpu_gpr[gprn]); } #endif @@ -XXX,XX +XXX,XX @@ static void gen_darn(DisasContext *ctx) if (l > 2) { tcg_gen_movi_i64(cpu_gpr[rD(ctx->opcode)], -1); } else { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); if (l == 0) { gen_helper_darn32(cpu_gpr[rD(ctx->opcode)]); } else { @@ -XXX,XX +XXX,XX @@ static void pmu_count_insns(DisasContext *ctx) * running with icount and we do not handle it beforehand, * the helper can trigger a 'bad icount read'. */ - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); /* Avoid helper calls when only PMC5-6 are enabled. */ if (!ctx->pmc_other) { @@ -XXX,XX +XXX,XX @@ static void gen_rfi(DisasContext *ctx) } /* Restore CPU state */ CHK_SV(ctx); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_update_cfar(ctx, ctx->cia); gen_helper_rfi(cpu_env); ctx->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static void gen_rfid(DisasContext *ctx) #else /* Restore CPU state */ CHK_SV(ctx); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_update_cfar(ctx, ctx->cia); gen_helper_rfid(cpu_env); ctx->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static void gen_rfscv(DisasContext *ctx) #else /* Restore CPU state */ CHK_SV(ctx); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_update_cfar(ctx, ctx->cia); gen_helper_rfscv(cpu_env); ctx->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static void gen_mtmsrd(DisasContext *ctx) t0 = tcg_temp_new(); t1 = tcg_temp_new(); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); if (ctx->opcode & 0x00010000) { /* L=1 form only updates EE and RI */ @@ -XXX,XX +XXX,XX @@ static void gen_mtmsr(DisasContext *ctx) t0 = tcg_temp_new(); t1 = tcg_temp_new(); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); if (ctx->opcode & 0x00010000) { /* L=1 form only updates EE and RI */ mask &= (1ULL << MSR_RI) | (1ULL << MSR_EE); diff --git a/target/ppc/power8-pmu-regs.c.inc b/target/ppc/power8-pmu-regs.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/power8-pmu-regs.c.inc +++ b/target/ppc/power8-pmu-regs.c.inc @@ -XXX,XX +XXX,XX @@ static void write_MMCR0_common(DisasContext *ctx, TCGv val) /* * helper_store_mmcr0 will make clock based operations that * will cause 'bad icount read' errors if we do not execute - * gen_icount_io_start() beforehand. + * translator_io_start() beforehand. */ - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_mmcr0(cpu_env, val); /* @@ -XXX,XX +XXX,XX @@ void spr_read_PMC(DisasContext *ctx, int gprn, int sprn) { TCGv_i32 t_sprn = tcg_constant_i32(sprn); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_read_pmc(cpu_gpr[gprn], cpu_env, t_sprn); } @@ -XXX,XX +XXX,XX @@ void spr_write_PMC(DisasContext *ctx, int sprn, int gprn) { TCGv_i32 t_sprn = tcg_constant_i32(sprn); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_pmc(cpu_env, t_sprn, cpu_gpr[gprn]); } @@ -XXX,XX +XXX,XX @@ void spr_write_MMCR0(DisasContext *ctx, int sprn, int gprn) void spr_write_MMCR1(DisasContext *ctx, int sprn, int gprn) { - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_helper_store_mmcr1(cpu_env, cpu_gpr[gprn]); } #else diff --git a/target/ppc/translate/branch-impl.c.inc b/target/ppc/translate/branch-impl.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/translate/branch-impl.c.inc +++ b/target/ppc/translate/branch-impl.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_RFEBB(DisasContext *ctx, arg_XL_s *arg) { REQUIRE_INSNS_FLAGS2(ctx, ISA207S); - gen_icount_io_start(ctx); + translator_io_start(&ctx->base); gen_update_cfar(ctx, ctx->cia); gen_helper_rfebb(cpu_env, cpu_gpr[arg->s]); -- 2.34.1 This is used by exactly one host in extraordinary circumstances. This means that translator.h need not include plugin-gen.h; translator.c already includes plugin-gen.h. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/translator.h | 8 +------- accel/tcg/translator.c | 5 +++++ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/include/exec/translator.h b/include/exec/translator.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -XXX,XX +XXX,XX @@ #include "qemu/bswap.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" -#include "exec/plugin-gen.h" #include "exec/translate-all.h" #include "tcg/tcg.h" @@ -XXX,XX +XXX,XX @@ translator_ldq_swap(CPUArchState *env, DisasContextBase *db, * re-synthesised for s390x "ex"). It ensures we update other areas of * the translator with details of the executed instruction. */ - -static inline void translator_fake_ldb(uint8_t insn8, abi_ptr pc) -{ - plugin_insn_append(pc, &insn8, sizeof(insn8)); -} - +void translator_fake_ldb(uint8_t insn8, abi_ptr pc); /* * Return whether addr is on the same page as where disassembly started. diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ uint64_t translator_ldq(CPUArchState *env, DisasContextBase *db, abi_ptr pc) plugin_insn_append(pc, &plug, sizeof(ret)); return ret; } + +void translator_fake_ldb(uint8_t insn8, abi_ptr pc) +{ + plugin_insn_append(pc, &insn8, sizeof(insn8)); +} -- 2.34.1 Move most includes from *translate*.c to translate.h, ensuring that we get the ordering correct. Ensure cpu.h is first. Use disas/disas.h instead of exec/log.h. Drop otherwise unused includes. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/translate.h | 3 +++ target/arm/tcg/translate-a64.c | 17 +++++------------ target/arm/tcg/translate-m-nocp.c | 2 -- target/arm/tcg/translate-mve.c | 3 --- target/arm/tcg/translate-neon.c | 3 --- target/arm/tcg/translate-sme.c | 6 ------ target/arm/tcg/translate-sve.c | 9 --------- target/arm/tcg/translate-vfp.c | 3 --- target/arm/tcg/translate.c | 17 +++++------------ 9 files changed, 13 insertions(+), 50 deletions(-) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_TRANSLATE_H #define TARGET_ARM_TRANSLATE_H +#include "cpu.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" #include "exec/translator.h" #include "exec/helper-gen.h" #include "internals.h" diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "cpu.h" -#include "exec/exec-all.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "qemu/log.h" -#include "arm_ldst.h" #include "translate.h" -#include "internals.h" -#include "qemu/host-utils.h" -#include "semihosting/semihost.h" -#include "exec/log.h" -#include "cpregs.h" #include "translate-a64.h" -#include "qemu/atomic128.h" +#include "qemu/log.h" +#include "disas/disas.h" +#include "arm_ldst.h" +#include "semihosting/semihost.h" +#include "cpregs.h" static TCGv_i64 cpu_X[32]; static TCGv_i64 cpu_pc; diff --git a/target/arm/tcg/translate-m-nocp.c b/target/arm/tcg/translate-m-nocp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-m-nocp.c +++ b/target/arm/tcg/translate-m-nocp.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" #include "translate.h" #include "translate-a32.h" diff --git a/target/arm/tcg/translate-mve.c b/target/arm/tcg/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-mve.c +++ b/target/arm/tcg/translate-mve.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "exec/exec-all.h" #include "translate.h" #include "translate-a32.h" diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "exec/exec-all.h" #include "translate.h" #include "translate-a32.h" diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sme.c +++ b/target/arm/tcg/translate-sme.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "cpu.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "tcg/tcg-gvec-desc.h" #include "translate.h" #include "translate-a64.h" -#include "fpu/softfloat.h" - /* * Include the generated decoder. diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "cpu.h" -#include "exec/exec-all.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "tcg/tcg-gvec-desc.h" -#include "qemu/log.h" -#include "arm_ldst.h" #include "translate.h" -#include "internals.h" -#include "exec/log.h" #include "translate-a64.h" #include "fpu/softfloat.h" diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "exec/exec-all.h" #include "translate.h" #include "translate-a32.h" diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "cpu.h" -#include "internals.h" -#include "disas/disas.h" -#include "exec/exec-all.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "qemu/log.h" -#include "qemu/bitops.h" -#include "arm_ldst.h" -#include "semihosting/semihost.h" -#include "exec/log.h" -#include "cpregs.h" #include "translate.h" #include "translate-a32.h" +#include "qemu/log.h" +#include "disas/disas.h" +#include "arm_ldst.h" +#include "semihosting/semihost.h" +#include "cpregs.h" #include "exec/helper-proto.h" #define HELPER_H "helper.h" -- 2.34.1 Move most includes from *translate*.c to translate.h, ensuring that we get the ordering correct. Ensure cpu.h is first. Use disas/disas.h instead of exec/log.h. Drop otherwise unused includes. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/mips/tcg/translate.h | 6 ++++-- target/mips/tcg/msa_translate.c | 3 --- target/mips/tcg/mxu_translate.c | 2 -- target/mips/tcg/octeon_translate.c | 4 +--- target/mips/tcg/rel6_translate.c | 2 -- target/mips/tcg/translate.c | 18 ++++++------------ target/mips/tcg/translate_addr_const.c | 1 - target/mips/tcg/tx79_translate.c | 4 +--- target/mips/tcg/vr54xx_translate.c | 3 --- 9 files changed, 12 insertions(+), 31 deletions(-) diff --git a/target/mips/tcg/translate.h b/target/mips/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.h +++ b/target/mips/tcg/translate.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_MIPS_TRANSLATE_H #define TARGET_MIPS_TRANSLATE_H -#include "qemu/log.h" -#include "exec/translator.h" +#include "cpu.h" #include "tcg/tcg-op.h" +#include "exec/translator.h" +#include "exec/helper-gen.h" +#include "qemu/log.h" #define MIPS_DEBUG_DISAS 0 diff --git a/target/mips/tcg/msa_translate.c b/target/mips/tcg/msa_translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/msa_translate.c +++ b/target/mips/tcg/msa_translate.c @@ -XXX,XX +XXX,XX @@ * SPDX-License-Identifier: LGPL-2.1-or-later */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "exec/helper-gen.h" #include "translate.h" #include "fpu_helper.h" -#include "internal.h" static int elm_n(DisasContext *ctx, int x); static int elm_df(DisasContext *ctx, int x); diff --git a/target/mips/tcg/mxu_translate.c b/target/mips/tcg/mxu_translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/mxu_translate.c +++ b/target/mips/tcg/mxu_translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "exec/helper-gen.h" #include "translate.h" /* diff --git a/target/mips/tcg/octeon_translate.c b/target/mips/tcg/octeon_translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/octeon_translate.c +++ b/target/mips/tcg/octeon_translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "exec/helper-gen.h" #include "translate.h" +#include "tcg/tcg-op-gvec.h" /* Include the auto-generated decoder. */ #include "decode-octeon.c.inc" diff --git a/target/mips/tcg/rel6_translate.c b/target/mips/tcg/rel6_translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/rel6_translate.c +++ b/target/mips/tcg/rel6_translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "exec/helper-gen.h" #include "translate.h" /* Include the auto-generated decoders. */ diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.c +++ b/target/mips/tcg/translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "cpu.h" -#include "internal.h" -#include "tcg/tcg-op.h" -#include "exec/translator.h" -#include "exec/helper-proto.h" -#include "exec/helper-gen.h" -#include "semihosting/semihost.h" - -#include "trace.h" -#include "exec/log.h" -#include "qemu/qemu-print.h" -#include "fpu_helper.h" #include "translate.h" +#include "internal.h" +#include "exec/helper-proto.h" +#include "semihosting/semihost.h" +#include "trace.h" +#include "disas/disas.h" +#include "fpu_helper.h" #define HELPER_H "helper.h" #include "exec/helper-info.c.inc" diff --git a/target/mips/tcg/translate_addr_const.c b/target/mips/tcg/translate_addr_const.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate_addr_const.c +++ b/target/mips/tcg/translate_addr_const.c @@ -XXX,XX +XXX,XX @@ * SPDX-License-Identifier: LGPL-2.1-or-later */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" #include "translate.h" bool gen_lsa(DisasContext *ctx, int rd, int rt, int rs, int sa) diff --git a/target/mips/tcg/tx79_translate.c b/target/mips/tcg/tx79_translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/tx79_translate.c +++ b/target/mips/tcg/tx79_translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "tcg/tcg-op-gvec.h" -#include "exec/helper-gen.h" #include "translate.h" +#include "tcg/tcg-op-gvec.h" /* Include the auto-generated decoder. */ #include "decode-tx79.c.inc" diff --git a/target/mips/tcg/vr54xx_translate.c b/target/mips/tcg/vr54xx_translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/vr54xx_translate.c +++ b/target/mips/tcg/vr54xx_translate.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg/tcg-op.h" -#include "exec/helper-gen.h" #include "translate.h" -#include "internal.h" /* Include the auto-generated decoder. */ #include "decode-vr54xx.c.inc" -- 2.34.1 This had been pulled in via exec/exec-all.h, via exec/translator.h, but the include of exec-all.h will be removed. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/translate.c | 1 + target/loongarch/translate.c | 3 +-- target/mips/tcg/translate.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-op-gvec.h" #include "exec/helper-gen.h" #include "exec/helper-proto.h" +#include "exec/translation-block.h" #include "exec/cpu_ldst.h" #include "exec/log.h" #include "internal.h" diff --git a/target/loongarch/translate.c b/target/loongarch/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/translate.c +++ b/target/loongarch/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" - +#include "exec/translation-block.h" #include "exec/translator.h" #include "exec/helper-proto.h" #include "exec/helper-gen.h" - #include "exec/log.h" #include "qemu/qemu-print.h" #include "fpu/softfloat.h" diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.c +++ b/target/mips/tcg/translate.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "internal.h" #include "exec/helper-proto.h" +#include "exec/translation-block.h" #include "semihosting/semihost.h" #include "trace.h" #include "disas/disas.h" -- 2.34.1 This had been pulled in via exec/translator.h, but the include of exec-all.h will be removed. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/translate.h | 1 + 1 file changed, 1 insertion(+) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "tcg/tcg-op.h" #include "tcg/tcg-op-gvec.h" +#include "exec/exec-all.h" #include "exec/translator.h" #include "exec/helper-gen.h" #include "internals.h" -- 2.34.1 Reduce the header to only bswap.h and cpu_ldst.h. Move exec/translate-all.h to translator.c. Reduce tcg.h and tcg-op.h to tcg-op-common.h. Remove otherwise unused headers. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/translator.h | 6 +----- accel/tcg/translator.c | 8 +++----- 2 files changed, 4 insertions(+), 10 deletions(-) diff --git a/include/exec/translator.h b/include/exec/translator.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -XXX,XX +XXX,XX @@ * member in your target-specific DisasContext. */ - #include "qemu/bswap.h" -#include "exec/exec-all.h" -#include "exec/cpu_ldst.h" -#include "exec/translate-all.h" -#include "tcg/tcg.h" +#include "exec/cpu_ldst.h" /* for abi_ptr */ /** * gen_intermediate_code diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "qemu/error-report.h" -#include "tcg/tcg.h" -#include "tcg/tcg-op.h" #include "exec/exec-all.h" -#include "exec/log.h" #include "exec/translator.h" +#include "exec/translate-all.h" #include "exec/plugin-gen.h" -#include "exec/replay-core.h" - +#include "tcg/tcg-op-common.h" static void gen_io_start(void) { -- 2.34.1 The bug was hidden because they happen to have the same values. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/region.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tcg/region.c b/tcg/region.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/region.c +++ b/tcg/region.c @@ -XXX,XX +XXX,XX @@ static int alloc_code_gen_buffer(size_t tb_size, int splitwx, Error **errp) return PROT_READ | PROT_WRITE; } #elif defined(_WIN32) +/* + * Local source-level compatibility with Unix. + * Used by tcg_region_init below. + */ +#define PROT_READ 1 +#define PROT_WRITE 2 +#define PROT_EXEC 4 + static int alloc_code_gen_buffer(size_t size, int splitwx, Error **errp) { void *buf; @@ -XXX,XX +XXX,XX @@ static int alloc_code_gen_buffer(size_t size, int splitwx, Error **errp) region.start_aligned = buf; region.total_size = size; - return PAGE_READ | PAGE_WRITE | PAGE_EXEC; + return PROT_READ | PROT_WRITE | PROT_EXEC; } #else static int alloc_code_gen_buffer_anon(size_t size, int prot, @@ -XXX,XX +XXX,XX @@ void tcg_region_init(size_t tb_size, int splitwx, unsigned max_cpus) * buffer -- let that one use hugepages throughout. * Work with the page protections set up with the initial mapping. */ - need_prot = PAGE_READ | PAGE_WRITE; + need_prot = PROT_READ | PROT_WRITE; #ifndef CONFIG_TCG_INTERPRETER if (tcg_splitwx_diff == 0) { - need_prot |= PAGE_EXEC; + need_prot |= PROT_EXEC; } #endif for (size_t i = 0, n = region.n; i < n; i++) { @@ -XXX,XX +XXX,XX @@ void tcg_region_init(size_t tb_size, int splitwx, unsigned max_cpus) if (have_prot != need_prot) { int rc; - if (need_prot == (PAGE_READ | PAGE_WRITE | PAGE_EXEC)) { + if (need_prot == (PROT_READ | PROT_WRITE | PROT_EXEC)) { rc = qemu_mprotect_rwx(start, end - start); - } else if (need_prot == (PAGE_READ | PAGE_WRITE)) { + } else if (need_prot == (PROT_READ | PROT_WRITE)) { rc = qemu_mprotect_rw(start, end - start); } else { g_assert_not_reached(); -- 2.34.1 Since the change to CPUArchState, we have a common typedef that can always be used. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/helper-head.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -XXX,XX +XXX,XX @@ #define dh_alias_f64 i64 #define dh_alias_ptr ptr #define dh_alias_cptr ptr +#define dh_alias_env ptr #define dh_alias_void void #define dh_alias_noreturn noreturn #define dh_alias(t) glue(dh_alias_, t) @@ -XXX,XX +XXX,XX @@ #define dh_ctype_f64 float64 #define dh_ctype_ptr void * #define dh_ctype_cptr const void * +#define dh_ctype_env CPUArchState * #define dh_ctype_void void #define dh_ctype_noreturn G_NORETURN void #define dh_ctype(t) dh_ctype_##t @@ -XXX,XX +XXX,XX @@ # endif # endif # define dh_ctype_tl target_ulong -# define dh_alias_env ptr -# define dh_ctype_env CPUArchState * -# define dh_typecode_env dh_typecode_ptr #endif /* We can't use glue() here because it falls foul of C preprocessor @@ -XXX,XX +XXX,XX @@ #define dh_typecode_f32 dh_typecode_i32 #define dh_typecode_f64 dh_typecode_i64 #define dh_typecode_cptr dh_typecode_ptr +#define dh_typecode_env dh_typecode_ptr #define dh_typecode(t) dh_typecode_##t #define dh_callflag_i32 0 -- 2.34.1 This finally paves the way for tcg/ to be built once per mode. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg.h | 1 - accel/tcg/plugin-gen.c | 1 + tcg/region.c | 2 +- tcg/tcg-op.c | 2 +- tcg/tcg.c | 2 +- 5 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ #ifndef TCG_H #define TCG_H -#include "cpu.h" #include "exec/memop.h" #include "exec/memopidx.h" #include "qemu/bitops.h" diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -XXX,XX +XXX,XX @@ * CPU's index into a TCG temp, since the first callback did it already. */ #include "qemu/osdep.h" +#include "cpu.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" #include "tcg/tcg-op.h" diff --git a/tcg/region.c b/tcg/region.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/region.c +++ b/tcg/region.c @@ -XXX,XX +XXX,XX @@ #include "qemu/cacheinfo.h" #include "qemu/qtree.h" #include "qapi/error.h" -#include "exec/exec-all.h" #include "tcg/tcg.h" +#include "exec/translation-block.h" #include "tcg-internal.h" diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "exec/exec-all.h" #include "tcg/tcg.h" #include "tcg/tcg-temp-internal.h" #include "tcg/tcg-op-common.h" +#include "exec/translation-block.h" #include "exec/plugin-gen.h" #include "tcg-internal.h" diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ #include "qemu/cacheflush.h" #include "qemu/cacheinfo.h" #include "qemu/timer.h" -#include "exec/exec-all.h" +#include "exec/translation-block.h" #include "exec/tlb-common.h" #include "tcg/tcg-op-common.h" -- 2.34.1 This function is only used in translator.c, and uses a target-specific typedef: abi_ptr. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/plugin-gen.h | 22 ---------------------- accel/tcg/translator.c | 21 +++++++++++++++++++++ 2 files changed, 21 insertions(+), 22 deletions(-) diff --git a/include/exec/plugin-gen.h b/include/exec/plugin-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/plugin-gen.h +++ b/include/exec/plugin-gen.h @@ -XXX,XX +XXX,XX @@ void plugin_gen_insn_end(void); void plugin_gen_disable_mem_helpers(void); void plugin_gen_empty_mem_callback(TCGv_i64 addr, uint32_t info); -static inline void plugin_insn_append(abi_ptr pc, const void *from, size_t size) -{ - struct qemu_plugin_insn *insn = tcg_ctx->plugin_insn; - abi_ptr off; - - if (insn == NULL) { - return; - } - off = pc - insn->vaddr; - if (off < insn->data->len) { - g_byte_array_set_size(insn->data, off); - } else if (off > insn->data->len) { - /* we have an unexpected gap */ - g_assert_not_reached(); - } - - insn->data = g_byte_array_append(insn->data, from, size); -} - #else /* !CONFIG_PLUGIN */ static inline bool @@ -XXX,XX +XXX,XX @@ static inline void plugin_gen_disable_mem_helpers(void) static inline void plugin_gen_empty_mem_callback(TCGv_i64 addr, uint32_t info) { } -static inline void plugin_insn_append(abi_ptr pc, const void *from, size_t size) -{ } - #endif /* CONFIG_PLUGIN */ #endif /* QEMU_PLUGIN_GEN_H */ diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ static void *translator_access(CPUArchState *env, DisasContextBase *db, return host + (pc - base); } +static void plugin_insn_append(abi_ptr pc, const void *from, size_t size) +{ +#ifdef CONFIG_PLUGIN + struct qemu_plugin_insn *insn = tcg_ctx->plugin_insn; + abi_ptr off; + + if (insn == NULL) { + return; + } + off = pc - insn->vaddr; + if (off < insn->data->len) { + g_byte_array_set_size(insn->data, off); + } else if (off > insn->data->len) { + /* we have an unexpected gap */ + g_assert_not_reached(); + } + + insn->data = g_byte_array_append(insn->data, from, size); +#endif +} + uint8_t translator_ldub(CPUArchState *env, DisasContextBase *db, abi_ptr pc) { uint8_t ret; -- 2.34.1 Two headers are not required for the rest of the contents of plugin-gen.h. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/plugin-gen.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/exec/plugin-gen.h b/include/exec/plugin-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/plugin-gen.h +++ b/include/exec/plugin-gen.h @@ -XXX,XX +XXX,XX @@ #ifndef QEMU_PLUGIN_GEN_H #define QEMU_PLUGIN_GEN_H -#include "exec/cpu_ldst.h" -#include "qemu/plugin.h" #include "tcg/tcg.h" struct DisasContextBase; -- 2.34.1 If CONFIG_USER_ONLY is ok generically, so is CONFIG_SOFTMMU, because they are exactly opposite. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/poison.h | 1 - scripts/make-config-poison.sh | 5 +++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/exec/poison.h b/include/exec/poison.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/poison.h +++ b/include/exec/poison.h @@ -XXX,XX +XXX,XX @@ #pragma GCC poison CONFIG_HVF #pragma GCC poison CONFIG_LINUX_USER #pragma GCC poison CONFIG_KVM -#pragma GCC poison CONFIG_SOFTMMU #pragma GCC poison CONFIG_WHPX #pragma GCC poison CONFIG_XEN diff --git a/scripts/make-config-poison.sh b/scripts/make-config-poison.sh index XXXXXXX..XXXXXXX 100755 --- a/scripts/make-config-poison.sh +++ b/scripts/make-config-poison.sh @@ -XXX,XX +XXX,XX @@ if test $# = 0; then exit 0 fi -# Create list of config switches that should be poisoned in common code... -# but filter out CONFIG_TCG and CONFIG_USER_ONLY which are special. +# Create list of config switches that should be poisoned in common code, +# but filter out several which are handled manually. exec sed -n \ -e' /CONFIG_TCG/d' \ -e '/CONFIG_USER_ONLY/d' \ + -e '/CONFIG_SOFTMMU/d' \ -e '/^#define / {' \ -e 's///' \ -e 's/ .*//' \ -- 2.34.1 Create two static libraries for use by each execution mode. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/meson.build | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/tcg/meson.build b/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tcg/meson.build +++ b/tcg/meson.build @@ -XXX,XX +XXX,XX @@ +if not get_option('tcg').allowed() + subdir_done() +endif + tcg_ss = ss.source_set() tcg_ss.add(files( @@ -XXX,XX +XXX,XX @@ tcg_ss.add(files( if get_option('tcg_interpreter') libffi = dependency('libffi', version: '>=3.0', required: true, method: 'pkg-config') - specific_ss.add(libffi) - specific_ss.add(files('tci.c')) + tcg_ss.add(libffi) + tcg_ss.add(files('tci.c')) endif -specific_ss.add_all(when: 'CONFIG_TCG', if_true: tcg_ss) +tcg_ss = tcg_ss.apply(config_host, strict: false) + +libtcg_user = static_library('tcg_user', + tcg_ss.sources() + genh, + name_suffix: 'fa', + c_args: '-DCONFIG_USER_ONLY', + build_by_default: have_user) + +tcg_user = declare_dependency(link_with: libtcg_user, + dependencies: tcg_ss.dependencies()) +user_ss.add(tcg_user) + +libtcg_softmmu = static_library('tcg_softmmu', + tcg_ss.sources() + genh, + name_suffix: 'fa', + c_args: '-DCONFIG_SOFTMMU', + build_by_default: have_system) + +tcg_softmmu = declare_dependency(link_with: libtcg_softmmu, + dependencies: tcg_ss.dependencies()) +softmmu_ss.add(tcg_softmmu) -- 2.34.1 From: Ilya Leoshkevich <iii@linux.ibm.com> Coverity complains that perf_marker is never unmapped. Fix by unmapping it in perf_exit(). Fixes: Coverity CID 1507929 Fixes: 5584e2dbe8c9 ("tcg: add perfmap and jitdump") Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com> Message-Id: <20230605114134.1169974-1-iii@linux.ibm.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/perf.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/accel/tcg/perf.c b/accel/tcg/perf.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/perf.c +++ b/accel/tcg/perf.c @@ -XXX,XX +XXX,XX @@ static void write_perfmap_entry(const void *start, size_t insn, } static FILE *jitdump; +static size_t perf_marker_size; +static void *perf_marker = MAP_FAILED; #define JITHEADER_MAGIC 0x4A695444 #define JITHEADER_VERSION 1 @@ -XXX,XX +XXX,XX @@ void perf_enable_jitdump(void) { struct jitheader header; char jitdump_file[32]; - void *perf_marker; if (!use_rt_clock) { warn_report("CLOCK_MONOTONIC is not available, proceeding without jitdump"); @@ -XXX,XX +XXX,XX @@ void perf_enable_jitdump(void) * PERF_RECORD_MMAP or PERF_RECORD_MMAP2 event is of the form jit-%d.dump * and will process it as a jitdump file. */ - perf_marker = mmap(NULL, qemu_real_host_page_size(), PROT_READ | PROT_EXEC, + perf_marker_size = qemu_real_host_page_size(); + perf_marker = mmap(NULL, perf_marker_size, PROT_READ | PROT_EXEC, MAP_PRIVATE, fileno(jitdump), 0); if (perf_marker == MAP_FAILED) { warn_report("Could not map %s: %s, proceeding without jitdump", @@ -XXX,XX +XXX,XX @@ void perf_exit(void) perfmap = NULL; } + if (perf_marker != MAP_FAILED) { + munmap(perf_marker, perf_marker_size); + perf_marker = MAP_FAILED; + } + if (jitdump) { fclose(jitdump); jitdump = NULL; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> In commit d56fea79f9 ("tcg: Move TCG_{LOW,HIGH} to tcg-internal.h") we replaced the "_link_error" definitions with modern QEMU_ERROR() attribute markup. We covered tcg-op.c but forgot to completely clean tcg-op-vec.c. Do it now. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-Id: <20230605175647.88395-3-philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/tcg-op-vec.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-vec.c +++ b/tcg/tcg-op-vec.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-mo.h" #include "tcg-internal.h" - -/* Reduce the number of ifdefs below. This assumes that all uses of - TCGV_HIGH and TCGV_LOW are properly protected by a conditional that - the compiler can eliminate. */ -#if TCG_TARGET_REG_BITS == 64 -extern TCGv_i32 TCGV_LOW_link_error(TCGv_i64); -extern TCGv_i32 TCGV_HIGH_link_error(TCGv_i64); -#define TCGV_LOW TCGV_LOW_link_error -#define TCGV_HIGH TCGV_HIGH_link_error -#endif - /* * Vector optional opcode tracking. * Except for the basic logical operations (and, or, xor), and -- 2.34.1