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 a9fe9e191b4305b88c356a1ed9ac3baf89eb18aa: Merge tag 'pull-riscv-to-apply-20230505-1' of https://github.com/alistair23/qemu into staging (2023-05-05 09:25:13 +0100) are available in the Git repository at: https://gitlab.com/rth7680/qemu.git tags/pull-tcg-20230505 for you to fetch changes up to 35a0bd63b458f30389b6bc6b7471c1665fe7b9d8: tcg: Widen helper_*_st[bw]_mmu val arguments (2023-05-05 17:21:03 +0100) ---------------------------------------------------------------- softfloat: Fix the incorrect computation in float32_exp2 tcg: Remove compatability helpers for qemu ld/st target/alpha: Remove TARGET_ALIGNED_ONLY target/hppa: Remove TARGET_ALIGNED_ONLY target/sparc: Remove TARGET_ALIGNED_ONLY tcg: Cleanups preparing to unify calls to qemu_ld/st helpers ---------------------------------------------------------------- Richard Henderson (41): target/avr: Finish conversion to tcg_gen_qemu_{ld,st}_* target/cris: Finish conversion to tcg_gen_qemu_{ld,st}_* target/Hexagon: Finish conversion to tcg_gen_qemu_{ld, st}_* target/m68k: Finish conversion to tcg_gen_qemu_{ld,st}_* target/mips: Finish conversion to tcg_gen_qemu_{ld,st}_* target/s390x: Finish conversion to tcg_gen_qemu_{ld, st}_* target/sparc: Finish conversion to tcg_gen_qemu_{ld, st}_* target/xtensa: Finish conversion to tcg_gen_qemu_{ld, st}_* tcg: Remove compatability helpers for qemu ld/st target/alpha: Use MO_ALIGN for system UNALIGN() target/alpha: Use MO_ALIGN where required target/alpha: Remove TARGET_ALIGNED_ONLY target/hppa: Use MO_ALIGN for system UNALIGN() target/hppa: Remove TARGET_ALIGNED_ONLY target/sparc: Use MO_ALIGN where required target/sparc: Use cpu_ld*_code_mmu target/sparc: Remove TARGET_ALIGNED_ONLY tcg/i386: Rationalize args to tcg_out_qemu_{ld,st} tcg/i386: Generalize multi-part load overlap test tcg/i386: Introduce HostAddress tcg/i386: Drop r0+r1 local variables from tcg_out_tlb_load tcg/i386: Introduce tcg_out_testi tcg/aarch64: Rationalize args to tcg_out_qemu_{ld,st} tcg/aarch64: Introduce HostAddress tcg/arm: Rationalize args to tcg_out_qemu_{ld,st} tcg/arm: Introduce HostAddress tcg/loongarch64: Rationalize args to tcg_out_qemu_{ld,st} tcg/loongarch64: Introduce HostAddress tcg/mips: Rationalize args to tcg_out_qemu_{ld,st} tcg/ppc: Rationalize args to tcg_out_qemu_{ld,st} tcg/ppc: Introduce HostAddress tcg/riscv: Require TCG_TARGET_REG_BITS == 64 tcg/riscv: Rationalize args to tcg_out_qemu_{ld,st} tcg/s390x: Pass TCGType to tcg_out_qemu_{ld,st} tcg/s390x: Introduce HostAddress tcg/sparc64: Drop is_64 test from tcg_out_qemu_ld data return tcg/sparc64: Pass TCGType to tcg_out_qemu_{ld,st} tcg: Move TCGLabelQemuLdst to tcg.c tcg: Replace REG_P with arg_loc_reg_p tcg: Introduce arg_slot_stk_ofs tcg: Widen helper_*_st[bw]_mmu val arguments Shivaprasad G Bhat (1): softfloat: Fix the incorrect computation in float32_exp2 configs/targets/alpha-linux-user.mak | 1 - configs/targets/alpha-softmmu.mak | 1 - configs/targets/hppa-linux-user.mak | 1 - configs/targets/hppa-softmmu.mak | 1 - configs/targets/sparc-linux-user.mak | 1 - configs/targets/sparc-softmmu.mak | 1 - configs/targets/sparc32plus-linux-user.mak | 1 - configs/targets/sparc64-linux-user.mak | 1 - configs/targets/sparc64-softmmu.mak | 1 - include/tcg/tcg-ldst.h | 10 +- include/tcg/tcg-op.h | 55 ----- target/hexagon/macros.h | 14 +- tcg/riscv/tcg-target-con-set.h | 8 - tcg/riscv/tcg-target.h | 22 +- tcg/tcg-internal.h | 4 - accel/tcg/cputlb.c | 6 +- fpu/softfloat.c | 2 +- target/alpha/translate.c | 38 +-- target/avr/translate.c | 16 +- target/hexagon/genptr.c | 8 +- target/hexagon/idef-parser/parser-helpers.c | 28 +-- target/hexagon/translate.c | 32 +-- target/hppa/translate.c | 2 +- target/m68k/translate.c | 76 ++---- target/mips/tcg/translate.c | 8 +- target/s390x/tcg/translate.c | 152 ++++++------ target/sparc/ldst_helper.c | 10 +- target/sparc/translate.c | 85 ++++--- target/xtensa/translate.c | 4 +- tcg/tcg.c | 58 +++-- target/cris/translate_v10.c.inc | 18 +- target/mips/tcg/nanomips_translate.c.inc | 2 +- tcg/aarch64/tcg-target.c.inc | 108 ++++++--- tcg/arm/tcg-target.c.inc | 357 +++++++++++++--------------- tcg/i386/tcg-target.c.inc | 345 ++++++++++++++------------- tcg/loongarch64/tcg-target.c.inc | 135 +++++------ tcg/mips/tcg-target.c.inc | 186 ++++++++------- tcg/ppc/tcg-target.c.inc | 192 ++++++++------- tcg/riscv/tcg-target.c.inc | 268 ++++++--------------- tcg/s390x/tcg-target.c.inc | 131 +++++----- tcg/sparc64/tcg-target.c.inc | 8 +- tcg/tcg-ldst.c.inc | 14 -- 42 files changed, 1120 insertions(+), 1291 deletions(-) From: Shivaprasad G Bhat <sbhat@linux.ibm.com> The float32_exp2 function is computing wrong exponent of 2. For example, with the following set of values {0.1, 2.0, 2.0, -1.0}, the expected output would be {1.071773, 4.000000, 4.000000, 0.500000}. Instead, the function is computing {1.119102, 3.382044, 3.382044, -0.191022} Looking at the code, the float32_exp2() attempts to do this 2 3 4 5 n x x x x x x x e = 1 + --- + --- + --- + --- + --- + ... + --- + ... 1! 2! 3! 4! 5! n! But because of the typo it ends up doing x x x x x x x e = 1 + --- + --- + --- + --- + --- + ... + --- + ... 1! 2! 3! 4! 5! n! This is because instead of the xnp which holds the numerator, parts_muladd is using the xp which is just 'x'. Commit '572c4d862ff2' refactored this function, and mistakenly used xp instead of xnp. Cc: qemu-stable@nongnu.org Fixes: 572c4d862ff2 "softfloat: Convert float32_exp2 to FloatParts" Partially-Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1623 Reported-By: Luca Barbato (https://gitlab.com/lu-zero) Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com> Message-Id: <168304110865.537992.13059030916325018670.stgit@localhost.localdomain> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- fpu/softfloat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ float32 float32_exp2(float32 a, float_status *status) float64_unpack_canonical(&rp, float64_one, status); for (i = 0 ; i < 15 ; i++) { float64_unpack_canonical(&tp, float32_exp2_coefficients[i], status); - rp = *parts_muladd(&tp, &xp, &rp, 0, status); + rp = *parts_muladd(&tp, &xnp, &rp, 0, status); xnp = *parts_mul(&xnp, &xp, status); } -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Anton Johansson <anjo@rev.ng> Message-Id: <20230502135741.1158035-2-richard.henderson@linaro.org> --- target/avr/translate.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) 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 @@ static void gen_data_store(DisasContext *ctx, TCGv data, TCGv addr) if (ctx->base.tb->flags & TB_FLAGS_FULL_ACCESS) { gen_helper_fullwr(cpu_env, data, addr); } else { - tcg_gen_qemu_st8(data, addr, MMU_DATA_IDX); /* mem[addr] = data */ + tcg_gen_qemu_st_tl(data, addr, MMU_DATA_IDX, MO_UB); } } @@ -XXX,XX +XXX,XX @@ static void gen_data_load(DisasContext *ctx, TCGv data, TCGv addr) if (ctx->base.tb->flags & TB_FLAGS_FULL_ACCESS) { gen_helper_fullrd(data, cpu_env, addr); } else { - tcg_gen_qemu_ld8u(data, addr, MMU_DATA_IDX); /* data = mem[addr] */ + tcg_gen_qemu_ld_tl(data, addr, MMU_DATA_IDX, MO_UB); } } @@ -XXX,XX +XXX,XX @@ static bool trans_LPM1(DisasContext *ctx, arg_LPM1 *a) tcg_gen_shli_tl(addr, H, 8); /* addr = H:L */ tcg_gen_or_tl(addr, addr, L); - tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */ + tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LPM2(DisasContext *ctx, arg_LPM2 *a) tcg_gen_shli_tl(addr, H, 8); /* addr = H:L */ tcg_gen_or_tl(addr, addr, L); - tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */ + tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LPMX(DisasContext *ctx, arg_LPMX *a) tcg_gen_shli_tl(addr, H, 8); /* addr = H:L */ tcg_gen_or_tl(addr, addr, L); - tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */ + tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB); tcg_gen_addi_tl(addr, addr, 1); /* addr = addr + 1 */ tcg_gen_andi_tl(L, addr, 0xff); tcg_gen_shri_tl(addr, addr, 8); @@ -XXX,XX +XXX,XX @@ static bool trans_ELPM1(DisasContext *ctx, arg_ELPM1 *a) TCGv Rd = cpu_r[0]; TCGv addr = gen_get_zaddr(); - tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */ + tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ELPM2(DisasContext *ctx, arg_ELPM2 *a) TCGv Rd = cpu_r[a->rd]; TCGv addr = gen_get_zaddr(); - tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */ + tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ELPMX(DisasContext *ctx, arg_ELPMX *a) TCGv Rd = cpu_r[a->rd]; TCGv addr = gen_get_zaddr(); - tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */ + tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB); tcg_gen_addi_tl(addr, addr, 1); /* addr = addr + 1 */ gen_set_zaddr(addr); return true; -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. In this case we can fold the calls using the size bits of MemOp. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Anton Johansson <anjo@rev.ng> Message-Id: <20230502135741.1158035-3-richard.henderson@linaro.org> --- target/cris/translate_v10.c.inc | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/target/cris/translate_v10.c.inc b/target/cris/translate_v10.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/cris/translate_v10.c.inc +++ b/target/cris/translate_v10.c.inc @@ -XXX,XX +XXX,XX @@ static void gen_store_v10_conditional(DisasContext *dc, TCGv addr, TCGv val, /* Store only if F flag isn't set */ tcg_gen_andi_tl(t1, cpu_PR[PR_CCS], F_FLAG_V10); tcg_gen_brcondi_tl(TCG_COND_NE, t1, 0, l1); - if (size == 1) { - tcg_gen_qemu_st8(tval, taddr, mem_index); - } else if (size == 2) { - tcg_gen_qemu_st16(tval, taddr, mem_index); - } else { - tcg_gen_qemu_st32(tval, taddr, mem_index); - } + + tcg_gen_qemu_st_tl(tval, taddr, mem_index, ctz32(size) | MO_TE); + gen_set_label(l1); tcg_gen_shri_tl(t1, t1, 1); /* shift F to P position */ tcg_gen_or_tl(cpu_PR[PR_CCS], cpu_PR[PR_CCS], t1); /*P=F*/ @@ -XXX,XX +XXX,XX @@ static void gen_store_v10(DisasContext *dc, TCGv addr, TCGv val, return; } - if (size == 1) { - tcg_gen_qemu_st8(val, addr, mem_index); - } else if (size == 2) { - tcg_gen_qemu_st16(val, addr, mem_index); - } else { - tcg_gen_qemu_st32(val, addr, mem_index); - } + tcg_gen_qemu_st_tl(val, addr, mem_index, ctz32(size) | MO_TE); } -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Importantly, this removes some incorrect casts generated by idef-parser's gen_load(). Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Taylor Simpson <tsimpson@quicinc.com> Reviewed-by: Taylor Simpson <tsimpson@quicinc.com> Reviewed-by: Anton Johansson <anjo@rev.ng> Message-Id: <20230502135741.1158035-4-richard.henderson@linaro.org> --- target/hexagon/macros.h | 14 ++++----- target/hexagon/genptr.c | 8 +++--- target/hexagon/idef-parser/parser-helpers.c | 28 +++++++++--------- target/hexagon/translate.c | 32 ++++++++++----------- 4 files changed, 40 insertions(+), 42 deletions(-) diff --git a/target/hexagon/macros.h b/target/hexagon/macros.h index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/macros.h +++ b/target/hexagon/macros.h @@ -XXX,XX +XXX,XX @@ #define MEM_LOAD1s(DST, VA) \ do { \ CHECK_NOSHUF(VA, 1); \ - tcg_gen_qemu_ld8s(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_SB); \ } while (0) #define MEM_LOAD1u(DST, VA) \ do { \ CHECK_NOSHUF(VA, 1); \ - tcg_gen_qemu_ld8u(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_UB); \ } while (0) #define MEM_LOAD2s(DST, VA) \ do { \ CHECK_NOSHUF(VA, 2); \ - tcg_gen_qemu_ld16s(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TESW); \ } while (0) #define MEM_LOAD2u(DST, VA) \ do { \ CHECK_NOSHUF(VA, 2); \ - tcg_gen_qemu_ld16u(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TEUW); \ } while (0) #define MEM_LOAD4s(DST, VA) \ do { \ CHECK_NOSHUF(VA, 4); \ - tcg_gen_qemu_ld32s(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TESL); \ } while (0) #define MEM_LOAD4u(DST, VA) \ do { \ CHECK_NOSHUF(VA, 4); \ - tcg_gen_qemu_ld32s(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TEUL); \ } while (0) #define MEM_LOAD8u(DST, VA) \ do { \ CHECK_NOSHUF(VA, 8); \ - tcg_gen_qemu_ld64(DST, VA, ctx->mem_idx); \ + tcg_gen_qemu_ld_i64(DST, VA, ctx->mem_idx, MO_TEUQ); \ } while (0) #define MEM_STORE1_FUNC(X) \ 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 @@ void gen_set_byte_i64(int N, TCGv_i64 result, TCGv src) static inline void gen_load_locked4u(TCGv dest, TCGv vaddr, int mem_index) { - tcg_gen_qemu_ld32u(dest, vaddr, mem_index); + tcg_gen_qemu_ld_tl(dest, vaddr, mem_index, MO_TEUL); tcg_gen_mov_tl(hex_llsc_addr, vaddr); tcg_gen_mov_tl(hex_llsc_val, dest); } static inline void gen_load_locked8u(TCGv_i64 dest, TCGv vaddr, int mem_index) { - tcg_gen_qemu_ld64(dest, vaddr, mem_index); + tcg_gen_qemu_ld_i64(dest, vaddr, mem_index, MO_TEUQ); tcg_gen_mov_tl(hex_llsc_addr, vaddr); tcg_gen_mov_i64(hex_llsc_val_i64, dest); } @@ -XXX,XX +XXX,XX @@ static void gen_load_frame(DisasContext *ctx, TCGv_i64 frame, TCGv EA) { Insn *insn = ctx->insn; /* Needed for CHECK_NOSHUF */ CHECK_NOSHUF(EA, 8); - tcg_gen_qemu_ld64(frame, EA, ctx->mem_idx); + tcg_gen_qemu_ld_i64(frame, EA, ctx->mem_idx, MO_TEUQ); } static void gen_return(DisasContext *ctx, TCGv_i64 dst, TCGv src) @@ -XXX,XX +XXX,XX @@ static void gen_vreg_load(DisasContext *ctx, intptr_t dstoff, TCGv src, tcg_gen_andi_tl(src, src, ~((int32_t)sizeof(MMVector) - 1)); } for (int i = 0; i < sizeof(MMVector) / 8; i++) { - tcg_gen_qemu_ld64(tmp, src, ctx->mem_idx); + tcg_gen_qemu_ld_i64(tmp, src, ctx->mem_idx, MO_TEUQ); tcg_gen_addi_tl(src, src, 8); tcg_gen_st_i64(tmp, cpu_env, dstoff + i * 8); } diff --git a/target/hexagon/idef-parser/parser-helpers.c b/target/hexagon/idef-parser/parser-helpers.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/idef-parser/parser-helpers.c +++ b/target/hexagon/idef-parser/parser-helpers.c @@ -XXX,XX +XXX,XX @@ void gen_load_cancel(Context *c, YYLTYPE *locp) void gen_load(Context *c, YYLTYPE *locp, HexValue *width, HexSignedness signedness, HexValue *ea, HexValue *dst) { - char size_suffix[4] = {0}; - const char *sign_suffix; + unsigned dst_bit_width; + unsigned src_bit_width; + /* Memop width is specified in the load macro */ assert_signedness(c, locp, signedness); - sign_suffix = (width->imm.value > 4) - ? "" - : ((signedness == UNSIGNED) ? "u" : "s"); + /* If dst is a variable, assert that is declared and load the type info */ if (dst->type == VARID) { find_variable(c, locp, dst, dst); } - snprintf(size_suffix, 4, "%" PRIu64, width->imm.value * 8); + src_bit_width = width->imm.value * 8; + dst_bit_width = MAX(dst->bit_width, 32); + /* Lookup the effective address EA */ find_variable(c, locp, ea, ea); OUT(c, locp, "if (insn->slot == 0 && pkt->pkt_has_store_s1) {\n"); OUT(c, locp, "probe_noshuf_load(", ea, ", ", width, ", ctx->mem_idx);\n"); OUT(c, locp, "process_store(ctx, 1);\n"); OUT(c, locp, "}\n"); - OUT(c, locp, "tcg_gen_qemu_ld", size_suffix, sign_suffix); + + OUT(c, locp, "tcg_gen_qemu_ld_i", &dst_bit_width); OUT(c, locp, "("); - if (dst->bit_width > width->imm.value * 8) { - /* - * Cast to the correct TCG type if necessary, to avoid implict cast - * warnings. This is needed when the width of the destination var is - * larger than the size of the requested load. - */ - OUT(c, locp, "(TCGv) "); + OUT(c, locp, dst, ", ", ea, ", ctx->mem_idx, MO_", &src_bit_width); + if (signedness == SIGNED) { + OUT(c, locp, " | MO_SIGN"); } - OUT(c, locp, dst, ", ", ea, ", ctx->mem_idx);\n"); + OUT(c, locp, " | MO_TE);\n"); } void gen_store(Context *c, YYLTYPE *locp, HexValue *width, HexValue *ea, 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 @@ void process_store(DisasContext *ctx, int slot_num) switch (ctx->store_width[slot_num]) { case 1: gen_check_store_width(ctx, slot_num); - tcg_gen_qemu_st8(hex_store_val32[slot_num], - hex_store_addr[slot_num], - ctx->mem_idx); + tcg_gen_qemu_st_tl(hex_store_val32[slot_num], + hex_store_addr[slot_num], + ctx->mem_idx, MO_UB); break; case 2: gen_check_store_width(ctx, slot_num); - tcg_gen_qemu_st16(hex_store_val32[slot_num], - hex_store_addr[slot_num], - ctx->mem_idx); + tcg_gen_qemu_st_tl(hex_store_val32[slot_num], + hex_store_addr[slot_num], + ctx->mem_idx, MO_TEUW); break; case 4: gen_check_store_width(ctx, slot_num); - tcg_gen_qemu_st32(hex_store_val32[slot_num], - hex_store_addr[slot_num], - ctx->mem_idx); + tcg_gen_qemu_st_tl(hex_store_val32[slot_num], + hex_store_addr[slot_num], + ctx->mem_idx, MO_TEUL); break; case 8: gen_check_store_width(ctx, slot_num); - tcg_gen_qemu_st64(hex_store_val64[slot_num], - hex_store_addr[slot_num], - ctx->mem_idx); + tcg_gen_qemu_st_i64(hex_store_val64[slot_num], + hex_store_addr[slot_num], + ctx->mem_idx, MO_TEUQ); break; default: { @@ -XXX,XX +XXX,XX @@ static void process_dczeroa(DisasContext *ctx) TCGv_i64 zero = tcg_constant_i64(0); tcg_gen_andi_tl(addr, hex_dczero_addr, ~0x1f); - tcg_gen_qemu_st64(zero, addr, ctx->mem_idx); + tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ); tcg_gen_addi_tl(addr, addr, 8); - tcg_gen_qemu_st64(zero, addr, ctx->mem_idx); + tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ); tcg_gen_addi_tl(addr, addr, 8); - tcg_gen_qemu_st64(zero, addr, ctx->mem_idx); + tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ); tcg_gen_addi_tl(addr, addr, 8); - tcg_gen_qemu_st64(zero, addr, ctx->mem_idx); + tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ); } } -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Anton Johansson <anjo@rev.ng> Message-Id: <20230502135741.1158035-5-richard.henderson@linaro.org> --- target/m68k/translate.c | 76 ++++++++++++++--------------------------- 1 file changed, 25 insertions(+), 51 deletions(-) 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 inline void gen_addr_fault(DisasContext *s) static inline TCGv gen_load(DisasContext *s, int opsize, TCGv addr, int sign, int index) { - TCGv tmp; - tmp = tcg_temp_new_i32(); - switch(opsize) { + TCGv tmp = tcg_temp_new_i32(); + + switch (opsize) { case OS_BYTE: - if (sign) - tcg_gen_qemu_ld8s(tmp, addr, index); - else - tcg_gen_qemu_ld8u(tmp, addr, index); - break; case OS_WORD: - if (sign) - tcg_gen_qemu_ld16s(tmp, addr, index); - else - tcg_gen_qemu_ld16u(tmp, addr, index); - break; case OS_LONG: - tcg_gen_qemu_ld32u(tmp, addr, index); + tcg_gen_qemu_ld_tl(tmp, addr, index, + opsize | (sign ? MO_SIGN : 0) | MO_TE); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static inline TCGv gen_load(DisasContext *s, int opsize, TCGv addr, static inline void gen_store(DisasContext *s, int opsize, TCGv addr, TCGv val, int index) { - switch(opsize) { + switch (opsize) { case OS_BYTE: - tcg_gen_qemu_st8(val, addr, index); - break; case OS_WORD: - tcg_gen_qemu_st16(val, addr, index); - break; case OS_LONG: - tcg_gen_qemu_st32(val, addr, index); + tcg_gen_qemu_st_tl(val, addr, index, opsize | MO_TE); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void gen_load_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp, tmp = tcg_temp_new(); switch (opsize) { case OS_BYTE: - tcg_gen_qemu_ld8s(tmp, addr, index); - gen_helper_exts32(cpu_env, fp, tmp); - break; case OS_WORD: - tcg_gen_qemu_ld16s(tmp, addr, index); - gen_helper_exts32(cpu_env, fp, tmp); - break; - case OS_LONG: - tcg_gen_qemu_ld32u(tmp, addr, index); + tcg_gen_qemu_ld_tl(tmp, addr, index, opsize | MO_SIGN | MO_TE); gen_helper_exts32(cpu_env, fp, tmp); break; case OS_SINGLE: - tcg_gen_qemu_ld32u(tmp, addr, index); + tcg_gen_qemu_ld_tl(tmp, addr, index, MO_TEUL); gen_helper_extf32(cpu_env, fp, tmp); break; case OS_DOUBLE: - tcg_gen_qemu_ld64(t64, addr, index); + tcg_gen_qemu_ld_i64(t64, addr, index, MO_TEUQ); gen_helper_extf64(cpu_env, fp, t64); break; case OS_EXTENDED: @@ -XXX,XX +XXX,XX @@ static void gen_load_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp, gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP); break; } - tcg_gen_qemu_ld32u(tmp, addr, index); + tcg_gen_qemu_ld_i32(tmp, addr, index, MO_TEUL); tcg_gen_shri_i32(tmp, tmp, 16); tcg_gen_st16_i32(tmp, fp, offsetof(FPReg, l.upper)); tcg_gen_addi_i32(tmp, addr, 4); - tcg_gen_qemu_ld64(t64, tmp, index); + tcg_gen_qemu_ld_i64(t64, tmp, index, MO_TEUQ); tcg_gen_st_i64(t64, fp, offsetof(FPReg, l.lower)); break; case OS_PACKED: @@ -XXX,XX +XXX,XX @@ static void gen_store_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp, tmp = tcg_temp_new(); switch (opsize) { case OS_BYTE: - gen_helper_reds32(tmp, cpu_env, fp); - tcg_gen_qemu_st8(tmp, addr, index); - break; case OS_WORD: - gen_helper_reds32(tmp, cpu_env, fp); - tcg_gen_qemu_st16(tmp, addr, index); - break; case OS_LONG: gen_helper_reds32(tmp, cpu_env, fp); - tcg_gen_qemu_st32(tmp, addr, index); + tcg_gen_qemu_st_tl(tmp, addr, index, opsize | MO_TE); break; case OS_SINGLE: gen_helper_redf32(tmp, cpu_env, fp); - tcg_gen_qemu_st32(tmp, addr, index); + tcg_gen_qemu_st_tl(tmp, addr, index, MO_TEUL); break; case OS_DOUBLE: gen_helper_redf64(t64, cpu_env, fp); - tcg_gen_qemu_st64(t64, addr, index); + tcg_gen_qemu_st_i64(t64, addr, index, MO_TEUQ); break; case OS_EXTENDED: if (m68k_feature(s->env, M68K_FEATURE_CF_FPU)) { @@ -XXX,XX +XXX,XX @@ static void gen_store_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp, } tcg_gen_ld16u_i32(tmp, fp, offsetof(FPReg, l.upper)); tcg_gen_shli_i32(tmp, tmp, 16); - tcg_gen_qemu_st32(tmp, addr, index); + tcg_gen_qemu_st_i32(tmp, addr, index, MO_TEUL); tcg_gen_addi_i32(tmp, addr, 4); tcg_gen_ld_i64(t64, fp, offsetof(FPReg, l.lower)); - tcg_gen_qemu_st64(t64, tmp, index); + tcg_gen_qemu_st_i64(t64, tmp, index, MO_TEUQ); break; case OS_PACKED: /* @@ -XXX,XX +XXX,XX @@ DISAS_INSN(movep) if (insn & 0x80) { for ( ; i > 0 ; i--) { tcg_gen_shri_i32(dbuf, reg, (i - 1) * 8); - tcg_gen_qemu_st8(dbuf, abuf, IS_USER(s)); + tcg_gen_qemu_st_i32(dbuf, abuf, IS_USER(s), MO_UB); if (i > 1) { tcg_gen_addi_i32(abuf, abuf, 2); } } } else { for ( ; i > 0 ; i--) { - tcg_gen_qemu_ld8u(dbuf, abuf, IS_USER(s)); + tcg_gen_qemu_ld_tl(dbuf, abuf, IS_USER(s), MO_UB); tcg_gen_deposit_i32(reg, reg, dbuf, (i - 1) * 8, 8); if (i > 1) { tcg_gen_addi_i32(abuf, abuf, 2); @@ -XXX,XX +XXX,XX @@ static void m68k_copy_line(TCGv dst, TCGv src, int index) t1 = tcg_temp_new_i64(); tcg_gen_andi_i32(addr, src, ~15); - tcg_gen_qemu_ld64(t0, addr, index); + tcg_gen_qemu_ld_i64(t0, addr, index, MO_TEUQ); tcg_gen_addi_i32(addr, addr, 8); - tcg_gen_qemu_ld64(t1, addr, index); + tcg_gen_qemu_ld_i64(t1, addr, index, MO_TEUQ); tcg_gen_andi_i32(addr, dst, ~15); - tcg_gen_qemu_st64(t0, addr, index); + tcg_gen_qemu_st_i64(t0, addr, index, MO_TEUQ); tcg_gen_addi_i32(addr, addr, 8); - tcg_gen_qemu_st64(t1, addr, index); + tcg_gen_qemu_st_i64(t1, addr, index, MO_TEUQ); } DISAS_INSN(move16_reg) @@ -XXX,XX +XXX,XX @@ static void gen_qemu_store_fcr(DisasContext *s, TCGv addr, int reg) tmp = tcg_temp_new(); gen_load_fcr(s, tmp, reg); - tcg_gen_qemu_st32(tmp, addr, index); + tcg_gen_qemu_st_tl(tmp, addr, index, MO_TEUL); } static void gen_qemu_load_fcr(DisasContext *s, TCGv addr, int reg) @@ -XXX,XX +XXX,XX @@ static void gen_qemu_load_fcr(DisasContext *s, TCGv addr, int reg) TCGv tmp; tmp = tcg_temp_new(); - tcg_gen_qemu_ld32u(tmp, addr, index); + tcg_gen_qemu_ld_tl(tmp, addr, index, MO_TEUL); gen_store_fcr(s, tmp, reg); } -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Anton Johansson <anjo@rev.ng> Message-Id: <20230502135741.1158035-6-richard.henderson@linaro.org> --- target/mips/tcg/translate.c | 8 ++++---- target/mips/tcg/nanomips_translate.c.inc | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) 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 @@ FOP_CONDNS(s, FMT_S, 32, gen_store_fpr32(ctx, fp0, fd)) /* load/store instructions. */ #ifdef CONFIG_USER_ONLY -#define OP_LD_ATOMIC(insn, fname) \ +#define OP_LD_ATOMIC(insn, memop) \ static inline void op_ld_##insn(TCGv ret, TCGv arg1, int mem_idx, \ DisasContext *ctx) \ { \ TCGv t0 = tcg_temp_new(); \ tcg_gen_mov_tl(t0, arg1); \ - tcg_gen_qemu_##fname(ret, arg1, ctx->mem_idx); \ + tcg_gen_qemu_ld_tl(ret, arg1, ctx->mem_idx, memop); \ tcg_gen_st_tl(t0, cpu_env, offsetof(CPUMIPSState, lladdr)); \ tcg_gen_st_tl(ret, cpu_env, offsetof(CPUMIPSState, llval)); \ } @@ -XXX,XX +XXX,XX @@ static inline void op_ld_##insn(TCGv ret, TCGv arg1, int mem_idx, \ gen_helper_##insn(ret, cpu_env, arg1, tcg_constant_i32(mem_idx)); \ } #endif -OP_LD_ATOMIC(ll, ld32s); +OP_LD_ATOMIC(ll, MO_TESL); #if defined(TARGET_MIPS64) -OP_LD_ATOMIC(lld, ld64); +OP_LD_ATOMIC(lld, MO_TEUQ); #endif #undef OP_LD_ATOMIC diff --git a/target/mips/tcg/nanomips_translate.c.inc b/target/mips/tcg/nanomips_translate.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/nanomips_translate.c.inc +++ b/target/mips/tcg/nanomips_translate.c.inc @@ -XXX,XX +XXX,XX @@ static void gen_llwp(DisasContext *ctx, uint32_t base, int16_t offset, TCGv tmp2 = tcg_temp_new(); gen_base_offset_addr(ctx, taddr, base, offset); - tcg_gen_qemu_ld64(tval, taddr, ctx->mem_idx); + tcg_gen_qemu_ld_i64(tval, taddr, ctx->mem_idx, MO_TEUQ); if (cpu_is_bigendian(ctx)) { tcg_gen_extr_i64_tl(tmp2, tmp1, tval); } else { -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Ilya Leoshkevich <iii@linux.ibm.com> Message-Id: <20230502135741.1158035-7-richard.henderson@linaro.org> --- target/s390x/tcg/translate.c | 152 ++++++++++++++++------------------- 1 file changed, 71 insertions(+), 81 deletions(-) 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 @@ static DisasJumpType op_clc(DisasContext *s, DisasOps *o) { int l = get_field(s, l1); TCGv_i32 vl; + MemOp mop; switch (l + 1) { case 1: - tcg_gen_qemu_ld8u(cc_src, o->addr1, get_mem_index(s)); - tcg_gen_qemu_ld8u(cc_dst, o->in2, get_mem_index(s)); - break; case 2: - tcg_gen_qemu_ld16u(cc_src, o->addr1, get_mem_index(s)); - tcg_gen_qemu_ld16u(cc_dst, o->in2, get_mem_index(s)); - break; case 4: - tcg_gen_qemu_ld32u(cc_src, o->addr1, get_mem_index(s)); - tcg_gen_qemu_ld32u(cc_dst, o->in2, get_mem_index(s)); - break; case 8: - tcg_gen_qemu_ld64(cc_src, o->addr1, get_mem_index(s)); - tcg_gen_qemu_ld64(cc_dst, o->in2, get_mem_index(s)); - break; + mop = ctz32(l + 1) | MO_TE; + tcg_gen_qemu_ld_tl(cc_src, o->addr1, get_mem_index(s), mop); + tcg_gen_qemu_ld_tl(cc_dst, o->in2, get_mem_index(s), mop); + gen_op_update2_cc_i64(s, CC_OP_LTUGTU_64, cc_src, cc_dst); + return DISAS_NEXT; default: vl = tcg_constant_i32(l); gen_helper_clc(cc_op, cpu_env, vl, o->addr1, o->in2); set_cc_static(s); return DISAS_NEXT; } - gen_op_update2_cc_i64(s, CC_OP_LTUGTU_64, cc_src, cc_dst); - return DISAS_NEXT; } static DisasJumpType op_clcl(DisasContext *s, DisasOps *o) @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_cvd(DisasContext *s, DisasOps *o) TCGv_i32 t2 = tcg_temp_new_i32(); tcg_gen_extrl_i64_i32(t2, o->in1); gen_helper_cvd(t1, t2); - tcg_gen_qemu_st64(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(t1, o->in2, get_mem_index(s), MO_TEUQ); return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o) switch (m3) { case 0xf: /* Effectively a 32-bit load. */ - tcg_gen_qemu_ld32u(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_TEUL); len = 32; goto one_insert; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o) case 0x6: case 0x3: /* Effectively a 16-bit load. */ - tcg_gen_qemu_ld16u(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_TEUW); len = 16; goto one_insert; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o) case 0x2: case 0x1: /* Effectively an 8-bit load. */ - tcg_gen_qemu_ld8u(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_UB); len = 8; goto one_insert; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o) ccm = 0; while (m3) { if (m3 & 0x8) { - tcg_gen_qemu_ld8u(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_UB); tcg_gen_addi_i64(o->in2, o->in2, 1); tcg_gen_deposit_i64(o->out, o->out, tmp, pos, 8); ccm |= 0xffull << pos; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_llgt(DisasContext *s, DisasOps *o) static DisasJumpType op_ld8s(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_ld8s(o->out, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_SB); return DISAS_NEXT; } static DisasJumpType op_ld8u(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_ld8u(o->out, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_UB); return DISAS_NEXT; } static DisasJumpType op_ld16s(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_ld16s(o->out, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TESW); return DISAS_NEXT; } static DisasJumpType op_ld16u(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_ld16u(o->out, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TEUW); return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lat(DisasContext *s, DisasOps *o) static DisasJumpType op_lgat(DisasContext *s, DisasOps *o) { TCGLabel *lab = gen_new_label(); - tcg_gen_qemu_ld64(o->out, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TEUQ); /* The value is stored even in case of trap. */ tcg_gen_brcondi_i64(TCG_COND_NE, o->out, 0, lab); gen_trap(s); @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lfhat(DisasContext *s, DisasOps *o) static DisasJumpType op_llgfat(DisasContext *s, DisasOps *o) { TCGLabel *lab = gen_new_label(); - tcg_gen_qemu_ld32u(o->out, o->in2, get_mem_index(s)); + + tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TEUL); /* The value is stored even in case of trap. */ tcg_gen_brcondi_i64(TCG_COND_NE, o->out, 0, lab); gen_trap(s); @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lpswe(DisasContext *s, DisasOps *o) tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUQ | MO_ALIGN_8); tcg_gen_addi_i64(o->in2, o->in2, 8); - tcg_gen_qemu_ld64(t2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t2, o->in2, get_mem_index(s), MO_TEUQ); gen_helper_load_psw(cpu_env, t1, t2); return DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lm32(DisasContext *s, DisasOps *o) /* Only one register to read. */ t1 = tcg_temp_new_i64(); if (unlikely(r1 == r3)) { - tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL); store_reg32_i64(r1, t1); return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lm32(DisasContext *s, DisasOps *o) /* First load the values of the first and last registers to trigger possible page faults. */ t2 = tcg_temp_new_i64(); - tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL); tcg_gen_addi_i64(t2, o->in2, 4 * ((r3 - r1) & 15)); - tcg_gen_qemu_ld32u(t2, t2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t2, t2, get_mem_index(s), MO_TEUL); store_reg32_i64(r1, t1); store_reg32_i64(r3, t2); @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lm32(DisasContext *s, DisasOps *o) while (r1 != r3) { r1 = (r1 + 1) & 15; tcg_gen_add_i64(o->in2, o->in2, t2); - tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL); store_reg32_i64(r1, t1); } return DISAS_NEXT; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lmh(DisasContext *s, DisasOps *o) /* Only one register to read. */ t1 = tcg_temp_new_i64(); if (unlikely(r1 == r3)) { - tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL); store_reg32h_i64(r1, t1); return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lmh(DisasContext *s, DisasOps *o) /* First load the values of the first and last registers to trigger possible page faults. */ t2 = tcg_temp_new_i64(); - tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL); tcg_gen_addi_i64(t2, o->in2, 4 * ((r3 - r1) & 15)); - tcg_gen_qemu_ld32u(t2, t2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t2, t2, get_mem_index(s), MO_TEUL); store_reg32h_i64(r1, t1); store_reg32h_i64(r3, t2); @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lmh(DisasContext *s, DisasOps *o) while (r1 != r3) { r1 = (r1 + 1) & 15; tcg_gen_add_i64(o->in2, o->in2, t2); - tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL); store_reg32h_i64(r1, t1); } return DISAS_NEXT; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lm64(DisasContext *s, DisasOps *o) /* Only one register to read. */ if (unlikely(r1 == r3)) { - tcg_gen_qemu_ld64(regs[r1], o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(regs[r1], o->in2, get_mem_index(s), MO_TEUQ); return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lm64(DisasContext *s, DisasOps *o) possible page faults. */ t1 = tcg_temp_new_i64(); t2 = tcg_temp_new_i64(); - tcg_gen_qemu_ld64(t1, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUQ); tcg_gen_addi_i64(t2, o->in2, 8 * ((r3 - r1) & 15)); - tcg_gen_qemu_ld64(regs[r3], t2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(regs[r3], t2, get_mem_index(s), MO_TEUQ); tcg_gen_mov_i64(regs[r1], t1); /* Only two registers to read. */ @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_lm64(DisasContext *s, DisasOps *o) while (r1 != r3) { r1 = (r1 + 1) & 15; tcg_gen_add_i64(o->in2, o->in2, t1); - tcg_gen_qemu_ld64(regs[r1], o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(regs[r1], o->in2, get_mem_index(s), MO_TEUQ); } return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_soc(DisasContext *s, DisasOps *o) a = get_address(s, 0, get_field(s, b2), get_field(s, d2)); switch (s->insn->data) { case 1: /* STOCG */ - tcg_gen_qemu_st64(regs[r1], a, get_mem_index(s)); + tcg_gen_qemu_st_i64(regs[r1], a, get_mem_index(s), MO_TEUQ); break; case 0: /* STOC */ - tcg_gen_qemu_st32(regs[r1], a, get_mem_index(s)); + tcg_gen_qemu_st_i64(regs[r1], a, get_mem_index(s), MO_TEUL); break; case 2: /* STOCFH */ h = tcg_temp_new_i64(); tcg_gen_shri_i64(h, regs[r1], 32); - tcg_gen_qemu_st32(h, a, get_mem_index(s)); + tcg_gen_qemu_st_i64(h, a, get_mem_index(s), MO_TEUL); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_ectg(DisasContext *s, DisasOps *o) gen_addi_and_wrap_i64(s, o->addr1, regs[r3], 0); /* load the third operand into r3 before modifying anything */ - tcg_gen_qemu_ld64(regs[r3], o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(regs[r3], o->addr1, get_mem_index(s), MO_TEUQ); /* subtract CPU timer from first operand and store in GR0 */ gen_helper_stpt(tmp, cpu_env); @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stcke(DisasContext *s, DisasOps *o) tcg_gen_shri_i64(c1, c1, 8); tcg_gen_ori_i64(c2, c2, 0x10000); tcg_gen_or_i64(c2, c2, todpr); - tcg_gen_qemu_st64(c1, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(c1, o->in2, get_mem_index(s), MO_TEUQ); tcg_gen_addi_i64(o->in2, o->in2, 8); - tcg_gen_qemu_st64(c2, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(c2, o->in2, get_mem_index(s), MO_TEUQ); /* ??? We don't implement clock states. */ gen_op_movi_cc(s, 0); return DISAS_NEXT; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stnosm(DisasContext *s, DisasOps *o) restart, we'll have the wrong SYSTEM MASK in place. */ t = tcg_temp_new_i64(); tcg_gen_shri_i64(t, psw_mask, 56); - tcg_gen_qemu_st8(t, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(t, o->addr1, get_mem_index(s), MO_UB); if (s->fields.op == 0xac) { tcg_gen_andi_i64(psw_mask, psw_mask, @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stfle(DisasContext *s, DisasOps *o) static DisasJumpType op_st8(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st8(o->in1, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->in1, o->in2, get_mem_index(s), MO_UB); return DISAS_NEXT; } static DisasJumpType op_st16(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st16(o->in1, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->in1, o->in2, get_mem_index(s), MO_TEUW); return DISAS_NEXT; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o) case 0xf: /* Effectively a 32-bit store. */ tcg_gen_shri_i64(tmp, o->in1, pos); - tcg_gen_qemu_st32(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_TEUL); break; case 0xc: @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o) case 0x3: /* Effectively a 16-bit store. */ tcg_gen_shri_i64(tmp, o->in1, pos); - tcg_gen_qemu_st16(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_TEUW); break; case 0x8: @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o) case 0x1: /* Effectively an 8-bit store. */ tcg_gen_shri_i64(tmp, o->in1, pos); - tcg_gen_qemu_st8(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_UB); break; default: @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o) while (m3) { if (m3 & 0x8) { tcg_gen_shri_i64(tmp, o->in1, pos); - tcg_gen_qemu_st8(tmp, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_UB); tcg_gen_addi_i64(o->in2, o->in2, 1); } m3 = (m3 << 1) & 0xf; @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stm(DisasContext *s, DisasOps *o) TCGv_i64 tsize = tcg_constant_i64(size); while (1) { - if (size == 8) { - tcg_gen_qemu_st64(regs[r1], o->in2, get_mem_index(s)); - } else { - tcg_gen_qemu_st32(regs[r1], o->in2, get_mem_index(s)); - } + tcg_gen_qemu_st_i64(regs[r1], o->in2, get_mem_index(s), + size == 8 ? MO_TEUQ : MO_TEUL); if (r1 == r3) { break; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_stmh(DisasContext *s, DisasOps *o) while (1) { tcg_gen_shl_i64(t, regs[r1], t32); - tcg_gen_qemu_st32(t, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(t, o->in2, get_mem_index(s), MO_TEUL); if (r1 == r3) { break; } @@ -XXX,XX +XXX,XX @@ static DisasJumpType op_xc(DisasContext *s, DisasOps *o) l++; while (l >= 8) { - tcg_gen_qemu_st64(o->in2, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UQ); l -= 8; if (l > 0) { tcg_gen_addi_i64(o->addr1, o->addr1, 8); } } if (l >= 4) { - tcg_gen_qemu_st32(o->in2, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UL); l -= 4; if (l > 0) { tcg_gen_addi_i64(o->addr1, o->addr1, 4); } } if (l >= 2) { - tcg_gen_qemu_st16(o->in2, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UW); l -= 2; if (l > 0) { tcg_gen_addi_i64(o->addr1, o->addr1, 2); } } if (l) { - tcg_gen_qemu_st8(o->in2, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UB); } gen_op_movi_cc(s, 0); return DISAS_NEXT; @@ -XXX,XX +XXX,XX @@ static void wout_cond_e1e2(DisasContext *s, DisasOps *o) static void wout_m1_8(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st8(o->out, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_UB); } #define SPEC_wout_m1_8 0 static void wout_m1_16(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st16(o->out, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_TEUW); } #define SPEC_wout_m1_16 0 @@ -XXX,XX +XXX,XX @@ static void wout_m1_16a(DisasContext *s, DisasOps *o) static void wout_m1_32(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st32(o->out, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_TEUL); } #define SPEC_wout_m1_32 0 @@ -XXX,XX +XXX,XX @@ static void wout_m1_32a(DisasContext *s, DisasOps *o) static void wout_m1_64(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st64(o->out, o->addr1, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_TEUQ); } #define SPEC_wout_m1_64 0 @@ -XXX,XX +XXX,XX @@ static void wout_m1_64a(DisasContext *s, DisasOps *o) static void wout_m2_32(DisasContext *s, DisasOps *o) { - tcg_gen_qemu_st32(o->out, o->in2, get_mem_index(s)); + tcg_gen_qemu_st_i64(o->out, o->in2, get_mem_index(s), MO_TEUL); } #define SPEC_wout_m2_32 0 @@ -XXX,XX +XXX,XX @@ static void in1_m1_8u(DisasContext *s, DisasOps *o) { in1_la1(s, o); o->in1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld8u(o->in1, o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_UB); } #define SPEC_in1_m1_8u 0 @@ -XXX,XX +XXX,XX @@ static void in1_m1_16s(DisasContext *s, DisasOps *o) { in1_la1(s, o); o->in1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld16s(o->in1, o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TESW); } #define SPEC_in1_m1_16s 0 @@ -XXX,XX +XXX,XX @@ static void in1_m1_16u(DisasContext *s, DisasOps *o) { in1_la1(s, o); o->in1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld16u(o->in1, o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TEUW); } #define SPEC_in1_m1_16u 0 @@ -XXX,XX +XXX,XX @@ static void in1_m1_32s(DisasContext *s, DisasOps *o) { in1_la1(s, o); o->in1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld32s(o->in1, o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TESL); } #define SPEC_in1_m1_32s 0 @@ -XXX,XX +XXX,XX @@ static void in1_m1_32u(DisasContext *s, DisasOps *o) { in1_la1(s, o); o->in1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld32u(o->in1, o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TEUL); } #define SPEC_in1_m1_32u 0 @@ -XXX,XX +XXX,XX @@ static void in1_m1_64(DisasContext *s, DisasOps *o) { in1_la1(s, o); o->in1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld64(o->in1, o->addr1, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TEUQ); } #define SPEC_in1_m1_64 0 @@ -XXX,XX +XXX,XX @@ static void in2_sh(DisasContext *s, DisasOps *o) static void in2_m2_8u(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld8u(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_UB); } #define SPEC_in2_m2_8u 0 static void in2_m2_16s(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld16s(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TESW); } #define SPEC_in2_m2_16s 0 static void in2_m2_16u(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld16u(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUW); } #define SPEC_in2_m2_16u 0 static void in2_m2_32s(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld32s(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TESL); } #define SPEC_in2_m2_32s 0 static void in2_m2_32u(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld32u(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUL); } #define SPEC_in2_m2_32u 0 @@ -XXX,XX +XXX,XX @@ static void in2_m2_32ua(DisasContext *s, DisasOps *o) static void in2_m2_64(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld64(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUQ); } #define SPEC_in2_m2_64 0 static void in2_m2_64w(DisasContext *s, DisasOps *o) { in2_a2(s, o); - tcg_gen_qemu_ld64(o->in2, o->in2, get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUQ); gen_addi_and_wrap_i64(s, o->in2, o->in2, 0); } #define SPEC_in2_m2_64w 0 @@ -XXX,XX +XXX,XX @@ static void in2_m2_64a(DisasContext *s, DisasOps *o) static void in2_mri2_16s(DisasContext *s, DisasOps *o) { o->in2 = tcg_temp_new_i64(); - tcg_gen_qemu_ld16s(o->in2, gen_ri2(s), get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, gen_ri2(s), get_mem_index(s), MO_TESW); } #define SPEC_in2_mri2_16s 0 static void in2_mri2_16u(DisasContext *s, DisasOps *o) { o->in2 = tcg_temp_new_i64(); - tcg_gen_qemu_ld16u(o->in2, gen_ri2(s), get_mem_index(s)); + tcg_gen_qemu_ld_i64(o->in2, gen_ri2(s), get_mem_index(s), MO_TEUW); } #define SPEC_in2_mri2_16u 0 -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Anton Johansson <anjo@rev.ng> Message-Id: <20230502135741.1158035-8-richard.henderson@linaro.org> --- target/sparc/translate.c | 43 ++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 15 deletions(-) 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 void disas_sparc_insn(DisasContext * dc, unsigned int insn) switch (xop) { case 0x0: /* ld, V9 lduw, load unsigned word */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld32u(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TEUL); break; case 0x1: /* ldub, load unsigned byte */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld8u(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_UB); break; case 0x2: /* lduh, load unsigned halfword */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld16u(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TEUW); break; case 0x3: /* ldd, load double word */ if (rd & 1) @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) gen_address_mask(dc, cpu_addr); t64 = tcg_temp_new_i64(); - tcg_gen_qemu_ld64(t64, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_i64(t64, cpu_addr, + dc->mem_idx, MO_TEUQ); tcg_gen_trunc_i64_tl(cpu_val, t64); tcg_gen_ext32u_tl(cpu_val, cpu_val); gen_store_gpr(dc, rd + 1, cpu_val); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) break; case 0x9: /* ldsb, load signed byte */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld8s(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, dc->mem_idx, MO_SB); break; case 0xa: /* ldsh, load signed halfword */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld16s(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TESW); break; case 0xd: /* ldstub */ gen_ldstub(dc, cpu_val, cpu_addr, dc->mem_idx); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) #ifdef TARGET_SPARC64 case 0x08: /* V9 ldsw */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld32s(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TESL); break; case 0x0b: /* V9 ldx */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_ld64(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TEUQ); break; case 0x18: /* V9 ldswa */ gen_ld_asi(dc, cpu_val, cpu_addr, insn, MO_TESL); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) switch (xop) { case 0x4: /* st, store word */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_st32(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TEUL); break; case 0x5: /* stb, store byte */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_st8(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_tl(cpu_val, cpu_addr, dc->mem_idx, MO_UB); break; case 0x6: /* sth, store halfword */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_st16(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TEUW); break; case 0x7: /* std, store double word */ if (rd & 1) @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) lo = gen_load_gpr(dc, rd + 1); t64 = tcg_temp_new_i64(); tcg_gen_concat_tl_i64(t64, lo, cpu_val); - tcg_gen_qemu_st64(t64, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_i64(t64, cpu_addr, + dc->mem_idx, MO_TEUQ); } break; #if !defined(CONFIG_USER_ONLY) || defined(TARGET_SPARC64) @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) #ifdef TARGET_SPARC64 case 0x0e: /* V9 stx */ gen_address_mask(dc, cpu_addr); - tcg_gen_qemu_st64(cpu_val, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_tl(cpu_val, cpu_addr, + dc->mem_idx, MO_TEUQ); break; case 0x1e: /* V9 stxa */ gen_st_asi(dc, cpu_val, cpu_addr, insn, MO_TEUQ); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) #ifdef TARGET_SPARC64 gen_address_mask(dc, cpu_addr); if (rd == 1) { - tcg_gen_qemu_st64(cpu_fsr, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_tl(cpu_fsr, cpu_addr, + dc->mem_idx, MO_TEUQ); break; } #endif - tcg_gen_qemu_st32(cpu_fsr, cpu_addr, dc->mem_idx); + tcg_gen_qemu_st_tl(cpu_fsr, cpu_addr, + dc->mem_idx, MO_TEUL); } break; case 0x26: -- 2.34.1 Convert away from the old interface with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Max Filippov <jcmvbkbc@gmail.com> Message-Id: <20230502135741.1158035-9-richard.henderson@linaro.org> --- target/xtensa/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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 void translate_dcache(DisasContext *dc, const OpcodeArg arg[], TCGv_i32 res = tcg_temp_new_i32(); tcg_gen_addi_i32(addr, arg[0].in, arg[1].imm); - tcg_gen_qemu_ld8u(res, addr, dc->cring); + tcg_gen_qemu_ld_i32(res, addr, dc->cring, MO_UB); } static void translate_depbits(DisasContext *dc, const OpcodeArg arg[], @@ -XXX,XX +XXX,XX @@ static void translate_l32r(DisasContext *dc, const OpcodeArg arg[], } else { tmp = tcg_constant_i32(arg[1].imm); } - tcg_gen_qemu_ld32u(arg[0].out, tmp, dc->cring); + tcg_gen_qemu_ld_i32(arg[0].out, tmp, dc->cring, MO_TEUL); } static void translate_loop(DisasContext *dc, const OpcodeArg arg[], -- 2.34.1 Remove the old interfaces with the implicit MemOp argument. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: David Hildenbrand <david@redhat.com> Message-Id: <20230502135741.1158035-10-richard.henderson@linaro.org> --- include/tcg/tcg-op.h | 55 -------------------------------------------- 1 file changed, 55 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 @@ void tcg_gen_qemu_st_i64(TCGv_i64, TCGv, TCGArg, MemOp); void tcg_gen_qemu_ld_i128(TCGv_i128, TCGv, TCGArg, MemOp); void tcg_gen_qemu_st_i128(TCGv_i128, TCGv, TCGArg, MemOp); -static inline void tcg_gen_qemu_ld8u(TCGv ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_UB); -} - -static inline void tcg_gen_qemu_ld8s(TCGv ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_SB); -} - -static inline void tcg_gen_qemu_ld16u(TCGv ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TEUW); -} - -static inline void tcg_gen_qemu_ld16s(TCGv ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TESW); -} - -static inline void tcg_gen_qemu_ld32u(TCGv ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TEUL); -} - -static inline void tcg_gen_qemu_ld32s(TCGv ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TESL); -} - -static inline void tcg_gen_qemu_ld64(TCGv_i64 ret, TCGv addr, int mem_index) -{ - tcg_gen_qemu_ld_i64(ret, addr, mem_index, MO_TEUQ); -} - -static inline void tcg_gen_qemu_st8(TCGv arg, TCGv addr, int mem_index) -{ - tcg_gen_qemu_st_tl(arg, addr, mem_index, MO_UB); -} - -static inline void tcg_gen_qemu_st16(TCGv arg, TCGv addr, int mem_index) -{ - tcg_gen_qemu_st_tl(arg, addr, mem_index, MO_TEUW); -} - -static inline void tcg_gen_qemu_st32(TCGv arg, TCGv addr, int mem_index) -{ - tcg_gen_qemu_st_tl(arg, addr, mem_index, MO_TEUL); -} - -static inline void tcg_gen_qemu_st64(TCGv_i64 arg, TCGv addr, int mem_index) -{ - tcg_gen_qemu_st_i64(arg, addr, mem_index, MO_TEUQ); -} - void tcg_gen_atomic_cmpxchg_i32(TCGv_i32, TCGv, TCGv_i32, TCGv_i32, TCGArg, MemOp); void tcg_gen_atomic_cmpxchg_i64(TCGv_i64, TCGv, TCGv_i64, TCGv_i64, -- 2.34.1 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/alpha/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 @@ struct DisasContext { #ifdef CONFIG_USER_ONLY #define UNALIGN(C) (C)->unalign #else -#define UNALIGN(C) 0 +#define UNALIGN(C) MO_ALIGN #endif /* Target-specific return values from translate_one, indicating the -- 2.34.1 Mark all memory operations that are not already marked with UNALIGN. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/alpha/translate.c | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) 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 DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) switch ((insn >> 12) & 0xF) { case 0x0: /* Longword physical access (hw_ldl/p) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL); + tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL | MO_ALIGN); break; case 0x1: /* Quadword physical access (hw_ldq/p) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ); + tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN); break; case 0x2: /* Longword physical access with lock (hw_ldl_l/p) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL); + tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL | MO_ALIGN); tcg_gen_mov_i64(cpu_lock_addr, addr); tcg_gen_mov_i64(cpu_lock_value, va); break; case 0x3: /* Quadword physical access with lock (hw_ldq_l/p) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ); + tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN); tcg_gen_mov_i64(cpu_lock_addr, addr); tcg_gen_mov_i64(cpu_lock_value, va); break; @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) goto invalid_opc; case 0xA: /* Longword virtual access with protection check (hw_ldl/w) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX, MO_LESL); + tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX, + MO_LESL | MO_ALIGN); break; case 0xB: /* Quadword virtual access with protection check (hw_ldq/w) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX, MO_LEUQ); + tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX, + MO_LEUQ | MO_ALIGN); break; case 0xC: /* Longword virtual access with alt access mode (hw_ldl/a)*/ @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) case 0xE: /* Longword virtual access with alternate access mode and protection checks (hw_ldl/wa) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX, MO_LESL); + tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX, + MO_LESL | MO_ALIGN); break; case 0xF: /* Quadword virtual access with alternate access mode and protection checks (hw_ldq/wa) */ - tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX, MO_LEUQ); + tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX, + MO_LEUQ | MO_ALIGN); break; } break; @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) vb = load_gpr(ctx, rb); tmp = tcg_temp_new(); tcg_gen_addi_i64(tmp, vb, disp12); - tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LESL); + tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LESL | MO_ALIGN); break; case 0x1: /* Quadword physical access */ @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) vb = load_gpr(ctx, rb); tmp = tcg_temp_new(); tcg_gen_addi_i64(tmp, vb, disp12); - tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LEUQ); + tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN); break; case 0x2: /* Longword physical access with lock */ ret = gen_store_conditional(ctx, ra, rb, disp12, - MMU_PHYS_IDX, MO_LESL); + MMU_PHYS_IDX, MO_LESL | MO_ALIGN); break; case 0x3: /* Quadword physical access with lock */ ret = gen_store_conditional(ctx, ra, rb, disp12, - MMU_PHYS_IDX, MO_LEUQ); + MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN); break; case 0x4: /* Longword virtual access */ @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) break; case 0x2A: /* LDL_L */ - gen_load_int(ctx, ra, rb, disp16, MO_LESL, 0, 1); + gen_load_int(ctx, ra, rb, disp16, MO_LESL | MO_ALIGN, 0, 1); break; case 0x2B: /* LDQ_L */ - gen_load_int(ctx, ra, rb, disp16, MO_LEUQ, 0, 1); + gen_load_int(ctx, ra, rb, disp16, MO_LEUQ | MO_ALIGN, 0, 1); break; case 0x2C: /* STL */ @@ -XXX,XX +XXX,XX @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn) case 0x2E: /* STL_C */ ret = gen_store_conditional(ctx, ra, rb, disp16, - ctx->mem_idx, MO_LESL); + ctx->mem_idx, MO_LESL | MO_ALIGN); break; case 0x2F: /* STQ_C */ ret = gen_store_conditional(ctx, ra, rb, disp16, - ctx->mem_idx, MO_LEUQ); + ctx->mem_idx, MO_LEUQ | MO_ALIGN); break; case 0x30: /* BR */ -- 2.34.1 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configs/targets/alpha-linux-user.mak | 1 - configs/targets/alpha-softmmu.mak | 1 - 2 files changed, 2 deletions(-) diff --git a/configs/targets/alpha-linux-user.mak b/configs/targets/alpha-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/alpha-linux-user.mak +++ b/configs/targets/alpha-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=alpha TARGET_SYSTBL_ABI=common TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y diff --git a/configs/targets/alpha-softmmu.mak b/configs/targets/alpha-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/alpha-softmmu.mak +++ b/configs/targets/alpha-softmmu.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=alpha -TARGET_ALIGNED_ONLY=y TARGET_SUPPORTS_MTTCG=y -- 2.34.1 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hppa/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 @@ typedef struct DisasContext { #ifdef CONFIG_USER_ONLY #define UNALIGN(C) (C)->unalign #else -#define UNALIGN(C) 0 +#define UNALIGN(C) MO_ALIGN #endif /* Note that ssm/rsm instructions number PSW_W and PSW_E differently. */ -- 2.34.1 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configs/targets/hppa-linux-user.mak | 1 - configs/targets/hppa-softmmu.mak | 1 - 2 files changed, 2 deletions(-) diff --git a/configs/targets/hppa-linux-user.mak b/configs/targets/hppa-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/hppa-linux-user.mak +++ b/configs/targets/hppa-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=hppa TARGET_SYSTBL_ABI=common,32 TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y diff --git a/configs/targets/hppa-softmmu.mak b/configs/targets/hppa-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/hppa-softmmu.mak +++ b/configs/targets/hppa-softmmu.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=hppa -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y TARGET_SUPPORTS_MTTCG=y -- 2.34.1 Acked-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sparc/translate.c | 66 +++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 32 deletions(-) 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 void gen_swap(DisasContext *dc, TCGv dst, TCGv src, TCGv addr, int mmu_idx, MemOp memop) { gen_address_mask(dc, addr); - tcg_gen_atomic_xchg_tl(dst, addr, src, mmu_idx, memop); + tcg_gen_atomic_xchg_tl(dst, addr, src, mmu_idx, memop | MO_ALIGN); } static void gen_ldstub(DisasContext *dc, TCGv dst, TCGv addr, int mmu_idx) @@ -XXX,XX +XXX,XX @@ static void gen_ld_asi(DisasContext *dc, TCGv dst, TCGv addr, break; case GET_ASI_DIRECT: gen_address_mask(dc, addr); - tcg_gen_qemu_ld_tl(dst, addr, da.mem_idx, da.memop); + tcg_gen_qemu_ld_tl(dst, addr, da.mem_idx, da.memop | MO_ALIGN); break; default: { TCGv_i32 r_asi = tcg_constant_i32(da.asi); - TCGv_i32 r_mop = tcg_constant_i32(memop); + TCGv_i32 r_mop = tcg_constant_i32(memop | MO_ALIGN); save_state(dc); #ifdef TARGET_SPARC64 @@ -XXX,XX +XXX,XX @@ static void gen_st_asi(DisasContext *dc, TCGv src, TCGv addr, /* fall through */ case GET_ASI_DIRECT: gen_address_mask(dc, addr); - tcg_gen_qemu_st_tl(src, addr, da.mem_idx, da.memop); + tcg_gen_qemu_st_tl(src, addr, da.mem_idx, da.memop | MO_ALIGN); break; #if !defined(TARGET_SPARC64) && !defined(CONFIG_USER_ONLY) case GET_ASI_BCOPY: @@ -XXX,XX +XXX,XX @@ static void gen_st_asi(DisasContext *dc, TCGv src, TCGv addr, default: { TCGv_i32 r_asi = tcg_constant_i32(da.asi); - TCGv_i32 r_mop = tcg_constant_i32(memop & MO_SIZE); + TCGv_i32 r_mop = tcg_constant_i32(memop | MO_ALIGN); save_state(dc); #ifdef TARGET_SPARC64 @@ -XXX,XX +XXX,XX @@ static void gen_cas_asi(DisasContext *dc, TCGv addr, TCGv cmpv, case GET_ASI_DIRECT: oldv = tcg_temp_new(); tcg_gen_atomic_cmpxchg_tl(oldv, addr, cmpv, gen_load_gpr(dc, rd), - da.mem_idx, da.memop); + da.mem_idx, da.memop | MO_ALIGN); gen_store_gpr(dc, rd, oldv); break; default: @@ -XXX,XX +XXX,XX @@ static void gen_ldf_asi(DisasContext *dc, TCGv addr, switch (size) { case 4: d32 = gen_dest_fpr_F(dc); - tcg_gen_qemu_ld_i32(d32, addr, da.mem_idx, da.memop); + tcg_gen_qemu_ld_i32(d32, addr, da.mem_idx, da.memop | MO_ALIGN); gen_store_fpr_F(dc, rd, d32); break; case 8: @@ -XXX,XX +XXX,XX @@ static void gen_ldf_asi(DisasContext *dc, TCGv addr, /* Valid for lddfa only. */ if (size == 8) { gen_address_mask(dc, addr); - tcg_gen_qemu_ld_i64(cpu_fpr[rd / 2], addr, da.mem_idx, da.memop); + tcg_gen_qemu_ld_i64(cpu_fpr[rd / 2], addr, da.mem_idx, + da.memop | MO_ALIGN); } else { gen_exception(dc, TT_ILL_INSN); } @@ -XXX,XX +XXX,XX @@ static void gen_ldf_asi(DisasContext *dc, TCGv addr, default: { TCGv_i32 r_asi = tcg_constant_i32(da.asi); - TCGv_i32 r_mop = tcg_constant_i32(da.memop); + TCGv_i32 r_mop = tcg_constant_i32(da.memop | MO_ALIGN); save_state(dc); /* According to the table in the UA2011 manual, the only @@ -XXX,XX +XXX,XX @@ static void gen_stf_asi(DisasContext *dc, TCGv addr, switch (size) { case 4: d32 = gen_load_fpr_F(dc, rd); - tcg_gen_qemu_st_i32(d32, addr, da.mem_idx, da.memop); + tcg_gen_qemu_st_i32(d32, addr, da.mem_idx, da.memop | MO_ALIGN); break; case 8: tcg_gen_qemu_st_i64(cpu_fpr[rd / 2], addr, da.mem_idx, @@ -XXX,XX +XXX,XX @@ static void gen_stf_asi(DisasContext *dc, TCGv addr, /* Valid for stdfa only. */ if (size == 8) { gen_address_mask(dc, addr); - tcg_gen_qemu_st_i64(cpu_fpr[rd / 2], addr, da.mem_idx, da.memop); + tcg_gen_qemu_st_i64(cpu_fpr[rd / 2], addr, da.mem_idx, + da.memop | MO_ALIGN); } else { gen_exception(dc, TT_ILL_INSN); } @@ -XXX,XX +XXX,XX @@ static void gen_ldda_asi(DisasContext *dc, TCGv addr, int insn, int rd) TCGv_i64 tmp = tcg_temp_new_i64(); gen_address_mask(dc, addr); - tcg_gen_qemu_ld_i64(tmp, addr, da.mem_idx, da.memop); + tcg_gen_qemu_ld_i64(tmp, addr, da.mem_idx, da.memop | MO_ALIGN); /* Note that LE ldda acts as if each 32-bit register result is byte swapped. Having just performed one @@ -XXX,XX +XXX,XX @@ static void gen_stda_asi(DisasContext *dc, TCGv hi, TCGv addr, tcg_gen_concat32_i64(t64, hi, lo); } gen_address_mask(dc, addr); - tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop); + tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop | MO_ALIGN); } break; @@ -XXX,XX +XXX,XX @@ static void gen_casx_asi(DisasContext *dc, TCGv addr, TCGv cmpv, case GET_ASI_DIRECT: oldv = tcg_temp_new(); tcg_gen_atomic_cmpxchg_tl(oldv, addr, cmpv, gen_load_gpr(dc, rd), - da.mem_idx, da.memop); + da.mem_idx, da.memop | MO_ALIGN); gen_store_gpr(dc, rd, oldv); break; default: @@ -XXX,XX +XXX,XX @@ static void gen_ldda_asi(DisasContext *dc, TCGv addr, int insn, int rd) return; case GET_ASI_DIRECT: gen_address_mask(dc, addr); - tcg_gen_qemu_ld_i64(t64, addr, da.mem_idx, da.memop); + tcg_gen_qemu_ld_i64(t64, addr, da.mem_idx, da.memop | MO_ALIGN); break; default: { @@ -XXX,XX +XXX,XX @@ static void gen_stda_asi(DisasContext *dc, TCGv hi, TCGv addr, break; case GET_ASI_DIRECT: gen_address_mask(dc, addr); - tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop); + tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop | MO_ALIGN); break; case GET_ASI_BFILL: /* Store 32 bytes of T64 to ADDR. */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0x0: /* ld, V9 lduw, load unsigned word */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TEUL); + dc->mem_idx, MO_TEUL | MO_ALIGN); break; case 0x1: /* ldub, load unsigned byte */ gen_address_mask(dc, cpu_addr); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0x2: /* lduh, load unsigned halfword */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TEUW); + dc->mem_idx, MO_TEUW | MO_ALIGN); break; case 0x3: /* ldd, load double word */ if (rd & 1) @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) gen_address_mask(dc, cpu_addr); t64 = tcg_temp_new_i64(); tcg_gen_qemu_ld_i64(t64, cpu_addr, - dc->mem_idx, MO_TEUQ); + dc->mem_idx, MO_TEUQ | MO_ALIGN); tcg_gen_trunc_i64_tl(cpu_val, t64); tcg_gen_ext32u_tl(cpu_val, cpu_val); gen_store_gpr(dc, rd + 1, cpu_val); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0xa: /* ldsh, load signed halfword */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TESW); + dc->mem_idx, MO_TESW | MO_ALIGN); break; case 0xd: /* ldstub */ gen_ldstub(dc, cpu_val, cpu_addr, dc->mem_idx); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0x08: /* V9 ldsw */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TESL); + dc->mem_idx, MO_TESL | MO_ALIGN); break; case 0x0b: /* V9 ldx */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TEUQ); + dc->mem_idx, MO_TEUQ | MO_ALIGN); break; case 0x18: /* V9 ldswa */ gen_ld_asi(dc, cpu_val, cpu_addr, insn, MO_TESL); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) gen_address_mask(dc, cpu_addr); cpu_dst_32 = gen_dest_fpr_F(dc); tcg_gen_qemu_ld_i32(cpu_dst_32, cpu_addr, - dc->mem_idx, MO_TEUL); + dc->mem_idx, MO_TEUL | MO_ALIGN); gen_store_fpr_F(dc, rd, cpu_dst_32); break; case 0x21: /* ldfsr, V9 ldxfsr */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) if (rd == 1) { TCGv_i64 t64 = tcg_temp_new_i64(); tcg_gen_qemu_ld_i64(t64, cpu_addr, - dc->mem_idx, MO_TEUQ); + dc->mem_idx, MO_TEUQ | MO_ALIGN); gen_helper_ldxfsr(cpu_fsr, cpu_env, cpu_fsr, t64); break; } #endif cpu_dst_32 = tcg_temp_new_i32(); tcg_gen_qemu_ld_i32(cpu_dst_32, cpu_addr, - dc->mem_idx, MO_TEUL); + dc->mem_idx, MO_TEUL | MO_ALIGN); gen_helper_ldfsr(cpu_fsr, cpu_env, cpu_fsr, cpu_dst_32); break; case 0x22: /* ldqf, load quad fpreg */ @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0x4: /* st, store word */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_st_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TEUL); + dc->mem_idx, MO_TEUL | MO_ALIGN); break; case 0x5: /* stb, store byte */ gen_address_mask(dc, cpu_addr); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0x6: /* sth, store halfword */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_st_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TEUW); + dc->mem_idx, MO_TEUW | MO_ALIGN); break; case 0x7: /* std, store double word */ if (rd & 1) @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) t64 = tcg_temp_new_i64(); tcg_gen_concat_tl_i64(t64, lo, cpu_val); tcg_gen_qemu_st_i64(t64, cpu_addr, - dc->mem_idx, MO_TEUQ); + dc->mem_idx, MO_TEUQ | MO_ALIGN); } break; #if !defined(CONFIG_USER_ONLY) || defined(TARGET_SPARC64) @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) case 0x0e: /* V9 stx */ gen_address_mask(dc, cpu_addr); tcg_gen_qemu_st_tl(cpu_val, cpu_addr, - dc->mem_idx, MO_TEUQ); + dc->mem_idx, MO_TEUQ | MO_ALIGN); break; case 0x1e: /* V9 stxa */ gen_st_asi(dc, cpu_val, cpu_addr, insn, MO_TEUQ); @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) gen_address_mask(dc, cpu_addr); cpu_src1_32 = gen_load_fpr_F(dc, rd); tcg_gen_qemu_st_i32(cpu_src1_32, cpu_addr, - dc->mem_idx, MO_TEUL); + dc->mem_idx, MO_TEUL | MO_ALIGN); break; case 0x25: /* stfsr, V9 stxfsr */ { @@ -XXX,XX +XXX,XX @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn) gen_address_mask(dc, cpu_addr); if (rd == 1) { tcg_gen_qemu_st_tl(cpu_fsr, cpu_addr, - dc->mem_idx, MO_TEUQ); + dc->mem_idx, MO_TEUQ | MO_ALIGN); break; } #endif tcg_gen_qemu_st_tl(cpu_fsr, cpu_addr, - dc->mem_idx, MO_TEUL); + dc->mem_idx, MO_TEUL | MO_ALIGN); } break; case 0x26: -- 2.34.1 This passes on the memop as given as argument to helper_ld_asi to the ultimate load primitive. Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sparc/ldst_helper.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/target/sparc/ldst_helper.c b/target/sparc/ldst_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/ldst_helper.c +++ b/target/sparc/ldst_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t helper_ld_asi(CPUSPARCState *env, target_ulong addr, #if defined(DEBUG_MXCC) || defined(DEBUG_ASI) uint32_t last_addr = addr; #endif + MemOpIdx oi; do_check_align(env, addr, size - 1, GETPC()); switch (asi) { @@ -XXX,XX +XXX,XX @@ uint64_t helper_ld_asi(CPUSPARCState *env, target_ulong addr, case ASI_M_IODIAG: /* Turbosparc IOTLB Diagnostic */ break; case ASI_KERNELTXT: /* Supervisor code access */ + oi = make_memop_idx(memop, cpu_mmu_index(env, true)); switch (size) { case 1: - ret = cpu_ldub_code(env, addr); + ret = cpu_ldb_code_mmu(env, addr, oi, GETPC()); break; case 2: - ret = cpu_lduw_code(env, addr); + ret = cpu_ldw_code_mmu(env, addr, oi, GETPC()); break; default: case 4: - ret = cpu_ldl_code(env, addr); + ret = cpu_ldl_code_mmu(env, addr, oi, GETPC()); break; case 8: - ret = cpu_ldq_code(env, addr); + ret = cpu_ldq_code_mmu(env, addr, oi, GETPC()); break; } break; -- 2.34.1 Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configs/targets/sparc-linux-user.mak | 1 - configs/targets/sparc-softmmu.mak | 1 - configs/targets/sparc32plus-linux-user.mak | 1 - configs/targets/sparc64-linux-user.mak | 1 - configs/targets/sparc64-softmmu.mak | 1 - 5 files changed, 5 deletions(-) diff --git a/configs/targets/sparc-linux-user.mak b/configs/targets/sparc-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/sparc-linux-user.mak +++ b/configs/targets/sparc-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=sparc TARGET_SYSTBL_ABI=common,32 TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y diff --git a/configs/targets/sparc-softmmu.mak b/configs/targets/sparc-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/sparc-softmmu.mak +++ b/configs/targets/sparc-softmmu.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=sparc -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y diff --git a/configs/targets/sparc32plus-linux-user.mak b/configs/targets/sparc32plus-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/sparc32plus-linux-user.mak +++ b/configs/targets/sparc32plus-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_BASE_ARCH=sparc TARGET_ABI_DIR=sparc TARGET_SYSTBL_ABI=common,32 TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y diff --git a/configs/targets/sparc64-linux-user.mak b/configs/targets/sparc64-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/sparc64-linux-user.mak +++ b/configs/targets/sparc64-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_BASE_ARCH=sparc TARGET_ABI_DIR=sparc TARGET_SYSTBL_ABI=common,64 TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y diff --git a/configs/targets/sparc64-softmmu.mak b/configs/targets/sparc64-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/sparc64-softmmu.mak +++ b/configs/targets/sparc64-softmmu.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=sparc64 TARGET_BASE_ARCH=sparc -TARGET_ALIGNED_ONLY=y TARGET_BIG_ENDIAN=y -- 2.34.1 Interpret the variable argument placement in the caller. Pass data_type instead of is64 -- there are several places where we already convert back from bool to type. Clean things up by using type throughout. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/i386/tcg-target.c.inc | 111 +++++++++++++++++--------------------- 1 file changed, 50 insertions(+), 61 deletions(-) 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 void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, * Record the context of a call to the out of line helper code for the slow path * for a load or store, so that we can later generate the correct helper code */ -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, - MemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, + TCGType type, MemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, tcg_insn_unit *raddr, @@ -XXX,XX +XXX,XX @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, label->is_ld = is_ld; label->oi = oi; - label->type = is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32; + label->type = type; label->datalo_reg = datalo; label->datahi_reg = datahi; label->addrlo_reg = addrlo; @@ -XXX,XX +XXX,XX @@ static inline int setup_guest_base_seg(void) static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, TCGReg base, int index, intptr_t ofs, - int seg, bool is64, MemOp memop) + int seg, TCGType type, MemOp memop) { - TCGType type = is64 ? TCG_TYPE_I64 : TCG_TYPE_I32; bool use_movbe = false; - int rexw = is64 * P_REXW; + int rexw = (type == TCG_TYPE_I32 ? 0 : P_REXW); int movop = OPC_MOVL_GvEv; /* Do big-endian loads with movbe. */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, } } -/* XXX: qemu_ld and qemu_st could be modified to clobber only EDX and - EAX. It will be useful once fixed registers globals are less - common. */ -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) +static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg datalo, datahi, addrlo; - TCGReg addrhi __attribute__((unused)); - MemOpIdx oi; - MemOp opc; + MemOp opc = get_memop(oi); + #if defined(CONFIG_SOFTMMU) - int mem_index; tcg_insn_unit *label_ptr[2]; -#else - unsigned a_bits; -#endif - datalo = *args++; - datahi = (TCG_TARGET_REG_BITS == 32 && is64 ? *args++ : 0); - addrlo = *args++; - addrhi = (TARGET_LONG_BITS > TCG_TARGET_REG_BITS ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); - -#if defined(CONFIG_SOFTMMU) - mem_index = get_mmuidx(oi); - - tcg_out_tlb_load(s, addrlo, addrhi, mem_index, opc, + tcg_out_tlb_load(s, addrlo, addrhi, get_mmuidx(oi), opc, label_ptr, offsetof(CPUTLBEntry, addr_read)); /* TLB Hit. */ - tcg_out_qemu_ld_direct(s, datalo, datahi, TCG_REG_L1, -1, 0, 0, is64, opc); + tcg_out_qemu_ld_direct(s, datalo, datahi, TCG_REG_L1, + -1, 0, 0, data_type, opc); /* Record the current context of a load into ldst label */ - add_qemu_ldst_label(s, true, is64, oi, datalo, datahi, addrlo, addrhi, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, true, data_type, oi, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #else - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } tcg_out_qemu_ld_direct(s, datalo, datahi, addrlo, x86_guest_base_index, x86_guest_base_offset, x86_guest_base_seg, - is64, opc); + data_type, opc); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, } } -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) +static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg datalo, datahi, addrlo; - TCGReg addrhi __attribute__((unused)); - MemOpIdx oi; - MemOp opc; + MemOp opc = get_memop(oi); + #if defined(CONFIG_SOFTMMU) - int mem_index; tcg_insn_unit *label_ptr[2]; -#else - unsigned a_bits; -#endif - datalo = *args++; - datahi = (TCG_TARGET_REG_BITS == 32 && is64 ? *args++ : 0); - addrlo = *args++; - addrhi = (TARGET_LONG_BITS > TCG_TARGET_REG_BITS ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); - -#if defined(CONFIG_SOFTMMU) - mem_index = get_mmuidx(oi); - - tcg_out_tlb_load(s, addrlo, addrhi, mem_index, opc, + tcg_out_tlb_load(s, addrlo, addrhi, get_mmuidx(oi), opc, label_ptr, offsetof(CPUTLBEntry, addr_write)); /* TLB Hit. */ tcg_out_qemu_st_direct(s, datalo, datahi, TCG_REG_L1, -1, 0, 0, opc); /* Record the current context of a store into ldst label */ - add_qemu_ldst_label(s, false, is64, oi, datalo, datahi, addrlo, addrhi, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, false, data_type, oi, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #else - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addrlo, addrhi, a_bits); } @@ -XXX,XX +XXX,XX @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, args, 0); + if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + tcg_out_qemu_ld(s, a0, -1, a1, -1, a2, TCG_TYPE_I32); + } else { + tcg_out_qemu_ld(s, a0, -1, a1, a2, args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args, 1); + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_qemu_ld(s, a0, -1, a1, -1, a2, TCG_TYPE_I64); + } else if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_ld(s, a0, a1, a2, -1, args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_ld(s, a0, a1, a2, args[3], args[4], TCG_TYPE_I64); + } break; case INDEX_op_qemu_st_i32: case INDEX_op_qemu_st8_i32: - tcg_out_qemu_st(s, args, 0); + if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + tcg_out_qemu_st(s, a0, -1, a1, -1, a2, TCG_TYPE_I32); + } else { + tcg_out_qemu_st(s, a0, -1, a1, a2, args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args, 1); + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_qemu_st(s, a0, -1, a1, -1, a2, TCG_TYPE_I64); + } else if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_st(s, a0, a1, a2, -1, args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_st(s, a0, a1, a2, args[3], args[4], TCG_TYPE_I64); + } break; OP_32_64(mulu2): -- 2.34.1 Test for both base and index; use datahi as a temporary, overwritten by the final load. Always perform the loads in ascending order, so that any (user-only) fault sees the correct address. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/i386/tcg-target.c.inc | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) 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 void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, if (TCG_TARGET_REG_BITS == 64) { tcg_out_modrm_sib_offset(s, movop + P_REXW + seg, datalo, base, index, 0, ofs); + break; + } + if (use_movbe) { + TCGReg t = datalo; + datalo = datahi; + datahi = t; + } + if (base == datalo || index == datalo) { + tcg_out_modrm_sib_offset(s, OPC_LEA, datahi, base, index, 0, ofs); + tcg_out_modrm_offset(s, movop + seg, datalo, datahi, 0); + tcg_out_modrm_offset(s, movop + seg, datahi, datahi, 4); } else { - if (use_movbe) { - TCGReg t = datalo; - datalo = datahi; - datahi = t; - } - if (base != datalo) { - tcg_out_modrm_sib_offset(s, movop + seg, datalo, - base, index, 0, ofs); - tcg_out_modrm_sib_offset(s, movop + seg, datahi, - base, index, 0, ofs + 4); - } else { - tcg_out_modrm_sib_offset(s, movop + seg, datahi, - base, index, 0, ofs + 4); - tcg_out_modrm_sib_offset(s, movop + seg, datalo, - base, index, 0, ofs); - } + tcg_out_modrm_sib_offset(s, movop + seg, datalo, + base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, movop + seg, datahi, + base, index, 0, ofs + 4); } break; default: -- 2.34.1 Collect the 4 potential parts of the host address into a struct. Reorg tcg_out_qemu_{ld,st}_direct to use it. Reorg guest_base handling to use it. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/i386/tcg-target.c.inc | 165 +++++++++++++++++++++----------------- 1 file changed, 90 insertions(+), 75 deletions(-) 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 void tcg_out_nopn(TCGContext *s, int n) tcg_out8(s, 0x90); } +typedef struct { + TCGReg base; + int index; + int ofs; + int seg; +} HostAddress; + #if defined(CONFIG_SOFTMMU) /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) return tcg_out_fail_alignment(s, l); } -#if TCG_TARGET_REG_BITS == 32 -# define x86_guest_base_seg 0 -# define x86_guest_base_index -1 -# define x86_guest_base_offset guest_base -#else -static int x86_guest_base_seg; -static int x86_guest_base_index = -1; -static int32_t x86_guest_base_offset; -# if defined(__x86_64__) && defined(__linux__) -# include <asm/prctl.h> -# include <sys/prctl.h> +static HostAddress x86_guest_base = { + .index = -1 +}; + +#if defined(__x86_64__) && defined(__linux__) +# include <asm/prctl.h> +# include <sys/prctl.h> int arch_prctl(int code, unsigned long addr); static inline int setup_guest_base_seg(void) { @@ -XXX,XX +XXX,XX @@ static inline int setup_guest_base_seg(void) } return 0; } -# elif defined (__FreeBSD__) || defined (__FreeBSD_kernel__) -# include <machine/sysarch.h> +#elif defined(__x86_64__) && \ + (defined (__FreeBSD__) || defined (__FreeBSD_kernel__)) +# include <machine/sysarch.h> static inline int setup_guest_base_seg(void) { if (sysarch(AMD64_SET_GSBASE, &guest_base) == 0) { @@ -XXX,XX +XXX,XX @@ static inline int setup_guest_base_seg(void) } return 0; } -# else +#else static inline int setup_guest_base_seg(void) { return 0; } -# endif -#endif +#endif /* setup_guest_base_seg */ #endif /* SOFTMMU */ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, - TCGReg base, int index, intptr_t ofs, - int seg, TCGType type, MemOp memop) + HostAddress h, TCGType type, MemOp memop) { bool use_movbe = false; int rexw = (type == TCG_TYPE_I32 ? 0 : P_REXW); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, switch (memop & MO_SSIZE) { case MO_UB: - tcg_out_modrm_sib_offset(s, OPC_MOVZBL + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVZBL + h.seg, datalo, + h.base, h.index, 0, h.ofs); break; case MO_SB: - tcg_out_modrm_sib_offset(s, OPC_MOVSBL + rexw + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVSBL + rexw + h.seg, datalo, + h.base, h.index, 0, h.ofs); break; case MO_UW: if (use_movbe) { /* There is no extending movbe; only low 16-bits are modified. */ - if (datalo != base && datalo != index) { + if (datalo != h.base && datalo != h.index) { /* XOR breaks dependency chains. */ tgen_arithr(s, ARITH_XOR, datalo, datalo); - tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + seg, - datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + h.seg, + datalo, h.base, h.index, 0, h.ofs); } else { - tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + seg, - datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + h.seg, + datalo, h.base, h.index, 0, h.ofs); tcg_out_ext16u(s, datalo, datalo); } } else { - tcg_out_modrm_sib_offset(s, OPC_MOVZWL + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVZWL + h.seg, datalo, + h.base, h.index, 0, h.ofs); } break; case MO_SW: if (use_movbe) { - tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + seg, - datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + h.seg, + datalo, h.base, h.index, 0, h.ofs); tcg_out_ext16s(s, type, datalo, datalo); } else { - tcg_out_modrm_sib_offset(s, OPC_MOVSWL + rexw + seg, - datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVSWL + rexw + h.seg, + datalo, h.base, h.index, 0, h.ofs); } break; case MO_UL: - tcg_out_modrm_sib_offset(s, movop + seg, datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, movop + h.seg, datalo, + h.base, h.index, 0, h.ofs); break; #if TCG_TARGET_REG_BITS == 64 case MO_SL: if (use_movbe) { - tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + h.seg, datalo, + h.base, h.index, 0, h.ofs); tcg_out_ext32s(s, datalo, datalo); } else { - tcg_out_modrm_sib_offset(s, OPC_MOVSLQ + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVSLQ + h.seg, datalo, + h.base, h.index, 0, h.ofs); } break; #endif case MO_UQ: if (TCG_TARGET_REG_BITS == 64) { - tcg_out_modrm_sib_offset(s, movop + P_REXW + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, movop + P_REXW + h.seg, datalo, + h.base, h.index, 0, h.ofs); break; } if (use_movbe) { @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, datalo = datahi; datahi = t; } - if (base == datalo || index == datalo) { - tcg_out_modrm_sib_offset(s, OPC_LEA, datahi, base, index, 0, ofs); - tcg_out_modrm_offset(s, movop + seg, datalo, datahi, 0); - tcg_out_modrm_offset(s, movop + seg, datahi, datahi, 4); + if (h.base == datalo || h.index == datalo) { + tcg_out_modrm_sib_offset(s, OPC_LEA, datahi, + h.base, h.index, 0, h.ofs); + tcg_out_modrm_offset(s, movop + h.seg, datalo, datahi, 0); + tcg_out_modrm_offset(s, movop + h.seg, datahi, datahi, 4); } else { - tcg_out_modrm_sib_offset(s, movop + seg, datalo, - base, index, 0, ofs); - tcg_out_modrm_sib_offset(s, movop + seg, datahi, - base, index, 0, ofs + 4); + tcg_out_modrm_sib_offset(s, movop + h.seg, datalo, + h.base, h.index, 0, h.ofs); + tcg_out_modrm_sib_offset(s, movop + h.seg, datahi, + h.base, h.index, 0, h.ofs + 4); } break; default: @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); + HostAddress h; #if defined(CONFIG_SOFTMMU) tcg_insn_unit *label_ptr[2]; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, label_ptr, offsetof(CPUTLBEntry, addr_read)); /* TLB Hit. */ - tcg_out_qemu_ld_direct(s, datalo, datahi, TCG_REG_L1, - -1, 0, 0, data_type, opc); + h.base = TCG_REG_L1; + h.index = -1; + h.ofs = 0; + h.seg = 0; + tcg_out_qemu_ld_direct(s, datalo, datahi, h, data_type, opc); /* Record the current context of a load into ldst label */ add_qemu_ldst_label(s, true, data_type, oi, datalo, datahi, @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } - tcg_out_qemu_ld_direct(s, datalo, datahi, addrlo, x86_guest_base_index, - x86_guest_base_offset, x86_guest_base_seg, - data_type, opc); + h = x86_guest_base; + h.base = addrlo; + tcg_out_qemu_ld_direct(s, datalo, datahi, h, data_type, opc); #endif } static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, - TCGReg base, int index, intptr_t ofs, - int seg, MemOp memop) + HostAddress h, MemOp memop) { bool use_movbe = false; int movop = OPC_MOVL_EvGv; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi, case MO_8: /* This is handled with constraints on INDEX_op_qemu_st8_i32. */ tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || datalo < 4); - tcg_out_modrm_sib_offset(s, OPC_MOVB_EvGv + P_REXB_R + seg, - datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, OPC_MOVB_EvGv + P_REXB_R + h.seg, + datalo, h.base, h.index, 0, h.ofs); break; case MO_16: - tcg_out_modrm_sib_offset(s, movop + P_DATA16 + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, movop + P_DATA16 + h.seg, datalo, + h.base, h.index, 0, h.ofs); break; case MO_32: - tcg_out_modrm_sib_offset(s, movop + seg, datalo, base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, movop + h.seg, datalo, + h.base, h.index, 0, h.ofs); break; case MO_64: if (TCG_TARGET_REG_BITS == 64) { - tcg_out_modrm_sib_offset(s, movop + P_REXW + seg, datalo, - base, index, 0, ofs); + tcg_out_modrm_sib_offset(s, movop + P_REXW + h.seg, datalo, + h.base, h.index, 0, h.ofs); } else { if (use_movbe) { TCGReg t = datalo; datalo = datahi; datahi = t; } - tcg_out_modrm_sib_offset(s, movop + seg, datalo, - base, index, 0, ofs); - tcg_out_modrm_sib_offset(s, movop + seg, datahi, - base, index, 0, ofs + 4); + tcg_out_modrm_sib_offset(s, movop + h.seg, datalo, + h.base, h.index, 0, h.ofs); + tcg_out_modrm_sib_offset(s, movop + h.seg, datahi, + h.base, h.index, 0, h.ofs + 4); } break; default: @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); + HostAddress h; #if defined(CONFIG_SOFTMMU) tcg_insn_unit *label_ptr[2]; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, label_ptr, offsetof(CPUTLBEntry, addr_write)); /* TLB Hit. */ - tcg_out_qemu_st_direct(s, datalo, datahi, TCG_REG_L1, -1, 0, 0, opc); + h.base = TCG_REG_L1; + h.index = -1; + h.ofs = 0; + h.seg = 0; + tcg_out_qemu_st_direct(s, datalo, datahi, h, opc); /* Record the current context of a store into ldst label */ add_qemu_ldst_label(s, false, data_type, oi, datalo, datahi, @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, tcg_out_test_alignment(s, false, addrlo, addrhi, a_bits); } - tcg_out_qemu_st_direct(s, datalo, datahi, addrlo, x86_guest_base_index, - x86_guest_base_offset, x86_guest_base_seg, opc); + h = x86_guest_base; + h.base = addrlo; + + tcg_out_qemu_st_direct(s, datalo, datahi, h, opc); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_target_qemu_prologue(TCGContext *s) (ARRAY_SIZE(tcg_target_callee_save_regs) + 2) * 4 + stack_addend); #else -# if !defined(CONFIG_SOFTMMU) && TCG_TARGET_REG_BITS == 64 +# if !defined(CONFIG_SOFTMMU) if (guest_base) { int seg = setup_guest_base_seg(); if (seg != 0) { - x86_guest_base_seg = seg; + x86_guest_base.seg = seg; } else if (guest_base == (int32_t)guest_base) { - x86_guest_base_offset = guest_base; + x86_guest_base.ofs = guest_base; } else { /* Choose R12 because, as a base, it requires a SIB byte. */ - x86_guest_base_index = TCG_REG_R12; - tcg_out_movi(s, TCG_TYPE_PTR, x86_guest_base_index, guest_base); - tcg_regset_set_reg(s->reserved_regs, x86_guest_base_index); + x86_guest_base.index = TCG_REG_R12; + tcg_out_movi(s, TCG_TYPE_PTR, x86_guest_base.index, guest_base); + tcg_regset_set_reg(s->reserved_regs, x86_guest_base.index); } } # endif -- 2.34.1 Use TCG_REG_L[01] constants directly. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/i386/tcg-target.c.inc | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) 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 void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, int mem_index, MemOp opc, tcg_insn_unit **label_ptr, int which) { - const TCGReg r0 = TCG_REG_L0; - const TCGReg r1 = TCG_REG_L1; TCGType ttype = TCG_TYPE_I32; TCGType tlbtype = TCG_TYPE_I32; int trexw = 0, hrexw = 0, tlbrexw = 0; @@ -XXX,XX +XXX,XX @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, } } - tcg_out_mov(s, tlbtype, r0, addrlo); - tcg_out_shifti(s, SHIFT_SHR + tlbrexw, r0, + tcg_out_mov(s, tlbtype, TCG_REG_L0, addrlo); + tcg_out_shifti(s, SHIFT_SHR + tlbrexw, TCG_REG_L0, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); - tcg_out_modrm_offset(s, OPC_AND_GvEv + trexw, r0, TCG_AREG0, + tcg_out_modrm_offset(s, OPC_AND_GvEv + trexw, TCG_REG_L0, TCG_AREG0, TLB_MASK_TABLE_OFS(mem_index) + offsetof(CPUTLBDescFast, mask)); - tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, r0, TCG_AREG0, + tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, TCG_REG_L0, TCG_AREG0, TLB_MASK_TABLE_OFS(mem_index) + offsetof(CPUTLBDescFast, table)); @@ -XXX,XX +XXX,XX @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, copy the address and mask. For lesser alignments, check that we don't cross pages for the complete access. */ if (a_bits >= s_bits) { - tcg_out_mov(s, ttype, r1, addrlo); + tcg_out_mov(s, ttype, TCG_REG_L1, addrlo); } else { - tcg_out_modrm_offset(s, OPC_LEA + trexw, r1, addrlo, s_mask - a_mask); + tcg_out_modrm_offset(s, OPC_LEA + trexw, TCG_REG_L1, + addrlo, s_mask - a_mask); } tlb_mask = (target_ulong)TARGET_PAGE_MASK | a_mask; - tgen_arithi(s, ARITH_AND + trexw, r1, tlb_mask, 0); + tgen_arithi(s, ARITH_AND + trexw, TCG_REG_L1, tlb_mask, 0); - /* cmp 0(r0), r1 */ - tcg_out_modrm_offset(s, OPC_CMP_GvEv + trexw, r1, r0, which); + /* cmp 0(TCG_REG_L0), TCG_REG_L1 */ + tcg_out_modrm_offset(s, OPC_CMP_GvEv + trexw, + TCG_REG_L1, TCG_REG_L0, which); /* Prepare for both the fast path add of the tlb addend, and the slow path function argument setup. */ - tcg_out_mov(s, ttype, r1, addrlo); + tcg_out_mov(s, ttype, TCG_REG_L1, addrlo); /* jne slow_path */ tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0); @@ -XXX,XX +XXX,XX @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, s->code_ptr += 4; if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - /* cmp 4(r0), addrhi */ - tcg_out_modrm_offset(s, OPC_CMP_GvEv, addrhi, r0, which + 4); + /* cmp 4(TCG_REG_L0), addrhi */ + tcg_out_modrm_offset(s, OPC_CMP_GvEv, addrhi, TCG_REG_L0, which + 4); /* jne slow_path */ tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0); @@ -XXX,XX +XXX,XX @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, /* TLB Hit. */ - /* add addend(r0), r1 */ - tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, r1, r0, + /* add addend(TCG_REG_L0), TCG_REG_L1 */ + tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, TCG_REG_L1, TCG_REG_L0, offsetof(CPUTLBEntry, addend)); } -- 2.34.1 Split out a helper for choosing testb vs testl. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/i386/tcg-target.c.inc | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) 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 void tcg_out_nopn(TCGContext *s, int n) tcg_out8(s, 0x90); } +/* Test register R vs immediate bits I, setting Z flag for EQ/NE. */ +static void __attribute__((unused)) +tcg_out_testi(TCGContext *s, TCGReg r, uint32_t i) +{ + /* + * This is used for testing alignment, so we can usually use testb. + * For i686, we have to use testl for %esi/%edi. + */ + if (i <= 0xff && (TCG_TARGET_REG_BITS == 64 || r < 4)) { + tcg_out_modrm(s, OPC_GRP3_Eb | P_REXB_RM, EXT3_TESTi, r); + tcg_out8(s, i); + } else { + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_TESTi, r); + tcg_out32(s, i); + } +} + typedef struct { TCGReg base; int index; @@ -XXX,XX +XXX,XX @@ static void tcg_out_test_alignment(TCGContext *s, bool is_ld, TCGReg addrlo, unsigned a_mask = (1 << a_bits) - 1; TCGLabelQemuLdst *label; - /* - * We are expecting a_bits to max out at 7, so we can usually use testb. - * For i686, we have to use testl for %esi/%edi. - */ - if (a_mask <= 0xff && (TCG_TARGET_REG_BITS == 64 || addrlo < 4)) { - tcg_out_modrm(s, OPC_GRP3_Eb | P_REXB_RM, EXT3_TESTi, addrlo); - tcg_out8(s, a_mask); - } else { - tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_TESTi, addrlo); - tcg_out32(s, a_mask); - } - + tcg_out_testi(s, addrlo, a_mask); /* jne slow_path */ tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0); -- 2.34.1 Rename the 'ext' parameter 'data_type' to make the use clearer; pass it to tcg_out_qemu_st as well to even out the interfaces. Rename the 'otype' local 'addr_type' to make the use clearer. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/aarch64/tcg-target.c.inc | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-) 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 void tcg_out_qemu_st_direct(TCGContext *s, MemOp memop, } static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, - MemOpIdx oi, TCGType ext) + MemOpIdx oi, TCGType data_type) { MemOp memop = get_memop(oi); - const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; + TCGType addr_type = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((memop & MO_BSWAP) == 0); #ifdef CONFIG_SOFTMMU - unsigned mem_index = get_mmuidx(oi); tcg_insn_unit *label_ptr; - tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, mem_index, 1); - tcg_out_qemu_ld_direct(s, memop, ext, data_reg, - TCG_REG_X1, otype, addr_reg); - add_qemu_ldst_label(s, true, oi, ext, data_reg, addr_reg, + tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, get_mmuidx(oi), 1); + tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, + TCG_REG_X1, addr_type, addr_reg); + add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, s->code_ptr, label_ptr); #else /* !CONFIG_SOFTMMU */ unsigned a_bits = get_alignment_bits(memop); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, tcg_out_test_alignment(s, true, addr_reg, a_bits); } if (USE_GUEST_BASE) { - tcg_out_qemu_ld_direct(s, memop, ext, data_reg, - TCG_REG_GUEST_BASE, otype, addr_reg); + tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, + TCG_REG_GUEST_BASE, addr_type, addr_reg); } else { - tcg_out_qemu_ld_direct(s, memop, ext, data_reg, + tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, addr_reg, TCG_TYPE_I64, TCG_REG_XZR); } #endif /* CONFIG_SOFTMMU */ } static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, - MemOpIdx oi) + MemOpIdx oi, TCGType data_type) { MemOp memop = get_memop(oi); - const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; + TCGType addr_type = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((memop & MO_BSWAP) == 0); #ifdef CONFIG_SOFTMMU - unsigned mem_index = get_mmuidx(oi); tcg_insn_unit *label_ptr; - tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, mem_index, 0); + tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, get_mmuidx(oi), 0); tcg_out_qemu_st_direct(s, memop, data_reg, - TCG_REG_X1, otype, addr_reg); - add_qemu_ldst_label(s, false, oi, (memop & MO_SIZE)== MO_64, - data_reg, addr_reg, s->code_ptr, label_ptr); + TCG_REG_X1, addr_type, addr_reg); + add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #else /* !CONFIG_SOFTMMU */ unsigned a_bits = get_alignment_bits(memop); if (a_bits) { @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, } if (USE_GUEST_BASE) { tcg_out_qemu_st_direct(s, memop, data_reg, - TCG_REG_GUEST_BASE, otype, addr_reg); + TCG_REG_GUEST_BASE, addr_type, addr_reg); } else { tcg_out_qemu_st_direct(s, memop, data_reg, addr_reg, TCG_TYPE_I64, TCG_REG_XZR); @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_st_i32: case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, REG0(0), a1, a2); + tcg_out_qemu_st(s, REG0(0), a1, a2, ext); break; case INDEX_op_bswap64_i64: -- 2.34.1 Collect the 3 potential parts of the host address into a struct. Reorg tcg_out_qemu_{ld,st}_direct to use it. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/aarch64/tcg-target.c.inc | 86 +++++++++++++++++++++++++----------- 1 file changed, 59 insertions(+), 27 deletions(-) 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 void tcg_out_adr(TCGContext *s, TCGReg rd, const void *target) tcg_out_insn(s, 3406, ADR, rd, offset); } +typedef struct { + TCGReg base; + TCGReg index; + TCGType index_ext; +} HostAddress; + #ifdef CONFIG_SOFTMMU /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * MemOpIdx oi, uintptr_t ra) @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) #endif /* CONFIG_SOFTMMU */ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp memop, TCGType ext, - TCGReg data_r, TCGReg addr_r, - TCGType otype, TCGReg off_r) + TCGReg data_r, HostAddress h) { switch (memop & MO_SSIZE) { case MO_UB: - tcg_out_ldst_r(s, I3312_LDRB, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_LDRB, data_r, h.base, h.index_ext, h.index); break; case MO_SB: tcg_out_ldst_r(s, ext ? I3312_LDRSBX : I3312_LDRSBW, - data_r, addr_r, otype, off_r); + data_r, h.base, h.index_ext, h.index); break; case MO_UW: - tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_LDRH, data_r, h.base, h.index_ext, h.index); break; case MO_SW: tcg_out_ldst_r(s, (ext ? I3312_LDRSHX : I3312_LDRSHW), - data_r, addr_r, otype, off_r); + data_r, h.base, h.index_ext, h.index); break; case MO_UL: - tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_LDRW, data_r, h.base, h.index_ext, h.index); break; case MO_SL: - tcg_out_ldst_r(s, I3312_LDRSWX, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_LDRSWX, data_r, h.base, h.index_ext, h.index); break; case MO_UQ: - tcg_out_ldst_r(s, I3312_LDRX, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_LDRX, data_r, h.base, h.index_ext, h.index); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp memop, TCGType ext, } static void tcg_out_qemu_st_direct(TCGContext *s, MemOp memop, - TCGReg data_r, TCGReg addr_r, - TCGType otype, TCGReg off_r) + TCGReg data_r, HostAddress h) { switch (memop & MO_SIZE) { case MO_8: - tcg_out_ldst_r(s, I3312_STRB, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_STRB, data_r, h.base, h.index_ext, h.index); break; case MO_16: - tcg_out_ldst_r(s, I3312_STRH, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_STRH, data_r, h.base, h.index_ext, h.index); break; case MO_32: - tcg_out_ldst_r(s, I3312_STRW, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_STRW, data_r, h.base, h.index_ext, h.index); break; case MO_64: - tcg_out_ldst_r(s, I3312_STRX, data_r, addr_r, otype, off_r); + tcg_out_ldst_r(s, I3312_STRX, data_r, h.base, h.index_ext, h.index); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, { MemOp memop = get_memop(oi); TCGType addr_type = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; + HostAddress h; /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((memop & MO_BSWAP) == 0); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, tcg_insn_unit *label_ptr; tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, get_mmuidx(oi), 1); - tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, - TCG_REG_X1, addr_type, addr_reg); + + h = (HostAddress){ + .base = TCG_REG_X1, + .index = addr_reg, + .index_ext = addr_type + }; + tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, h); + add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, s->code_ptr, label_ptr); #else /* !CONFIG_SOFTMMU */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, tcg_out_test_alignment(s, true, addr_reg, a_bits); } if (USE_GUEST_BASE) { - tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, - TCG_REG_GUEST_BASE, addr_type, addr_reg); + h = (HostAddress){ + .base = TCG_REG_GUEST_BASE, + .index = addr_reg, + .index_ext = addr_type + }; } else { - tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, - addr_reg, TCG_TYPE_I64, TCG_REG_XZR); + h = (HostAddress){ + .base = addr_reg, + .index = TCG_REG_XZR, + .index_ext = TCG_TYPE_I64 + }; } + tcg_out_qemu_ld_direct(s, memop, data_type, data_reg, h); #endif /* CONFIG_SOFTMMU */ } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, { MemOp memop = get_memop(oi); TCGType addr_type = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; + HostAddress h; /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((memop & MO_BSWAP) == 0); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, tcg_insn_unit *label_ptr; tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, get_mmuidx(oi), 0); - tcg_out_qemu_st_direct(s, memop, data_reg, - TCG_REG_X1, addr_type, addr_reg); + + h = (HostAddress){ + .base = TCG_REG_X1, + .index = addr_reg, + .index_ext = addr_type + }; + tcg_out_qemu_st_direct(s, memop, data_reg, h); + add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, s->code_ptr, label_ptr); #else /* !CONFIG_SOFTMMU */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, tcg_out_test_alignment(s, false, addr_reg, a_bits); } if (USE_GUEST_BASE) { - tcg_out_qemu_st_direct(s, memop, data_reg, - TCG_REG_GUEST_BASE, addr_type, addr_reg); + h = (HostAddress){ + .base = TCG_REG_GUEST_BASE, + .index = addr_reg, + .index_ext = addr_type + }; } else { - tcg_out_qemu_st_direct(s, memop, data_reg, - addr_reg, TCG_TYPE_I64, TCG_REG_XZR); + h = (HostAddress){ + .base = addr_reg, + .index = TCG_REG_XZR, + .index_ext = TCG_TYPE_I64 + }; } + tcg_out_qemu_st_direct(s, memop, data_reg, h); #endif /* CONFIG_SOFTMMU */ } -- 2.34.1 Interpret the variable argument placement in the caller. Pass data_type instead of is_64. We need to set this in TCGLabelQemuLdst, so plumb this all the way through from tcg_out_op. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/arm/tcg-target.c.inc | 113 +++++++++++++++++++-------------------- 1 file changed, 56 insertions(+), 57 deletions(-) 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 TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, /* Record the context of a call to the out of line helper code for the slow path for a load or store, so that we can later generate the correct helper code. */ -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, - TCGReg datalo, TCGReg datahi, TCGReg addrlo, - TCGReg addrhi, tcg_insn_unit *raddr, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, + MemOpIdx oi, TCGType type, + TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s); label->is_ld = is_ld; label->oi = oi; + label->type = type; label->datalo_reg = datalo; label->datahi_reg = datahi; label->addrlo_reg = addrlo; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg datalo, } #endif -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) +static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg addrlo, datalo, datahi, addrhi __attribute__((unused)); - MemOpIdx oi; - MemOp opc; -#ifdef CONFIG_SOFTMMU - int mem_index; - TCGReg addend; - tcg_insn_unit *label_ptr; -#else - unsigned a_bits; -#endif - - datalo = *args++; - datahi = (is64 ? *args++ : 0); - addrlo = *args++; - addrhi = (TARGET_LONG_BITS == 64 ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); + MemOp opc = get_memop(oi); #ifdef CONFIG_SOFTMMU - mem_index = get_mmuidx(oi); - addend = tcg_out_tlb_read(s, addrlo, addrhi, opc, mem_index, 1); + TCGReg addend= tcg_out_tlb_read(s, addrlo, addrhi, opc, get_mmuidx(oi), 1); - /* This a conditional BL only to load a pointer within this opcode into LR - for the slow path. We will not be using the value for a tail call. */ - label_ptr = s->code_ptr; + /* + * This a conditional BL only to load a pointer within this opcode into + * LR for the slow path. We will not be using the value for a tail call. + */ + tcg_insn_unit *label_ptr = s->code_ptr; tcg_out_bl_imm(s, COND_NE, 0); tcg_out_qemu_ld_index(s, opc, datalo, datahi, addrlo, addend, true); - add_qemu_ldst_label(s, true, oi, datalo, datahi, addrlo, addrhi, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, true, oi, data_type, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #else /* !CONFIG_SOFTMMU */ - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo, } #endif -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) +static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg addrlo, datalo, datahi, addrhi __attribute__((unused)); - MemOpIdx oi; - MemOp opc; -#ifdef CONFIG_SOFTMMU - int mem_index; - TCGReg addend; - tcg_insn_unit *label_ptr; -#else - unsigned a_bits; -#endif - - datalo = *args++; - datahi = (is64 ? *args++ : 0); - addrlo = *args++; - addrhi = (TARGET_LONG_BITS == 64 ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); + MemOp opc = get_memop(oi); #ifdef CONFIG_SOFTMMU - mem_index = get_mmuidx(oi); - addend = tcg_out_tlb_read(s, addrlo, addrhi, opc, mem_index, 0); + TCGReg addend = tcg_out_tlb_read(s, addrlo, addrhi, opc, get_mmuidx(oi), 0); tcg_out_qemu_st_index(s, COND_EQ, opc, datalo, datahi, addrlo, addend, true); /* The conditional call must come last, as we're going to return here. */ - label_ptr = s->code_ptr; + tcg_insn_unit *label_ptr = s->code_ptr; tcg_out_bl_imm(s, COND_NE, 0); - add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, false, oi, data_type, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #else /* !CONFIG_SOFTMMU */ - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addrlo, addrhi, a_bits); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, args, 0); + if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_ld(s, args[0], -1, args[1], -1, + args[2], TCG_TYPE_I32); + } else { + tcg_out_qemu_ld(s, args[0], -1, args[1], args[2], + args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args, 1); + if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_ld(s, args[0], args[1], args[2], -1, + args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_ld(s, args[0], args[1], args[2], args[3], + args[4], TCG_TYPE_I64); + } break; case INDEX_op_qemu_st_i32: - tcg_out_qemu_st(s, args, 0); + if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_st(s, args[0], -1, args[1], -1, + args[2], TCG_TYPE_I32); + } else { + tcg_out_qemu_st(s, args[0], -1, args[1], args[2], + args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args, 1); + if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_st(s, args[0], args[1], args[2], -1, + args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_st(s, args[0], args[1], args[2], args[3], + args[4], TCG_TYPE_I64); + } break; case INDEX_op_bswap16_i32: -- 2.34.1 Collect the parts of the host address, and condition, into a struct. Merge tcg_out_qemu_*_{index,direct} and use it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/arm/tcg-target.c.inc | 248 ++++++++++++++++++--------------------- 1 file changed, 115 insertions(+), 133 deletions(-) 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 void tcg_out_vldst(TCGContext *s, ARMInsn insn, tcg_out32(s, insn | (rn << 16) | encode_vd(rd) | 0xf); } +typedef struct { + ARMCond cond; + TCGReg base; + int index; + bool index_scratch; +} HostAddress; + #ifdef CONFIG_SOFTMMU /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } #endif /* SOFTMMU */ -static void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo, TCGReg addend, - bool scratch_addend) +static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg datalo, + TCGReg datahi, HostAddress h) { + TCGReg base; + /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); switch (opc & MO_SSIZE) { case MO_UB: - tcg_out_ld8_r(s, COND_AL, datalo, addrlo, addend); + if (h.index < 0) { + tcg_out_ld8_12(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_ld8_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_SB: - tcg_out_ld8s_r(s, COND_AL, datalo, addrlo, addend); + if (h.index < 0) { + tcg_out_ld8s_8(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_ld8s_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_UW: - tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend); + if (h.index < 0) { + tcg_out_ld16u_8(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_ld16u_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_SW: - tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend); + if (h.index < 0) { + tcg_out_ld16s_8(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_ld16s_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_UL: - tcg_out_ld32_r(s, COND_AL, datalo, addrlo, addend); + if (h.index < 0) { + tcg_out_ld32_12(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_ld32_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_UQ: /* We used pair allocation for datalo, so already should be aligned. */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc, tcg_debug_assert(datahi == datalo + 1); /* LDRD requires alignment; double-check that. */ if (get_alignment_bits(opc) >= MO_64) { + if (h.index < 0) { + tcg_out_ldrd_8(s, h.cond, datalo, h.base, 0); + break; + } /* * Rm (the second address op) must not overlap Rt or Rt + 1. * Since datalo is aligned, we can simplify the test via alignment. * Flip the two address arguments if that works. */ - if ((addend & ~1) != datalo) { - tcg_out_ldrd_r(s, COND_AL, datalo, addrlo, addend); + if ((h.index & ~1) != datalo) { + tcg_out_ldrd_r(s, h.cond, datalo, h.base, h.index); break; } - if ((addrlo & ~1) != datalo) { - tcg_out_ldrd_r(s, COND_AL, datalo, addend, addrlo); + if ((h.base & ~1) != datalo) { + tcg_out_ldrd_r(s, h.cond, datalo, h.index, h.base); break; } } - if (scratch_addend) { - tcg_out_ld32_rwb(s, COND_AL, datalo, addend, addrlo); - tcg_out_ld32_12(s, COND_AL, datahi, addend, 4); + if (h.index < 0) { + base = h.base; + if (datalo == h.base) { + tcg_out_mov_reg(s, h.cond, TCG_REG_TMP, base); + base = TCG_REG_TMP; + } + } else if (h.index_scratch) { + tcg_out_ld32_rwb(s, h.cond, datalo, h.index, h.base); + tcg_out_ld32_12(s, h.cond, datahi, h.index, 4); + break; } else { - tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP, - addend, addrlo, SHIFT_IMM_LSL(0)); - tcg_out_ld32_12(s, COND_AL, datalo, TCG_REG_TMP, 0); - tcg_out_ld32_12(s, COND_AL, datahi, TCG_REG_TMP, 4); + tcg_out_dat_reg(s, h.cond, ARITH_ADD, TCG_REG_TMP, + h.base, h.index, SHIFT_IMM_LSL(0)); + base = TCG_REG_TMP; } + tcg_out_ld32_12(s, h.cond, datalo, base, 0); + tcg_out_ld32_12(s, h.cond, datahi, base, 4); break; default: g_assert_not_reached(); } } -#ifndef CONFIG_SOFTMMU -static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg datalo, - TCGReg datahi, TCGReg addrlo) -{ - /* Byte swapping is left to middle-end expansion. */ - tcg_debug_assert((opc & MO_BSWAP) == 0); - - switch (opc & MO_SSIZE) { - case MO_UB: - tcg_out_ld8_12(s, COND_AL, datalo, addrlo, 0); - break; - case MO_SB: - tcg_out_ld8s_8(s, COND_AL, datalo, addrlo, 0); - break; - case MO_UW: - tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0); - break; - case MO_SW: - tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0); - break; - case MO_UL: - tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0); - break; - case MO_UQ: - /* We used pair allocation for datalo, so already should be aligned. */ - tcg_debug_assert((datalo & 1) == 0); - tcg_debug_assert(datahi == datalo + 1); - /* LDRD requires alignment; double-check that. */ - if (get_alignment_bits(opc) >= MO_64) { - tcg_out_ldrd_8(s, COND_AL, datalo, addrlo, 0); - } else if (datalo == addrlo) { - tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4); - tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0); - } else { - tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0); - tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4); - } - break; - default: - g_assert_not_reached(); - } -} -#endif - static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); + HostAddress h; #ifdef CONFIG_SOFTMMU - TCGReg addend= tcg_out_tlb_read(s, addrlo, addrhi, opc, get_mmuidx(oi), 1); + h.cond = COND_AL; + h.base = addrlo; + h.index_scratch = true; + h.index = tcg_out_tlb_read(s, addrlo, addrhi, opc, get_mmuidx(oi), 1); /* * This a conditional BL only to load a pointer within this opcode into @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, tcg_insn_unit *label_ptr = s->code_ptr; tcg_out_bl_imm(s, COND_NE, 0); - tcg_out_qemu_ld_index(s, opc, datalo, datahi, addrlo, addend, true); + tcg_out_qemu_ld_direct(s, opc, datalo, datahi, h); add_qemu_ldst_label(s, true, oi, data_type, datalo, datahi, addrlo, addrhi, s->code_ptr, label_ptr); -#else /* !CONFIG_SOFTMMU */ +#else unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } - if (guest_base) { - tcg_out_qemu_ld_index(s, opc, datalo, datahi, - addrlo, TCG_REG_GUEST_BASE, false); - } else { - tcg_out_qemu_ld_direct(s, opc, datalo, datahi, addrlo); - } + + h.cond = COND_AL; + h.base = addrlo; + h.index = guest_base ? TCG_REG_GUEST_BASE : -1; + h.index_scratch = false; + tcg_out_qemu_ld_direct(s, opc, datalo, datahi, h); #endif } -static void tcg_out_qemu_st_index(TCGContext *s, ARMCond cond, MemOp opc, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo, TCGReg addend, - bool scratch_addend) -{ - /* Byte swapping is left to middle-end expansion. */ - tcg_debug_assert((opc & MO_BSWAP) == 0); - - switch (opc & MO_SIZE) { - case MO_8: - tcg_out_st8_r(s, cond, datalo, addrlo, addend); - break; - case MO_16: - tcg_out_st16_r(s, cond, datalo, addrlo, addend); - break; - case MO_32: - tcg_out_st32_r(s, cond, datalo, addrlo, addend); - break; - case MO_64: - /* We used pair allocation for datalo, so already should be aligned. */ - tcg_debug_assert((datalo & 1) == 0); - tcg_debug_assert(datahi == datalo + 1); - /* STRD requires alignment; double-check that. */ - if (get_alignment_bits(opc) >= MO_64) { - tcg_out_strd_r(s, cond, datalo, addrlo, addend); - } else if (scratch_addend) { - tcg_out_st32_rwb(s, cond, datalo, addend, addrlo); - tcg_out_st32_12(s, cond, datahi, addend, 4); - } else { - tcg_out_dat_reg(s, cond, ARITH_ADD, TCG_REG_TMP, - addend, addrlo, SHIFT_IMM_LSL(0)); - tcg_out_st32_12(s, cond, datalo, TCG_REG_TMP, 0); - tcg_out_st32_12(s, cond, datahi, TCG_REG_TMP, 4); - } - break; - default: - g_assert_not_reached(); - } -} - -#ifndef CONFIG_SOFTMMU static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo, - TCGReg datahi, TCGReg addrlo) + TCGReg datahi, HostAddress h) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); switch (opc & MO_SIZE) { case MO_8: - tcg_out_st8_12(s, COND_AL, datalo, addrlo, 0); + if (h.index < 0) { + tcg_out_st8_12(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_st8_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_16: - tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0); + if (h.index < 0) { + tcg_out_st16_8(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_st16_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_32: - tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0); + if (h.index < 0) { + tcg_out_st32_12(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_st32_r(s, h.cond, datalo, h.base, h.index); + } break; case MO_64: /* We used pair allocation for datalo, so already should be aligned. */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo, tcg_debug_assert(datahi == datalo + 1); /* STRD requires alignment; double-check that. */ if (get_alignment_bits(opc) >= MO_64) { - tcg_out_strd_8(s, COND_AL, datalo, addrlo, 0); + if (h.index < 0) { + tcg_out_strd_8(s, h.cond, datalo, h.base, 0); + } else { + tcg_out_strd_r(s, h.cond, datalo, h.base, h.index); + } + } else if (h.index_scratch) { + tcg_out_st32_rwb(s, h.cond, datalo, h.index, h.base); + tcg_out_st32_12(s, h.cond, datahi, h.index, 4); } else { - tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0); - tcg_out_st32_12(s, COND_AL, datahi, addrlo, 4); + tcg_out_dat_reg(s, h.cond, ARITH_ADD, TCG_REG_TMP, + h.base, h.index, SHIFT_IMM_LSL(0)); + tcg_out_st32_12(s, h.cond, datalo, TCG_REG_TMP, 0); + tcg_out_st32_12(s, h.cond, datahi, TCG_REG_TMP, 4); } break; default: g_assert_not_reached(); } } -#endif static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); + HostAddress h; #ifdef CONFIG_SOFTMMU - TCGReg addend = tcg_out_tlb_read(s, addrlo, addrhi, opc, get_mmuidx(oi), 0); - - tcg_out_qemu_st_index(s, COND_EQ, opc, datalo, datahi, - addrlo, addend, true); + h.cond = COND_EQ; + h.base = addrlo; + h.index_scratch = true; + h.index = tcg_out_tlb_read(s, addrlo, addrhi, opc, get_mmuidx(oi), 0); + tcg_out_qemu_st_direct(s, opc, datalo, datahi, h); /* The conditional call must come last, as we're going to return here. */ tcg_insn_unit *label_ptr = s->code_ptr; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, add_qemu_ldst_label(s, false, oi, data_type, datalo, datahi, addrlo, addrhi, s->code_ptr, label_ptr); -#else /* !CONFIG_SOFTMMU */ +#else unsigned a_bits = get_alignment_bits(opc); + + h.cond = COND_AL; if (a_bits) { tcg_out_test_alignment(s, false, addrlo, addrhi, a_bits); + h.cond = COND_EQ; } - if (guest_base) { - tcg_out_qemu_st_index(s, COND_AL, opc, datalo, datahi, - addrlo, TCG_REG_GUEST_BASE, false); - } else { - tcg_out_qemu_st_direct(s, opc, datalo, datahi, addrlo); - } + + h.base = addrlo; + h.index = guest_base ? TCG_REG_GUEST_BASE : -1; + h.index_scratch = false; + tcg_out_qemu_st_direct(s, opc, datalo, datahi, h); #endif } -- 2.34.1 Interpret the variable argument placement in the caller. Shift some code around slightly to share more between softmmu and user-only. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/loongarch64/tcg-target.c.inc | 100 +++++++++++++------------------ 1 file changed, 42 insertions(+), 58 deletions(-) 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 void tcg_out_qemu_ld_indexed(TCGContext *s, TCGReg rd, TCGReg rj, } } -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, TCGType type) +static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, + MemOpIdx oi, TCGType data_type) { - TCGReg addr_regl; - TCGReg data_regl; - MemOpIdx oi; - MemOp opc; -#if defined(CONFIG_SOFTMMU) + MemOp opc = get_memop(oi); + TCGReg base, index; + +#ifdef CONFIG_SOFTMMU tcg_insn_unit *label_ptr[1]; -#else - unsigned a_bits; -#endif - TCGReg base; - data_regl = *args++; - addr_regl = *args++; - oi = *args++; - opc = get_memop(oi); - -#if defined(CONFIG_SOFTMMU) - tcg_out_tlb_load(s, addr_regl, oi, label_ptr, 1); - base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); - tcg_out_qemu_ld_indexed(s, data_regl, base, TCG_REG_TMP2, opc, type); - add_qemu_ldst_label(s, 1, oi, type, - data_regl, addr_regl, - s->code_ptr, label_ptr); + tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 1); + index = TCG_REG_TMP2; #else - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { - tcg_out_test_alignment(s, true, addr_regl, a_bits); + tcg_out_test_alignment(s, true, addr_reg, a_bits); } - base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); - TCGReg guest_base_reg = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; - tcg_out_qemu_ld_indexed(s, data_regl, base, guest_base_reg, opc, type); + index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; +#endif + + base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0); + tcg_out_qemu_ld_indexed(s, data_reg, base, index, opc, data_type); + +#ifdef CONFIG_SOFTMMU + add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_indexed(TCGContext *s, TCGReg data, } } -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, TCGType type) +static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, + MemOpIdx oi, TCGType data_type) { - TCGReg addr_regl; - TCGReg data_regl; - MemOpIdx oi; - MemOp opc; -#if defined(CONFIG_SOFTMMU) + MemOp opc = get_memop(oi); + TCGReg base, index; + +#ifdef CONFIG_SOFTMMU tcg_insn_unit *label_ptr[1]; -#else - unsigned a_bits; -#endif - TCGReg base; - data_regl = *args++; - addr_regl = *args++; - oi = *args++; - opc = get_memop(oi); - -#if defined(CONFIG_SOFTMMU) - tcg_out_tlb_load(s, addr_regl, oi, label_ptr, 0); - base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); - tcg_out_qemu_st_indexed(s, data_regl, base, TCG_REG_TMP2, opc); - add_qemu_ldst_label(s, 0, oi, type, - data_regl, addr_regl, - s->code_ptr, label_ptr); + tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 0); + index = TCG_REG_TMP2; #else - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { - tcg_out_test_alignment(s, false, addr_regl, a_bits); + tcg_out_test_alignment(s, false, addr_reg, a_bits); } - base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); - TCGReg guest_base_reg = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; - tcg_out_qemu_st_indexed(s, data_regl, base, guest_base_reg, opc); + index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; +#endif + + base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0); + tcg_out_qemu_st_indexed(s, data_reg, base, index, opc); + +#ifdef CONFIG_SOFTMMU + add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, args, TCG_TYPE_I32); + tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I32); break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args, TCG_TYPE_I64); + tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I64); break; case INDEX_op_qemu_st_i32: - tcg_out_qemu_st(s, args, TCG_TYPE_I32); + tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I32); break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args, TCG_TYPE_I64); + tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I64); break; case INDEX_op_mov_i32: /* Always emitted via tcg_out_mov. */ -- 2.34.1 Collect the 2 parts of the host address into a struct. Reorg tcg_out_qemu_{ld,st}_direct to use it. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/loongarch64/tcg-target.c.inc | 55 +++++++++++++++++--------------- 1 file changed, 30 insertions(+), 25 deletions(-) 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 TCGReg tcg_out_zext_addr_if_32_bit(TCGContext *s, return addr; } -static void tcg_out_qemu_ld_indexed(TCGContext *s, TCGReg rd, TCGReg rj, - TCGReg rk, MemOp opc, TCGType type) +typedef struct { + TCGReg base; + TCGReg index; +} HostAddress; + +static void tcg_out_qemu_ld_indexed(TCGContext *s, MemOp opc, TCGType type, + TCGReg rd, HostAddress h) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); switch (opc & MO_SSIZE) { case MO_UB: - tcg_out_opc_ldx_bu(s, rd, rj, rk); + tcg_out_opc_ldx_bu(s, rd, h.base, h.index); break; case MO_SB: - tcg_out_opc_ldx_b(s, rd, rj, rk); + tcg_out_opc_ldx_b(s, rd, h.base, h.index); break; case MO_UW: - tcg_out_opc_ldx_hu(s, rd, rj, rk); + tcg_out_opc_ldx_hu(s, rd, h.base, h.index); break; case MO_SW: - tcg_out_opc_ldx_h(s, rd, rj, rk); + tcg_out_opc_ldx_h(s, rd, h.base, h.index); break; case MO_UL: if (type == TCG_TYPE_I64) { - tcg_out_opc_ldx_wu(s, rd, rj, rk); + tcg_out_opc_ldx_wu(s, rd, h.base, h.index); break; } /* fallthrough */ case MO_SL: - tcg_out_opc_ldx_w(s, rd, rj, rk); + tcg_out_opc_ldx_w(s, rd, h.base, h.index); break; case MO_UQ: - tcg_out_opc_ldx_d(s, rd, rj, rk); + tcg_out_opc_ldx_d(s, rd, h.base, h.index); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); - TCGReg base, index; + HostAddress h; #ifdef CONFIG_SOFTMMU tcg_insn_unit *label_ptr[1]; tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 1); - index = TCG_REG_TMP2; + h.index = TCG_REG_TMP2; #else unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addr_reg, a_bits); } - index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; + h.index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; #endif - base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0); - tcg_out_qemu_ld_indexed(s, data_reg, base, index, opc, data_type); + h.base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0); + tcg_out_qemu_ld_indexed(s, opc, data_type, data_reg, h); #ifdef CONFIG_SOFTMMU add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, #endif } -static void tcg_out_qemu_st_indexed(TCGContext *s, TCGReg data, - TCGReg rj, TCGReg rk, MemOp opc) +static void tcg_out_qemu_st_indexed(TCGContext *s, MemOp opc, + TCGReg rd, HostAddress h) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); switch (opc & MO_SIZE) { case MO_8: - tcg_out_opc_stx_b(s, data, rj, rk); + tcg_out_opc_stx_b(s, rd, h.base, h.index); break; case MO_16: - tcg_out_opc_stx_h(s, data, rj, rk); + tcg_out_opc_stx_h(s, rd, h.base, h.index); break; case MO_32: - tcg_out_opc_stx_w(s, data, rj, rk); + tcg_out_opc_stx_w(s, rd, h.base, h.index); break; case MO_64: - tcg_out_opc_stx_d(s, data, rj, rk); + tcg_out_opc_stx_d(s, rd, h.base, h.index); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); - TCGReg base, index; + HostAddress h; #ifdef CONFIG_SOFTMMU tcg_insn_unit *label_ptr[1]; tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 0); - index = TCG_REG_TMP2; + h.index = TCG_REG_TMP2; #else unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addr_reg, a_bits); } - index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; + h.index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; #endif - base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0); - tcg_out_qemu_st_indexed(s, data_reg, base, index, opc); + h.base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0); + tcg_out_qemu_st_indexed(s, opc, data_reg, h); #ifdef CONFIG_SOFTMMU add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, -- 2.34.1 Interpret the variable argument placement in the caller. There are several places where we already convert back from bool to type. Clean things up by using type throughout. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/mips/tcg-target.c.inc | 186 +++++++++++++++++++------------------- 1 file changed, 95 insertions(+), 91 deletions(-) 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 bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) #endif /* SOFTMMU */ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, - TCGReg base, MemOp opc, bool is_64) + TCGReg base, MemOp opc, TCGType type) { switch (opc & (MO_SSIZE | MO_BSWAP)) { case MO_UB: @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, tcg_out_opc_imm(s, OPC_LH, lo, base, 0); break; case MO_UL | MO_BSWAP: - if (TCG_TARGET_REG_BITS == 64 && is_64) { + if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64) { if (use_mips32r2_instructions) { tcg_out_opc_imm(s, OPC_LWU, lo, base, 0); tcg_out_bswap32(s, lo, lo, TCG_BSWAP_IZ | TCG_BSWAP_OZ); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, } break; case MO_UL: - if (TCG_TARGET_REG_BITS == 64 && is_64) { + if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64) { tcg_out_opc_imm(s, OPC_LWU, lo, base, 0); break; } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, } static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi, - TCGReg base, MemOp opc, bool is_64) + TCGReg base, MemOp opc, TCGType type) { const MIPSInsn lw1 = MIPS_BE ? OPC_LWL : OPC_LWR; const MIPSInsn lw2 = MIPS_BE ? OPC_LWR : OPC_LWL; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi, case MO_UL: tcg_out_opc_imm(s, lw1, lo, base, 0); tcg_out_opc_imm(s, lw2, lo, base, 3); - if (TCG_TARGET_REG_BITS == 64 && is_64 && !sgn) { + if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64 && !sgn) { tcg_out_ext32u(s, lo, lo); } break; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi, tcg_out_opc_imm(s, lw1, lo, base, 0); tcg_out_opc_imm(s, lw2, lo, base, 3); tcg_out_bswap32(s, lo, lo, - TCG_TARGET_REG_BITS == 64 && is_64 + TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64 ? (sgn ? TCG_BSWAP_OS : TCG_BSWAP_OZ) : 0); } else { const tcg_insn_unit *subr = - (TCG_TARGET_REG_BITS == 64 && is_64 && !sgn + (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64 && !sgn ? bswap32u_addr : bswap32_addr); tcg_out_opc_imm(s, lw1, TCG_TMP0, base, 0); tcg_out_bswap_subr(s, subr); /* delay slot */ tcg_out_opc_imm(s, lw2, TCG_TMP0, base, 3); - tcg_out_mov(s, is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32, lo, TCG_TMP3); + tcg_out_mov(s, type, lo, TCG_TMP3); } break; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi, } } -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) +static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg addr_regl, addr_regh __attribute__((unused)); - TCGReg data_regl, data_regh; - MemOpIdx oi; - MemOp opc; -#if defined(CONFIG_SOFTMMU) - tcg_insn_unit *label_ptr[2]; -#else -#endif - unsigned a_bits, s_bits; - TCGReg base = TCG_REG_A0; - - data_regl = *args++; - data_regh = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0); - addr_regl = *args++; - addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); - a_bits = get_alignment_bits(opc); - s_bits = opc & MO_SIZE; + MemOp opc = get_memop(oi); + unsigned a_bits = get_alignment_bits(opc); + unsigned s_bits = opc & MO_SIZE; + TCGReg base; /* * R6 removes the left/right instructions but requires the * system to support misaligned memory accesses. */ #if defined(CONFIG_SOFTMMU) - tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 1); + tcg_insn_unit *label_ptr[2]; + + base = TCG_REG_A0; + tcg_out_tlb_load(s, base, addrlo, addrhi, oi, label_ptr, 1); if (use_mips32r6_instructions || a_bits >= s_bits) { - tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64); + tcg_out_qemu_ld_direct(s, datalo, datahi, base, opc, data_type); } else { - tcg_out_qemu_ld_unalign(s, data_regl, data_regh, base, opc, is_64); + tcg_out_qemu_ld_unalign(s, datalo, datahi, base, opc, data_type); } - add_qemu_ldst_label(s, 1, oi, - (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), - data_regl, data_regh, addr_regl, addr_regh, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, true, oi, data_type, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #else + base = addrlo; if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { - tcg_out_ext32u(s, base, addr_regl); - addr_regl = base; + tcg_out_ext32u(s, TCG_REG_A0, base); + base = TCG_REG_A0; } - if (guest_base == 0 && data_regl != addr_regl) { - base = addr_regl; - } else if (guest_base == (int16_t)guest_base) { - tcg_out_opc_imm(s, ALIAS_PADDI, base, addr_regl, guest_base); - } else { - tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl); + if (guest_base) { + if (guest_base == (int16_t)guest_base) { + tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_A0, base, guest_base); + } else { + tcg_out_opc_reg(s, ALIAS_PADD, TCG_REG_A0, base, + TCG_GUEST_BASE_REG); + } + base = TCG_REG_A0; } if (use_mips32r6_instructions) { if (a_bits) { - tcg_out_test_alignment(s, true, addr_regl, addr_regh, a_bits); + tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } - tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64); + tcg_out_qemu_ld_direct(s, datalo, datahi, base, opc, data_type); } else { if (a_bits && a_bits != s_bits) { - tcg_out_test_alignment(s, true, addr_regl, addr_regh, a_bits); + tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } if (a_bits >= s_bits) { - tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64); + tcg_out_qemu_ld_direct(s, datalo, datahi, base, opc, data_type); } else { - tcg_out_qemu_ld_unalign(s, data_regl, data_regh, base, opc, is_64); + tcg_out_qemu_ld_unalign(s, datalo, datahi, base, opc, data_type); } } #endif @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_unalign(TCGContext *s, TCGReg lo, TCGReg hi, g_assert_not_reached(); } } -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) -{ - TCGReg addr_regl, addr_regh __attribute__((unused)); - TCGReg data_regl, data_regh; - MemOpIdx oi; - MemOp opc; -#if defined(CONFIG_SOFTMMU) - tcg_insn_unit *label_ptr[2]; -#endif - unsigned a_bits, s_bits; - TCGReg base = TCG_REG_A0; - data_regl = *args++; - data_regh = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0); - addr_regl = *args++; - addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); - a_bits = get_alignment_bits(opc); - s_bits = opc & MO_SIZE; +static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) +{ + MemOp opc = get_memop(oi); + unsigned a_bits = get_alignment_bits(opc); + unsigned s_bits = opc & MO_SIZE; + TCGReg base; /* * R6 removes the left/right instructions but requires the * system to support misaligned memory accesses. */ #if defined(CONFIG_SOFTMMU) - tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 0); + tcg_insn_unit *label_ptr[2]; + + base = TCG_REG_A0; + tcg_out_tlb_load(s, base, addrlo, addrhi, oi, label_ptr, 0); if (use_mips32r6_instructions || a_bits >= s_bits) { - tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc); + tcg_out_qemu_st_direct(s, datalo, datahi, base, opc); } else { - tcg_out_qemu_st_unalign(s, data_regl, data_regh, base, opc); + tcg_out_qemu_st_unalign(s, datalo, datahi, base, opc); } - add_qemu_ldst_label(s, 0, oi, - (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), - data_regl, data_regh, addr_regl, addr_regh, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, false, oi, data_type, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #else + base = addrlo; if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { - tcg_out_ext32u(s, base, addr_regl); - addr_regl = base; + tcg_out_ext32u(s, TCG_REG_A0, base); + base = TCG_REG_A0; } - if (guest_base == 0) { - base = addr_regl; - } else if (guest_base == (int16_t)guest_base) { - tcg_out_opc_imm(s, ALIAS_PADDI, base, addr_regl, guest_base); - } else { - tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl); + if (guest_base) { + if (guest_base == (int16_t)guest_base) { + tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_A0, base, guest_base); + } else { + tcg_out_opc_reg(s, ALIAS_PADD, TCG_REG_A0, base, + TCG_GUEST_BASE_REG); + } + base = TCG_REG_A0; } if (use_mips32r6_instructions) { if (a_bits) { - tcg_out_test_alignment(s, true, addr_regl, addr_regh, a_bits); + tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } - tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc); + tcg_out_qemu_st_direct(s, datalo, datahi, base, opc); } else { if (a_bits && a_bits != s_bits) { - tcg_out_test_alignment(s, true, addr_regl, addr_regh, a_bits); + tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } if (a_bits >= s_bits) { - tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc); + tcg_out_qemu_st_direct(s, datalo, datahi, base, opc); } else { - tcg_out_qemu_st_unalign(s, data_regl, data_regh, base, opc); + tcg_out_qemu_st_unalign(s, datalo, datahi, base, opc); } } #endif @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, args, false); + if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + tcg_out_qemu_ld(s, a0, 0, a1, 0, a2, TCG_TYPE_I32); + } else { + tcg_out_qemu_ld(s, a0, 0, a1, a2, args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args, true); + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_qemu_ld(s, a0, 0, a1, 0, a2, TCG_TYPE_I64); + } else if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_ld(s, a0, a1, a2, 0, args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_ld(s, a0, a1, a2, args[3], args[4], TCG_TYPE_I64); + } break; case INDEX_op_qemu_st_i32: - tcg_out_qemu_st(s, args, false); + if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + tcg_out_qemu_st(s, a0, 0, a1, 0, a2, TCG_TYPE_I32); + } else { + tcg_out_qemu_st(s, a0, 0, a1, a2, args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args, true); + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_qemu_st(s, a0, 0, a1, 0, a2, TCG_TYPE_I64); + } else if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_st(s, a0, a1, a2, 0, args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_st(s, a0, a1, a2, args[3], args[4], TCG_TYPE_I64); + } break; case INDEX_op_add2_i32: -- 2.34.1 Interpret the variable argument placement in the caller. Pass data_type instead of is64 -- there are several places where we already convert back from bool to type. Clean things up by using type throughout. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.c.inc | 110 +++++++++++++++++++++------------------ 1 file changed, 59 insertions(+), 51 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 TCGReg tcg_out_tlb_read(TCGContext *s, MemOp opc, /* Record the context of a call to the out of line helper code for the slow path for a load or store, so that we can later generate the correct helper code. */ -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, + TCGType type, MemOpIdx oi, TCGReg datalo_reg, TCGReg datahi_reg, TCGReg addrlo_reg, TCGReg addrhi_reg, tcg_insn_unit *raddr, tcg_insn_unit *lptr) @@ -XXX,XX +XXX,XX @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, TCGLabelQemuLdst *label = new_ldst_label(s); label->is_ld = is_ld; + label->type = type; label->oi = oi; label->datalo_reg = datalo_reg; label->datahi_reg = datahi_reg; @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) #endif /* SOFTMMU */ -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) +static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg datalo, datahi, addrlo, rbase; - TCGReg addrhi __attribute__((unused)); - MemOpIdx oi; - MemOp opc, s_bits; + MemOp opc = get_memop(oi); + MemOp s_bits = opc & MO_SIZE; + TCGReg rbase; + #ifdef CONFIG_SOFTMMU - int mem_index; tcg_insn_unit *label_ptr; -#else - unsigned a_bits; -#endif - datalo = *args++; - datahi = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0); - addrlo = *args++; - addrhi = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); - s_bits = opc & MO_SIZE; - -#ifdef CONFIG_SOFTMMU - mem_index = get_mmuidx(oi); - addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, mem_index, true); + addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, get_mmuidx(oi), true); /* Load a pointer into the current opcode w/conditional branch-link. */ label_ptr = s->code_ptr; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) rbase = TCG_REG_R3; #else /* !CONFIG_SOFTMMU */ - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) } #ifdef CONFIG_SOFTMMU - add_qemu_ldst_label(s, true, oi, datalo, datahi, addrlo, addrhi, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, true, data_type, oi, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #endif } -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) +static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addrhi, + MemOpIdx oi, TCGType data_type) { - TCGReg datalo, datahi, addrlo, rbase; - TCGReg addrhi __attribute__((unused)); - MemOpIdx oi; - MemOp opc, s_bits; + MemOp opc = get_memop(oi); + MemOp s_bits = opc & MO_SIZE; + TCGReg rbase; + #ifdef CONFIG_SOFTMMU - int mem_index; tcg_insn_unit *label_ptr; -#else - unsigned a_bits; -#endif - datalo = *args++; - datahi = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0); - addrlo = *args++; - addrhi = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0); - oi = *args++; - opc = get_memop(oi); - s_bits = opc & MO_SIZE; - -#ifdef CONFIG_SOFTMMU - mem_index = get_mmuidx(oi); - addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, mem_index, false); + addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, get_mmuidx(oi), false); /* Load a pointer into the current opcode w/conditional branch-link. */ label_ptr = s->code_ptr; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) rbase = TCG_REG_R3; #else /* !CONFIG_SOFTMMU */ - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addrlo, addrhi, a_bits); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) } #ifdef CONFIG_SOFTMMU - add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi, - s->code_ptr, label_ptr); + add_qemu_ldst_label(s, false, data_type, oi, datalo, datahi, + addrlo, addrhi, s->code_ptr, label_ptr); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, args, false); + if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + tcg_out_qemu_ld(s, args[0], -1, args[1], -1, + args[2], TCG_TYPE_I32); + } else { + tcg_out_qemu_ld(s, args[0], -1, args[1], args[2], + args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args, true); + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_qemu_ld(s, args[0], -1, args[1], -1, + args[2], TCG_TYPE_I64); + } else if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_ld(s, args[0], args[1], args[2], -1, + args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_ld(s, args[0], args[1], args[2], args[3], + args[4], TCG_TYPE_I64); + } break; case INDEX_op_qemu_st_i32: - tcg_out_qemu_st(s, args, false); + if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) { + tcg_out_qemu_st(s, args[0], -1, args[1], -1, + args[2], TCG_TYPE_I32); + } else { + tcg_out_qemu_st(s, args[0], -1, args[1], args[2], + args[3], TCG_TYPE_I32); + } break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args, true); + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_qemu_st(s, args[0], -1, args[1], -1, + args[2], TCG_TYPE_I64); + } else if (TARGET_LONG_BITS == 32) { + tcg_out_qemu_st(s, args[0], args[1], args[2], -1, + args[3], TCG_TYPE_I64); + } else { + tcg_out_qemu_st(s, args[0], args[1], args[2], args[3], + args[4], TCG_TYPE_I64); + } break; case INDEX_op_setcond_i32: -- 2.34.1 Collect the parts of the host address into a struct. Reorg tcg_out_qemu_{ld,st} to use it. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.c.inc | 90 +++++++++++++++++++++------------------- 1 file changed, 47 insertions(+), 43 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 bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { return tcg_out_fail_alignment(s, l); } - #endif /* SOFTMMU */ +typedef struct { + TCGReg base; + TCGReg index; +} HostAddress; + static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; - TCGReg rbase; + HostAddress h; #ifdef CONFIG_SOFTMMU tcg_insn_unit *label_ptr; - addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, get_mmuidx(oi), true); + h.index = tcg_out_tlb_read(s, opc, addrlo, addrhi, get_mmuidx(oi), true); + h.base = TCG_REG_R3; /* Load a pointer into the current opcode w/conditional branch-link. */ label_ptr = s->code_ptr; tcg_out32(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK); - - rbase = TCG_REG_R3; #else /* !CONFIG_SOFTMMU */ unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addrlo, addrhi, a_bits); } - rbase = guest_base ? TCG_GUEST_BASE_REG : 0; + h.base = guest_base ? TCG_GUEST_BASE_REG : 0; + h.index = addrlo; if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { tcg_out_ext32u(s, TCG_REG_TMP1, addrlo); - addrlo = TCG_REG_TMP1; + h.index = TCG_REG_TMP1; } #endif if (TCG_TARGET_REG_BITS == 32 && s_bits == MO_64) { if (opc & MO_BSWAP) { - tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4)); - tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo)); - tcg_out32(s, LWBRX | TAB(datahi, rbase, TCG_REG_R0)); - } else if (rbase != 0) { - tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4)); - tcg_out32(s, LWZX | TAB(datahi, rbase, addrlo)); - tcg_out32(s, LWZX | TAB(datalo, rbase, TCG_REG_R0)); - } else if (addrlo == datahi) { - tcg_out32(s, LWZ | TAI(datalo, addrlo, 4)); - tcg_out32(s, LWZ | TAI(datahi, addrlo, 0)); + tcg_out32(s, ADDI | TAI(TCG_REG_R0, h.index, 4)); + tcg_out32(s, LWBRX | TAB(datalo, h.base, h.index)); + tcg_out32(s, LWBRX | TAB(datahi, h.base, TCG_REG_R0)); + } else if (h.base != 0) { + tcg_out32(s, ADDI | TAI(TCG_REG_R0, h.index, 4)); + tcg_out32(s, LWZX | TAB(datahi, h.base, h.index)); + tcg_out32(s, LWZX | TAB(datalo, h.base, TCG_REG_R0)); + } else if (h.index == datahi) { + tcg_out32(s, LWZ | TAI(datalo, h.index, 4)); + tcg_out32(s, LWZ | TAI(datahi, h.index, 0)); } else { - tcg_out32(s, LWZ | TAI(datahi, addrlo, 0)); - tcg_out32(s, LWZ | TAI(datalo, addrlo, 4)); + tcg_out32(s, LWZ | TAI(datahi, h.index, 0)); + tcg_out32(s, LWZ | TAI(datalo, h.index, 4)); } } else { uint32_t insn = qemu_ldx_opc[opc & (MO_BSWAP | MO_SSIZE)]; if (!have_isa_2_06 && insn == LDBRX) { - tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4)); - tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo)); - tcg_out32(s, LWBRX | TAB(TCG_REG_R0, rbase, TCG_REG_R0)); + tcg_out32(s, ADDI | TAI(TCG_REG_R0, h.index, 4)); + tcg_out32(s, LWBRX | TAB(datalo, h.base, h.index)); + tcg_out32(s, LWBRX | TAB(TCG_REG_R0, h.base, TCG_REG_R0)); tcg_out_rld(s, RLDIMI, datalo, TCG_REG_R0, 32, 0); } else if (insn) { - tcg_out32(s, insn | TAB(datalo, rbase, addrlo)); + tcg_out32(s, insn | TAB(datalo, h.base, h.index)); } else { insn = qemu_ldx_opc[opc & (MO_SIZE | MO_BSWAP)]; - tcg_out32(s, insn | TAB(datalo, rbase, addrlo)); + tcg_out32(s, insn | TAB(datalo, h.base, h.index)); tcg_out_movext(s, TCG_TYPE_REG, datalo, TCG_TYPE_REG, opc & MO_SSIZE, datalo); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi, { MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; - TCGReg rbase; + HostAddress h; #ifdef CONFIG_SOFTMMU tcg_insn_unit *label_ptr; - addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, get_mmuidx(oi), false); + h.index = tcg_out_tlb_read(s, opc, addrlo, addrhi, get_mmuidx(oi), false); + h.base = TCG_REG_R3; /* Load a pointer into the current opcode w/conditional branch-link. */ label_ptr = s->code_ptr; tcg_out32(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK); - - rbase = TCG_REG_R3; #else /* !CONFIG_SOFTMMU */ unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addrlo, addrhi, a_bits); } - rbase = guest_base ? TCG_GUEST_BASE_REG : 0; + h.base = guest_base ? TCG_GUEST_BASE_REG : 0; + h.index = addrlo; if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { tcg_out_ext32u(s, TCG_REG_TMP1, addrlo); - addrlo = TCG_REG_TMP1; + h.index = TCG_REG_TMP1; } #endif if (TCG_TARGET_REG_BITS == 32 && s_bits == MO_64) { if (opc & MO_BSWAP) { - tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4)); - tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo)); - tcg_out32(s, STWBRX | SAB(datahi, rbase, TCG_REG_R0)); - } else if (rbase != 0) { - tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4)); - tcg_out32(s, STWX | SAB(datahi, rbase, addrlo)); - tcg_out32(s, STWX | SAB(datalo, rbase, TCG_REG_R0)); + tcg_out32(s, ADDI | TAI(TCG_REG_R0, h.index, 4)); + tcg_out32(s, STWBRX | SAB(datalo, h.base, h.index)); + tcg_out32(s, STWBRX | SAB(datahi, h.base, TCG_REG_R0)); + } else if (h.base != 0) { + tcg_out32(s, ADDI | TAI(TCG_REG_R0, h.index, 4)); + tcg_out32(s, STWX | SAB(datahi, h.base, h.index)); + tcg_out32(s, STWX | SAB(datalo, h.base, TCG_REG_R0)); } else { - tcg_out32(s, STW | TAI(datahi, addrlo, 0)); - tcg_out32(s, STW | TAI(datalo, addrlo, 4)); + tcg_out32(s, STW | TAI(datahi, h.index, 0)); + tcg_out32(s, STW | TAI(datalo, h.index, 4)); } } else { uint32_t insn = qemu_stx_opc[opc & (MO_BSWAP | MO_SIZE)]; if (!have_isa_2_06 && insn == STDBRX) { - tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo)); - tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, addrlo, 4)); + tcg_out32(s, STWBRX | SAB(datalo, h.base, h.index)); + tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, h.index, 4)); tcg_out_shri64(s, TCG_REG_R0, datalo, 32); - tcg_out32(s, STWBRX | SAB(TCG_REG_R0, rbase, TCG_REG_TMP1)); + tcg_out32(s, STWBRX | SAB(TCG_REG_R0, h.base, TCG_REG_TMP1)); } else { - tcg_out32(s, insn | SAB(datalo, rbase, addrlo)); + tcg_out32(s, insn | SAB(datalo, h.base, h.index)); } } -- 2.34.1 The port currently does not support "oversize" guests, which means riscv32 can only target 32-bit guests. We will soon be building TCG once for all guests. This implies that we can only support riscv64. Since all Linux distributions target riscv64 not riscv32, this is not much of a restriction and simplifies the code. The brcond2 and setcond2 opcodes are exclusive to 32-bit hosts, so we can and should remove the stubs. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/riscv/tcg-target-con-set.h | 8 -- tcg/riscv/tcg-target.h | 22 ++-- tcg/riscv/tcg-target.c.inc | 232 +++++++++------------------------ 3 files changed, 72 insertions(+), 190 deletions(-) diff --git a/tcg/riscv/tcg-target-con-set.h b/tcg/riscv/tcg-target-con-set.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/riscv/tcg-target-con-set.h +++ b/tcg/riscv/tcg-target-con-set.h @@ -XXX,XX +XXX,XX @@ C_O0_I1(r) C_O0_I2(LZ, L) C_O0_I2(rZ, r) C_O0_I2(rZ, rZ) -C_O0_I3(LZ, L, L) -C_O0_I3(LZ, LZ, L) -C_O0_I4(LZ, LZ, L, L) -C_O0_I4(rZ, rZ, rZ, rZ) C_O1_I1(r, L) C_O1_I1(r, r) -C_O1_I2(r, L, L) C_O1_I2(r, r, ri) C_O1_I2(r, r, rI) C_O1_I2(r, rZ, rN) C_O1_I2(r, rZ, rZ) -C_O1_I4(r, rZ, rZ, rZ, rZ) -C_O2_I1(r, r, L) -C_O2_I2(r, r, L, L) C_O2_I4(r, r, rZ, rZ, rM, rM) 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 -#if __riscv_xlen == 32 -# define TCG_TARGET_REG_BITS 32 -#elif __riscv_xlen == 64 -# define TCG_TARGET_REG_BITS 64 +/* + * 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_TLB_DISPLACEMENT_BITS 20 @@ -XXX,XX +XXX,XX @@ typedef enum { #define TCG_TARGET_STACK_ALIGN 16 #define TCG_TARGET_CALL_STACK_OFFSET 0 #define TCG_TARGET_CALL_ARG_I32 TCG_CALL_ARG_NORMAL -#if TCG_TARGET_REG_BITS == 32 -#define TCG_TARGET_CALL_ARG_I64 TCG_CALL_ARG_EVEN -#define TCG_TARGET_CALL_ARG_I128 TCG_CALL_ARG_EVEN -#else #define TCG_TARGET_CALL_ARG_I64 TCG_CALL_ARG_NORMAL #define TCG_TARGET_CALL_ARG_I128 TCG_CALL_ARG_NORMAL -#endif #define TCG_TARGET_CALL_RET_I128 TCG_CALL_RET_NORMAL /* optional instructions */ @@ -XXX,XX +XXX,XX @@ typedef enum { #define TCG_TARGET_HAS_sub2_i32 1 #define TCG_TARGET_HAS_mulu2_i32 0 #define TCG_TARGET_HAS_muls2_i32 0 -#define TCG_TARGET_HAS_muluh_i32 (TCG_TARGET_REG_BITS == 32) -#define TCG_TARGET_HAS_mulsh_i32 (TCG_TARGET_REG_BITS == 32) +#define TCG_TARGET_HAS_muluh_i32 0 +#define TCG_TARGET_HAS_mulsh_i32 0 #define TCG_TARGET_HAS_ext8s_i32 1 #define TCG_TARGET_HAS_ext16s_i32 1 #define TCG_TARGET_HAS_ext8u_i32 1 @@ -XXX,XX +XXX,XX @@ typedef enum { #define TCG_TARGET_HAS_setcond2 1 #define TCG_TARGET_HAS_qemu_st8_i32 0 -#if TCG_TARGET_REG_BITS == 64 #define TCG_TARGET_HAS_movcond_i64 0 #define TCG_TARGET_HAS_div_i64 1 #define TCG_TARGET_HAS_rem_i64 1 @@ -XXX,XX +XXX,XX @@ typedef enum { #define TCG_TARGET_HAS_muls2_i64 0 #define TCG_TARGET_HAS_muluh_i64 1 #define TCG_TARGET_HAS_mulsh_i64 1 -#endif #define TCG_TARGET_DEFAULT_MO (0) 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 TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot) #define SOFTMMU_RESERVE_REGS 0 #endif - -static inline tcg_target_long sextreg(tcg_target_long val, int pos, int len) -{ - if (TCG_TARGET_REG_BITS == 32) { - return sextract32(val, pos, len); - } else { - return sextract64(val, pos, len); - } -} +#define sextreg sextract64 /* test if a constant matches the constraint */ static bool tcg_target_const_match(int64_t val, TCGType type, int ct) @@ -XXX,XX +XXX,XX @@ typedef enum { OPC_XOR = 0x4033, OPC_XORI = 0x4013, -#if TCG_TARGET_REG_BITS == 64 OPC_ADDIW = 0x1b, OPC_ADDW = 0x3b, OPC_DIVUW = 0x200503b, @@ -XXX,XX +XXX,XX @@ typedef enum { OPC_SRLIW = 0x501b, OPC_SRLW = 0x503b, OPC_SUBW = 0x4000003b, -#else - /* Simplify code throughout by defining aliases for RV32. */ - OPC_ADDIW = OPC_ADDI, - OPC_ADDW = OPC_ADD, - OPC_DIVUW = OPC_DIVU, - OPC_DIVW = OPC_DIV, - OPC_MULW = OPC_MUL, - OPC_REMUW = OPC_REMU, - OPC_REMW = OPC_REM, - OPC_SLLIW = OPC_SLLI, - OPC_SLLW = OPC_SLL, - OPC_SRAIW = OPC_SRAI, - OPC_SRAW = OPC_SRA, - OPC_SRLIW = OPC_SRLI, - OPC_SRLW = OPC_SRL, - OPC_SUBW = OPC_SUB, -#endif OPC_FENCE = 0x0000000f, OPC_NOP = OPC_ADDI, /* nop = addi r0,r0,0 */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd, tcg_target_long lo, hi, tmp; int shift, ret; - if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) { + if (type == TCG_TYPE_I32) { val = (int32_t)val; } @@ -XXX,XX +XXX,XX @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd, } hi = val - lo; - if (TCG_TARGET_REG_BITS == 32 || val == (int32_t)val) { + if (val == (int32_t)val) { tcg_out_opc_upper(s, OPC_LUI, rd, hi); if (lo != 0) { tcg_out_opc_imm(s, OPC_ADDIW, rd, rd, lo); @@ -XXX,XX +XXX,XX @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd, return; } - /* We can only be here if TCG_TARGET_REG_BITS != 32 */ tmp = tcg_pcrel_diff(s, (void *)val); if (tmp == (int32_t)tmp) { tcg_out_opc_upper(s, OPC_AUIPC, rd, 0); @@ -XXX,XX +XXX,XX @@ static void tcg_out_ldst(TCGContext *s, RISCVInsn opc, TCGReg data, static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1, intptr_t arg2) { - bool is32bit = (TCG_TARGET_REG_BITS == 32 || type == TCG_TYPE_I32); - tcg_out_ldst(s, is32bit ? OPC_LW : OPC_LD, arg, arg1, arg2); + RISCVInsn insn = type == TCG_TYPE_I32 ? OPC_LW : OPC_LD; + tcg_out_ldst(s, insn, arg, arg1, arg2); } static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1, intptr_t arg2) { - bool is32bit = (TCG_TARGET_REG_BITS == 32 || type == TCG_TYPE_I32); - tcg_out_ldst(s, is32bit ? OPC_SW : OPC_SD, arg, arg1, arg2); + RISCVInsn insn = type == TCG_TYPE_I32 ? OPC_SW : OPC_SD; + tcg_out_ldst(s, insn, arg, arg1, arg2); } static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val, @@ -XXX,XX +XXX,XX @@ static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGReg ret, } } -static void tcg_out_brcond2(TCGContext *s, TCGCond cond, TCGReg al, TCGReg ah, - TCGReg bl, TCGReg bh, TCGLabel *l) -{ - /* todo */ - g_assert_not_reached(); -} - -static void tcg_out_setcond2(TCGContext *s, TCGCond cond, TCGReg ret, - TCGReg al, TCGReg ah, TCGReg bl, TCGReg bh) -{ - /* todo */ - g_assert_not_reached(); -} - static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail) { TCGReg link = tail ? TCG_REG_ZERO : TCG_REG_RA; @@ -XXX,XX +XXX,XX @@ static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail) if (offset == sextreg(offset, 0, 20)) { /* short jump: -2097150 to 2097152 */ tcg_out_opc_jump(s, OPC_JAL, link, offset); - } else if (TCG_TARGET_REG_BITS == 32 || offset == (int32_t)offset) { + } else if (offset == (int32_t)offset) { /* long jump: -2147483646 to 2147483648 */ tcg_out_opc_upper(s, OPC_AUIPC, TCG_REG_TMP0, 0); tcg_out_opc_imm(s, OPC_JALR, link, TCG_REG_TMP0, 0); ret = reloc_call(s->code_ptr - 2, arg); tcg_debug_assert(ret == true); - } else if (TCG_TARGET_REG_BITS == 64) { + } else { /* far jump: 64-bit */ tcg_target_long imm = sextreg((tcg_target_long)arg, 0, 12); tcg_target_long base = (tcg_target_long)arg - imm; tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP0, base); tcg_out_opc_imm(s, OPC_JALR, link, TCG_REG_TMP0, imm); - } else { - g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void * const qemu_st_helpers[MO_SIZE + 1] = { #endif }; -/* We don't support oversize guests */ -QEMU_BUILD_BUG_ON(TCG_TARGET_REG_BITS < TARGET_LONG_BITS); - /* We expect to use a 12-bit negative offset from ENV. */ QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11)); @@ -XXX,XX +XXX,XX @@ static void tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) tcg_debug_assert(ok); } -static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addrl, - TCGReg addrh, MemOpIdx oi, +static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addr, MemOpIdx oi, tcg_insn_unit **label_ptr, bool is_load) { MemOp opc = get_memop(oi); @@ -XXX,XX +XXX,XX @@ static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addrl, tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, mask_base, mask_ofs); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, table_base, table_ofs); - tcg_out_opc_imm(s, OPC_SRLI, TCG_REG_TMP2, addrl, + tcg_out_opc_imm(s, OPC_SRLI, TCG_REG_TMP2, addr, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP0); tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1); @@ -XXX,XX +XXX,XX @@ static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addrl, /* Clear the non-page, non-alignment bits from the address. */ compare_mask = (tcg_target_long)TARGET_PAGE_MASK | ((1 << a_bits) - 1); if (compare_mask == sextreg(compare_mask, 0, 12)) { - tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addrl, compare_mask); + tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr, compare_mask); } else { tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_TMP1, compare_mask); - tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addrl); + tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addr); } /* Compare masked address with the TLB entry. */ @@ -XXX,XX +XXX,XX @@ static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addrl, tcg_out_opc_branch(s, OPC_BNE, TCG_REG_TMP0, TCG_REG_TMP1, 0); /* TLB Hit - translate address using addend. */ - if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { - tcg_out_ext32u(s, TCG_REG_TMP0, addrl); - addrl = TCG_REG_TMP0; + if (TARGET_LONG_BITS == 32) { + tcg_out_ext32u(s, TCG_REG_TMP0, addr); + addr = TCG_REG_TMP0; } - tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_REG_TMP2, addrl); + tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_REG_TMP2, addr); return TCG_REG_TMP0; } static void add_qemu_ldst_label(TCGContext *s, int is_ld, MemOpIdx oi, - TCGType ext, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo, TCGReg addrhi, - void *raddr, tcg_insn_unit **label_ptr) + TCGType data_type, TCGReg data_reg, + TCGReg addr_reg, void *raddr, + tcg_insn_unit **label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s); label->is_ld = is_ld; label->oi = oi; - label->type = ext; - label->datalo_reg = datalo; - label->datahi_reg = datahi; - label->addrlo_reg = addrlo; - label->addrhi_reg = addrhi; + label->type = data_type; + label->datalo_reg = data_reg; + label->addrlo_reg = addr_reg; label->raddr = tcg_splitwx_to_rx(raddr); label->label_ptr[0] = label_ptr[0]; } @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) TCGReg a2 = tcg_target_call_iarg_regs[2]; TCGReg a3 = tcg_target_call_iarg_regs[3]; - /* We don't support oversize guests */ - if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { - g_assert_not_reached(); - } - /* resolve label address */ if (!reloc_sbimm12(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) { return false; @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) TCGReg a3 = tcg_target_call_iarg_regs[3]; TCGReg a4 = tcg_target_call_iarg_regs[4]; - /* We don't support oversize guests */ - if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { - g_assert_not_reached(); - } - /* resolve label address */ if (!reloc_sbimm12(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) { return false; @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) #endif /* CONFIG_SOFTMMU */ -static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, +static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg val, TCGReg base, MemOp opc, bool is_64) { /* Byte swapping is left to middle-end expansion. */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, switch (opc & (MO_SSIZE)) { case MO_UB: - tcg_out_opc_imm(s, OPC_LBU, lo, base, 0); + tcg_out_opc_imm(s, OPC_LBU, val, base, 0); break; case MO_SB: - tcg_out_opc_imm(s, OPC_LB, lo, base, 0); + tcg_out_opc_imm(s, OPC_LB, val, base, 0); break; case MO_UW: - tcg_out_opc_imm(s, OPC_LHU, lo, base, 0); + tcg_out_opc_imm(s, OPC_LHU, val, base, 0); break; case MO_SW: - tcg_out_opc_imm(s, OPC_LH, lo, base, 0); + tcg_out_opc_imm(s, OPC_LH, val, base, 0); break; case MO_UL: - if (TCG_TARGET_REG_BITS == 64 && is_64) { - tcg_out_opc_imm(s, OPC_LWU, lo, base, 0); + if (is_64) { + tcg_out_opc_imm(s, OPC_LWU, val, base, 0); break; } /* FALLTHRU */ case MO_SL: - tcg_out_opc_imm(s, OPC_LW, lo, base, 0); + tcg_out_opc_imm(s, OPC_LW, val, base, 0); break; case MO_UQ: - /* Prefer to load from offset 0 first, but allow for overlap. */ - if (TCG_TARGET_REG_BITS == 64) { - tcg_out_opc_imm(s, OPC_LD, lo, base, 0); - } else if (lo != base) { - tcg_out_opc_imm(s, OPC_LW, lo, base, 0); - tcg_out_opc_imm(s, OPC_LW, hi, base, 4); - } else { - tcg_out_opc_imm(s, OPC_LW, hi, base, 4); - tcg_out_opc_imm(s, OPC_LW, lo, base, 0); - } + tcg_out_opc_imm(s, OPC_LD, val, base, 0); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi, static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) { - TCGReg addr_regl, addr_regh __attribute__((unused)); - TCGReg data_regl, data_regh; + TCGReg addr_reg, data_reg; MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) #endif TCGReg base; - data_regl = *args++; - data_regh = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0); - addr_regl = *args++; - addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0); + data_reg = *args++; + addr_reg = *args++; oi = *args++; opc = get_memop(oi); #if defined(CONFIG_SOFTMMU) - base = tcg_out_tlb_load(s, addr_regl, addr_regh, oi, label_ptr, 1); - tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64); - add_qemu_ldst_label(s, 1, oi, - (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), - data_regl, data_regh, addr_regl, addr_regh, - s->code_ptr, label_ptr); + base = tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 1); + tcg_out_qemu_ld_direct(s, data_reg, base, opc, is_64); + add_qemu_ldst_label(s, 1, oi, (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), + data_reg, addr_reg, s->code_ptr, label_ptr); #else a_bits = get_alignment_bits(opc); if (a_bits) { - tcg_out_test_alignment(s, true, addr_regl, a_bits); + tcg_out_test_alignment(s, true, addr_reg, a_bits); } - base = addr_regl; - if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { + base = addr_reg; + if (TARGET_LONG_BITS == 32) { tcg_out_ext32u(s, TCG_REG_TMP0, base); base = TCG_REG_TMP0; } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_GUEST_BASE_REG, base); base = TCG_REG_TMP0; } - tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64); + tcg_out_qemu_ld_direct(s, data_reg, base, opc, is_64); #endif } -static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi, +static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg val, TCGReg base, MemOp opc) { /* Byte swapping is left to middle-end expansion. */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi, switch (opc & (MO_SSIZE)) { case MO_8: - tcg_out_opc_store(s, OPC_SB, base, lo, 0); + tcg_out_opc_store(s, OPC_SB, base, val, 0); break; case MO_16: - tcg_out_opc_store(s, OPC_SH, base, lo, 0); + tcg_out_opc_store(s, OPC_SH, base, val, 0); break; case MO_32: - tcg_out_opc_store(s, OPC_SW, base, lo, 0); + tcg_out_opc_store(s, OPC_SW, base, val, 0); break; case MO_64: - if (TCG_TARGET_REG_BITS == 64) { - tcg_out_opc_store(s, OPC_SD, base, lo, 0); - } else { - tcg_out_opc_store(s, OPC_SW, base, lo, 0); - tcg_out_opc_store(s, OPC_SW, base, hi, 4); - } + tcg_out_opc_store(s, OPC_SD, base, val, 0); break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi, static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) { - TCGReg addr_regl, addr_regh __attribute__((unused)); - TCGReg data_regl, data_regh; + TCGReg addr_reg, data_reg; MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) #endif TCGReg base; - data_regl = *args++; - data_regh = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0); - addr_regl = *args++; - addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0); + data_reg = *args++; + addr_reg = *args++; oi = *args++; opc = get_memop(oi); #if defined(CONFIG_SOFTMMU) - base = tcg_out_tlb_load(s, addr_regl, addr_regh, oi, label_ptr, 0); - tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc); - add_qemu_ldst_label(s, 0, oi, - (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), - data_regl, data_regh, addr_regl, addr_regh, - s->code_ptr, label_ptr); + base = tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 0); + tcg_out_qemu_st_direct(s, data_reg, base, opc); + add_qemu_ldst_label(s, 0, oi, (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), + data_reg, addr_reg, s->code_ptr, label_ptr); #else a_bits = get_alignment_bits(opc); if (a_bits) { - tcg_out_test_alignment(s, false, addr_regl, a_bits); + tcg_out_test_alignment(s, false, addr_reg, a_bits); } - base = addr_regl; - if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) { + base = addr_reg; + if (TARGET_LONG_BITS == 32) { tcg_out_ext32u(s, TCG_REG_TMP0, base); base = TCG_REG_TMP0; } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_GUEST_BASE_REG, base); base = TCG_REG_TMP0; } - tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc); + tcg_out_qemu_st_direct(s, data_reg, base, opc); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, case INDEX_op_brcond_i64: tcg_out_brcond(s, a2, a0, a1, arg_label(args[3])); break; - case INDEX_op_brcond2_i32: - tcg_out_brcond2(s, args[4], a0, a1, a2, args[3], arg_label(args[5])); - break; case INDEX_op_setcond_i32: case INDEX_op_setcond_i64: tcg_out_setcond(s, args[3], a0, a1, a2); break; - case INDEX_op_setcond2_i32: - tcg_out_setcond2(s, args[5], a0, a1, a2, args[3], args[4]); - break; case INDEX_op_qemu_ld_i32: tcg_out_qemu_ld(s, args, false); @@ -XXX,XX +XXX,XX @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_sub2_i64: return C_O2_I4(r, r, rZ, rZ, rM, rM); - case INDEX_op_brcond2_i32: - return C_O0_I4(rZ, rZ, rZ, rZ); - - case INDEX_op_setcond2_i32: - return C_O1_I4(r, rZ, rZ, rZ, rZ); - case INDEX_op_qemu_ld_i32: - return (TARGET_LONG_BITS <= TCG_TARGET_REG_BITS - ? C_O1_I1(r, L) : C_O1_I2(r, L, L)); - case INDEX_op_qemu_st_i32: - return (TARGET_LONG_BITS <= TCG_TARGET_REG_BITS - ? C_O0_I2(LZ, L) : C_O0_I3(LZ, L, L)); case INDEX_op_qemu_ld_i64: - return (TCG_TARGET_REG_BITS == 64 ? C_O1_I1(r, L) - : TARGET_LONG_BITS <= TCG_TARGET_REG_BITS ? C_O2_I1(r, r, L) - : C_O2_I2(r, r, L, L)); + return C_O1_I1(r, L); + case INDEX_op_qemu_st_i32: case INDEX_op_qemu_st_i64: - return (TCG_TARGET_REG_BITS == 64 ? C_O0_I2(LZ, L) - : TARGET_LONG_BITS <= TCG_TARGET_REG_BITS ? C_O0_I3(LZ, LZ, L) - : C_O0_I4(LZ, LZ, L, L)); + return C_O0_I2(LZ, L); default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void tcg_target_qemu_prologue(TCGContext *s) static void tcg_target_init(TCGContext *s) { tcg_target_available_regs[TCG_TYPE_I32] = 0xffffffff; - if (TCG_TARGET_REG_BITS == 64) { - tcg_target_available_regs[TCG_TYPE_I64] = 0xffffffff; - } + tcg_target_available_regs[TCG_TYPE_I64] = 0xffffffff; tcg_target_call_clobber_regs = -1u; tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_S0); -- 2.34.1 Interpret the variable argument placement in the caller. Pass data_type instead of is64 -- there are several places where we already convert back from bool to type. Clean things up by using type throughout. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/riscv/tcg-target.c.inc | 66 ++++++++++++++------------------------ 1 file changed, 24 insertions(+), 42 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 bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) #endif /* CONFIG_SOFTMMU */ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg val, - TCGReg base, MemOp opc, bool is_64) + TCGReg base, MemOp opc, TCGType type) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg val, tcg_out_opc_imm(s, OPC_LH, val, base, 0); break; case MO_UL: - if (is_64) { + if (type == TCG_TYPE_I64) { tcg_out_opc_imm(s, OPC_LWU, val, base, 0); break; } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg val, } } -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) +static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, + MemOpIdx oi, TCGType data_type) { - TCGReg addr_reg, data_reg; - MemOpIdx oi; - MemOp opc; -#if defined(CONFIG_SOFTMMU) - tcg_insn_unit *label_ptr[1]; -#else - unsigned a_bits; -#endif + MemOp opc = get_memop(oi); TCGReg base; - data_reg = *args++; - addr_reg = *args++; - oi = *args++; - opc = get_memop(oi); - #if defined(CONFIG_SOFTMMU) + tcg_insn_unit *label_ptr[1]; + base = tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 1); - tcg_out_qemu_ld_direct(s, data_reg, base, opc, is_64); - add_qemu_ldst_label(s, 1, oi, (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), - data_reg, addr_reg, s->code_ptr, label_ptr); + tcg_out_qemu_ld_direct(s, data_reg, base, opc, data_type); + add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #else - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addr_reg, a_bits); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_GUEST_BASE_REG, base); base = TCG_REG_TMP0; } - tcg_out_qemu_ld_direct(s, data_reg, base, opc, is_64); + tcg_out_qemu_ld_direct(s, data_reg, base, opc, data_type); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg val, } } -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) +static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, + MemOpIdx oi, TCGType data_type) { - TCGReg addr_reg, data_reg; - MemOpIdx oi; - MemOp opc; -#if defined(CONFIG_SOFTMMU) - tcg_insn_unit *label_ptr[1]; -#else - unsigned a_bits; -#endif + MemOp opc = get_memop(oi); TCGReg base; - data_reg = *args++; - addr_reg = *args++; - oi = *args++; - opc = get_memop(oi); - #if defined(CONFIG_SOFTMMU) + tcg_insn_unit *label_ptr[1]; + base = tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 0); tcg_out_qemu_st_direct(s, data_reg, base, opc); - add_qemu_ldst_label(s, 0, oi, (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32), - data_reg, addr_reg, s->code_ptr, label_ptr); + add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #else - a_bits = get_alignment_bits(opc); + unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addr_reg, a_bits); } @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, args, false); + tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I32); break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args, true); + tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I64); break; case INDEX_op_qemu_st_i32: - tcg_out_qemu_st(s, args, false); + tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I32); break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args, true); + tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I64); break; case INDEX_op_extrh_i64_i32: -- 2.34.1 We need to set this in TCGLabelQemuLdst, so plumb this all the way through from tcg_out_op. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/s390x/tcg-target.c.inc | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 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 TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, MemOp opc, } static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, - TCGReg data, TCGReg addr, + TCGType type, TCGReg data, TCGReg addr, tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s); label->is_ld = is_ld; label->oi = oi; + label->type = type; label->datalo_reg = data; label->addrlo_reg = addr; label->raddr = tcg_splitwx_to_rx(raddr); @@ -XXX,XX +XXX,XX @@ static void tcg_prepare_user_ldst(TCGContext *s, TCGReg *addr_reg, #endif /* CONFIG_SOFTMMU */ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, - MemOpIdx oi) + MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); #ifdef CONFIG_SOFTMMU @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, tcg_out_qemu_ld_direct(s, opc, data_reg, base_reg, TCG_REG_R2, 0); - add_qemu_ldst_label(s, 1, oi, data_reg, addr_reg, s->code_ptr, label_ptr); + add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #else TCGReg index_reg; tcg_target_long disp; @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, } static void tcg_out_qemu_st(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, - MemOpIdx oi) + MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); #ifdef CONFIG_SOFTMMU @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, tcg_out_qemu_st_direct(s, opc, data_reg, base_reg, TCG_REG_R2, 0); - add_qemu_ldst_label(s, 0, oi, data_reg, addr_reg, s->code_ptr, label_ptr); + add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, + s->code_ptr, label_ptr); #else TCGReg index_reg; tcg_target_long disp; @@ -XXX,XX +XXX,XX @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - /* ??? Technically we can use a non-extending instruction. */ + tcg_out_qemu_ld(s, args[0], args[1], args[2], TCG_TYPE_I32); + break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, args[0], args[1], args[2]); + tcg_out_qemu_ld(s, args[0], args[1], args[2], TCG_TYPE_I64); break; case INDEX_op_qemu_st_i32: + tcg_out_qemu_st(s, args[0], args[1], args[2], TCG_TYPE_I32); + break; case INDEX_op_qemu_st_i64: - tcg_out_qemu_st(s, args[0], args[1], args[2]); + tcg_out_qemu_st(s, args[0], args[1], args[2], TCG_TYPE_I64); break; case INDEX_op_ld16s_i64: -- 2.34.1 Collect the 3 potential parts of the host address into a struct. Reorg tcg_out_qemu_{ld,st}_direct to use it. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/s390x/tcg-target.c.inc | 109 ++++++++++++++++++++----------------- 1 file changed, 60 insertions(+), 49 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 void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest, tcg_out_call_int(s, dest); } +typedef struct { + TCGReg base; + TCGReg index; + int disp; +} HostAddress; + static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg data, - TCGReg base, TCGReg index, int disp) + HostAddress h) { switch (opc & (MO_SSIZE | MO_BSWAP)) { case MO_UB: - tcg_out_insn(s, RXY, LLGC, data, base, index, disp); + tcg_out_insn(s, RXY, LLGC, data, h.base, h.index, h.disp); break; case MO_SB: - tcg_out_insn(s, RXY, LGB, data, base, index, disp); + tcg_out_insn(s, RXY, LGB, data, h.base, h.index, h.disp); break; case MO_UW | MO_BSWAP: /* swapped unsigned halfword load with upper bits zeroed */ - tcg_out_insn(s, RXY, LRVH, data, base, index, disp); + tcg_out_insn(s, RXY, LRVH, data, h.base, h.index, h.disp); tcg_out_ext16u(s, data, data); break; case MO_UW: - tcg_out_insn(s, RXY, LLGH, data, base, index, disp); + tcg_out_insn(s, RXY, LLGH, data, h.base, h.index, h.disp); break; case MO_SW | MO_BSWAP: /* swapped sign-extended halfword load */ - tcg_out_insn(s, RXY, LRVH, data, base, index, disp); + tcg_out_insn(s, RXY, LRVH, data, h.base, h.index, h.disp); tcg_out_ext16s(s, TCG_TYPE_REG, data, data); break; case MO_SW: - tcg_out_insn(s, RXY, LGH, data, base, index, disp); + tcg_out_insn(s, RXY, LGH, data, h.base, h.index, h.disp); break; case MO_UL | MO_BSWAP: /* swapped unsigned int load with upper bits zeroed */ - tcg_out_insn(s, RXY, LRV, data, base, index, disp); + tcg_out_insn(s, RXY, LRV, data, h.base, h.index, h.disp); tcg_out_ext32u(s, data, data); break; case MO_UL: - tcg_out_insn(s, RXY, LLGF, data, base, index, disp); + tcg_out_insn(s, RXY, LLGF, data, h.base, h.index, h.disp); break; case MO_SL | MO_BSWAP: /* swapped sign-extended int load */ - tcg_out_insn(s, RXY, LRV, data, base, index, disp); + tcg_out_insn(s, RXY, LRV, data, h.base, h.index, h.disp); tcg_out_ext32s(s, data, data); break; case MO_SL: - tcg_out_insn(s, RXY, LGF, data, base, index, disp); + tcg_out_insn(s, RXY, LGF, data, h.base, h.index, h.disp); break; case MO_UQ | MO_BSWAP: - tcg_out_insn(s, RXY, LRVG, data, base, index, disp); + tcg_out_insn(s, RXY, LRVG, data, h.base, h.index, h.disp); break; case MO_UQ: - tcg_out_insn(s, RXY, LG, data, base, index, disp); + tcg_out_insn(s, RXY, LG, data, h.base, h.index, h.disp); break; default: @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg data, } static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg data, - TCGReg base, TCGReg index, int disp) + HostAddress h) { switch (opc & (MO_SIZE | MO_BSWAP)) { case MO_UB: - if (disp >= 0 && disp < 0x1000) { - tcg_out_insn(s, RX, STC, data, base, index, disp); + if (h.disp >= 0 && h.disp < 0x1000) { + tcg_out_insn(s, RX, STC, data, h.base, h.index, h.disp); } else { - tcg_out_insn(s, RXY, STCY, data, base, index, disp); + tcg_out_insn(s, RXY, STCY, data, h.base, h.index, h.disp); } break; case MO_UW | MO_BSWAP: - tcg_out_insn(s, RXY, STRVH, data, base, index, disp); + tcg_out_insn(s, RXY, STRVH, data, h.base, h.index, h.disp); break; case MO_UW: - if (disp >= 0 && disp < 0x1000) { - tcg_out_insn(s, RX, STH, data, base, index, disp); + if (h.disp >= 0 && h.disp < 0x1000) { + tcg_out_insn(s, RX, STH, data, h.base, h.index, h.disp); } else { - tcg_out_insn(s, RXY, STHY, data, base, index, disp); + tcg_out_insn(s, RXY, STHY, data, h.base, h.index, h.disp); } break; case MO_UL | MO_BSWAP: - tcg_out_insn(s, RXY, STRV, data, base, index, disp); + tcg_out_insn(s, RXY, STRV, data, h.base, h.index, h.disp); break; case MO_UL: - if (disp >= 0 && disp < 0x1000) { - tcg_out_insn(s, RX, ST, data, base, index, disp); + if (h.disp >= 0 && h.disp < 0x1000) { + tcg_out_insn(s, RX, ST, data, h.base, h.index, h.disp); } else { - tcg_out_insn(s, RXY, STY, data, base, index, disp); + tcg_out_insn(s, RXY, STY, data, h.base, h.index, h.disp); } break; case MO_UQ | MO_BSWAP: - tcg_out_insn(s, RXY, STRVG, data, base, index, disp); + tcg_out_insn(s, RXY, STRVG, data, h.base, h.index, h.disp); break; case MO_UQ: - tcg_out_insn(s, RXY, STG, data, base, index, disp); + tcg_out_insn(s, RXY, STG, data, h.base, h.index, h.disp); break; default: @@ -XXX,XX +XXX,XX @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) return tcg_out_fail_alignment(s, l); } -static void tcg_prepare_user_ldst(TCGContext *s, TCGReg *addr_reg, - TCGReg *index_reg, tcg_target_long *disp) +static HostAddress tcg_prepare_user_ldst(TCGContext *s, TCGReg addr_reg) { + TCGReg index; + int disp; + if (TARGET_LONG_BITS == 32) { - tcg_out_ext32u(s, TCG_TMP0, *addr_reg); - *addr_reg = TCG_TMP0; + tcg_out_ext32u(s, TCG_TMP0, addr_reg); + addr_reg = TCG_TMP0; } if (guest_base < 0x80000) { - *index_reg = TCG_REG_NONE; - *disp = guest_base; + index = TCG_REG_NONE; + disp = guest_base; } else { - *index_reg = TCG_GUEST_BASE_REG; - *disp = 0; + index = TCG_GUEST_BASE_REG; + disp = 0; } + return (HostAddress){ .base = addr_reg, .index = index, .disp = disp }; } #endif /* CONFIG_SOFTMMU */ @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); + HostAddress h; + #ifdef CONFIG_SOFTMMU unsigned mem_index = get_mmuidx(oi); tcg_insn_unit *label_ptr; - TCGReg base_reg; - base_reg = tcg_out_tlb_read(s, addr_reg, opc, mem_index, 1); + h.base = tcg_out_tlb_read(s, addr_reg, opc, mem_index, 1); + h.index = TCG_REG_R2; + h.disp = 0; tcg_out16(s, RI_BRC | (S390_CC_NE << 4)); label_ptr = s->code_ptr; s->code_ptr += 1; - tcg_out_qemu_ld_direct(s, opc, data_reg, base_reg, TCG_REG_R2, 0); + tcg_out_qemu_ld_direct(s, opc, data_reg, h); add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg, s->code_ptr, label_ptr); #else - TCGReg index_reg; - tcg_target_long disp; unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, true, addr_reg, a_bits); } - tcg_prepare_user_ldst(s, &addr_reg, &index_reg, &disp); - tcg_out_qemu_ld_direct(s, opc, data_reg, addr_reg, index_reg, disp); + h = tcg_prepare_user_ldst(s, addr_reg); + tcg_out_qemu_ld_direct(s, opc, data_reg, h); #endif } @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, MemOpIdx oi, TCGType data_type) { MemOp opc = get_memop(oi); + HostAddress h; + #ifdef CONFIG_SOFTMMU unsigned mem_index = get_mmuidx(oi); tcg_insn_unit *label_ptr; - TCGReg base_reg; - base_reg = tcg_out_tlb_read(s, addr_reg, opc, mem_index, 0); + h.base = tcg_out_tlb_read(s, addr_reg, opc, mem_index, 0); + h.index = TCG_REG_R2; + h.disp = 0; tcg_out16(s, RI_BRC | (S390_CC_NE << 4)); label_ptr = s->code_ptr; s->code_ptr += 1; - tcg_out_qemu_st_direct(s, opc, data_reg, base_reg, TCG_REG_R2, 0); + tcg_out_qemu_st_direct(s, opc, data_reg, h); add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg, s->code_ptr, label_ptr); #else - TCGReg index_reg; - tcg_target_long disp; unsigned a_bits = get_alignment_bits(opc); if (a_bits) { tcg_out_test_alignment(s, false, addr_reg, a_bits); } - tcg_prepare_user_ldst(s, &addr_reg, &index_reg, &disp); - tcg_out_qemu_st_direct(s, opc, data_reg, addr_reg, index_reg, disp); + h = tcg_prepare_user_ldst(s, addr_reg); + tcg_out_qemu_st_direct(s, opc, data_reg, h); #endif } -- 2.34.1 In tcg_canonicalize_memop, we remove MO_SIGN from MO_32 operations with TCG_TYPE_I32. Thus this is never set. We already have an identical test just above which does not include is_64 Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/sparc64/tcg-target.c.inc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_O2, oi); /* We let the helper sign-extend SB and SW, but leave SL for here. */ - if (is_64 && (memop & MO_SSIZE) == MO_SL) { + if ((memop & MO_SSIZE) == MO_SL) { tcg_out_ext32s(s, data, TCG_REG_O0); } else { tcg_out_mov(s, TCG_TYPE_REG, data, TCG_REG_O0); -- 2.34.1 We need to set this in TCGLabelQemuLdst, so plumb this all the way through from tcg_out_op. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/sparc64/tcg-target.c.inc | 6 +++--- 1 file changed, 3 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 const int qemu_st_opc[(MO_SIZE | MO_BSWAP) + 1] = { }; static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, - MemOpIdx oi, bool is_64) + MemOpIdx oi, TCGType data_type) { MemOp memop = get_memop(oi); tcg_insn_unit *label_ptr; @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_qemu_ld_i32: - tcg_out_qemu_ld(s, a0, a1, a2, false); + tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I32); break; case INDEX_op_qemu_ld_i64: - tcg_out_qemu_ld(s, a0, a1, a2, true); + tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I64); break; case INDEX_op_qemu_st_i32: tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I32); -- 2.34.1 Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/tcg.c | 13 +++++++++++++ tcg/tcg-ldst.c.inc | 14 -------------- 2 files changed, 13 insertions(+), 14 deletions(-) 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 @@ typedef struct QEMU_PACKED { DebugFrameFDEHeader fde; } DebugFrameHeader; +typedef struct TCGLabelQemuLdst { + bool is_ld; /* qemu_ld: true, qemu_st: false */ + MemOpIdx oi; + TCGType type; /* result type of a load */ + TCGReg addrlo_reg; /* reg index for low word of guest virtual addr */ + TCGReg addrhi_reg; /* reg index for high word of guest virtual addr */ + TCGReg datalo_reg; /* reg index for low word to be loaded or stored */ + TCGReg datahi_reg; /* reg index for high word to be loaded or stored */ + const tcg_insn_unit *raddr; /* addr of the next IR of qemu_ld/st IR */ + tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */ + QSIMPLEQ_ENTRY(TCGLabelQemuLdst) next; +} TCGLabelQemuLdst; + static void tcg_register_jit_int(const void *buf, size_t size, const void *debug_frame, size_t debug_frame_size) diff --git a/tcg/tcg-ldst.c.inc b/tcg/tcg-ldst.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-ldst.c.inc +++ b/tcg/tcg-ldst.c.inc @@ -XXX,XX +XXX,XX @@ * THE SOFTWARE. */ -typedef struct TCGLabelQemuLdst { - bool is_ld; /* qemu_ld: true, qemu_st: false */ - MemOpIdx oi; - TCGType type; /* result type of a load */ - TCGReg addrlo_reg; /* reg index for low word of guest virtual addr */ - TCGReg addrhi_reg; /* reg index for high word of guest virtual addr */ - TCGReg datalo_reg; /* reg index for low word to be loaded or stored */ - TCGReg datahi_reg; /* reg index for high word to be loaded or stored */ - const tcg_insn_unit *raddr; /* addr of the next IR of qemu_ld/st IR */ - tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */ - QSIMPLEQ_ENTRY(TCGLabelQemuLdst) next; -} TCGLabelQemuLdst; - - /* * Generate TB finalization at the end of block */ -- 2.34.1 An inline function is safer than a macro, and REG_P was rather too generic. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/tcg-internal.h | 4 ---- tcg/tcg.c | 16 +++++++++++++--- 2 files changed, 13 insertions(+), 7 deletions(-) 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 @@ typedef struct TCGCallArgumentLoc { unsigned tmp_subindex : 2; } TCGCallArgumentLoc; -/* Avoid "unsigned < 0 is always false" Werror, when iarg_regs is empty. */ -#define REG_P(L) \ - ((int)(L)->arg_slot < (int)ARRAY_SIZE(tcg_target_call_iarg_regs)) - typedef struct TCGHelperInfo { void *func; const char *name; 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 @@ static void init_ffi_layouts(void) } #endif /* CONFIG_TCG_INTERPRETER */ +static inline bool arg_slot_reg_p(unsigned arg_slot) +{ + /* + * Split the sizeof away from the comparison to avoid Werror from + * "unsigned < 0 is always false", when iarg_regs is empty. + */ + unsigned nreg = ARRAY_SIZE(tcg_target_call_iarg_regs); + return arg_slot < nreg; +} + typedef struct TCGCumulativeArgs { int arg_idx; /* tcg_gen_callN args[] */ int info_in_idx; /* TCGHelperInfo in[] */ @@ -XXX,XX +XXX,XX @@ liveness_pass_1(TCGContext *s) case TCG_CALL_ARG_NORMAL: case TCG_CALL_ARG_EXTEND_U: case TCG_CALL_ARG_EXTEND_S: - if (REG_P(loc)) { + if (arg_slot_reg_p(loc->arg_slot)) { *la_temp_pref(ts) = 0; break; } @@ -XXX,XX +XXX,XX @@ liveness_pass_1(TCGContext *s) case TCG_CALL_ARG_NORMAL: case TCG_CALL_ARG_EXTEND_U: case TCG_CALL_ARG_EXTEND_S: - if (REG_P(loc)) { + if (arg_slot_reg_p(loc->arg_slot)) { tcg_regset_set_reg(*la_temp_pref(ts), tcg_target_call_iarg_regs[loc->arg_slot]); } @@ -XXX,XX +XXX,XX @@ static void load_arg_stk(TCGContext *s, int stk_slot, TCGTemp *ts, static void load_arg_normal(TCGContext *s, const TCGCallArgumentLoc *l, TCGTemp *ts, TCGRegSet *allocated_regs) { - if (REG_P(l)) { + if (arg_slot_reg_p(l->arg_slot)) { TCGReg reg = tcg_target_call_iarg_regs[l->arg_slot]; load_arg_reg(s, reg, ts, *allocated_regs); tcg_regset_set_reg(*allocated_regs, reg); -- 2.34.1 Unify all computation of argument stack offset in one function. This requires that we adjust ref_slot to be in the same units, by adding max_reg_slots during init_call_layout. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/tcg.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) 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 @@ static inline bool arg_slot_reg_p(unsigned arg_slot) return arg_slot < nreg; } +static inline int arg_slot_stk_ofs(unsigned arg_slot) +{ + unsigned max = TCG_STATIC_CALL_ARGS_SIZE / sizeof(tcg_target_long); + unsigned stk_slot = arg_slot - ARRAY_SIZE(tcg_target_call_iarg_regs); + + tcg_debug_assert(stk_slot < max); + return TCG_TARGET_CALL_STACK_OFFSET + stk_slot * sizeof(tcg_target_long); +} + typedef struct TCGCumulativeArgs { int arg_idx; /* tcg_gen_callN args[] */ int info_in_idx; /* TCGHelperInfo in[] */ @@ -XXX,XX +XXX,XX @@ static void init_call_layout(TCGHelperInfo *info) } } assert(ref_base + cum.ref_slot <= max_stk_slots); + ref_base += max_reg_slots; if (ref_base != 0) { for (int i = cum.info_in_idx - 1; i >= 0; --i) { @@ -XXX,XX +XXX,XX @@ static void load_arg_reg(TCGContext *s, TCGReg reg, TCGTemp *ts, } } -static void load_arg_stk(TCGContext *s, int stk_slot, TCGTemp *ts, +static void load_arg_stk(TCGContext *s, unsigned arg_slot, TCGTemp *ts, TCGRegSet allocated_regs) { /* @@ -XXX,XX +XXX,XX @@ static void load_arg_stk(TCGContext *s, int stk_slot, TCGTemp *ts, */ temp_load(s, ts, tcg_target_available_regs[ts->type], allocated_regs, 0); tcg_out_st(s, ts->type, ts->reg, TCG_REG_CALL_STACK, - TCG_TARGET_CALL_STACK_OFFSET + - stk_slot * sizeof(tcg_target_long)); + arg_slot_stk_ofs(arg_slot)); } static void load_arg_normal(TCGContext *s, const TCGCallArgumentLoc *l, @@ -XXX,XX +XXX,XX @@ static void load_arg_normal(TCGContext *s, const TCGCallArgumentLoc *l, load_arg_reg(s, reg, ts, *allocated_regs); tcg_regset_set_reg(*allocated_regs, reg); } else { - load_arg_stk(s, l->arg_slot - ARRAY_SIZE(tcg_target_call_iarg_regs), - ts, *allocated_regs); + load_arg_stk(s, l->arg_slot, ts, *allocated_regs); } } -static void load_arg_ref(TCGContext *s, int arg_slot, TCGReg ref_base, +static void load_arg_ref(TCGContext *s, unsigned arg_slot, TCGReg ref_base, intptr_t ref_off, TCGRegSet *allocated_regs) { TCGReg reg; - int stk_slot = arg_slot - ARRAY_SIZE(tcg_target_call_iarg_regs); - if (stk_slot < 0) { + if (arg_slot_reg_p(arg_slot)) { reg = tcg_target_call_iarg_regs[arg_slot]; tcg_reg_free(s, reg, *allocated_regs); tcg_out_addi_ptr(s, reg, ref_base, ref_off); @@ -XXX,XX +XXX,XX @@ static void load_arg_ref(TCGContext *s, int arg_slot, TCGReg ref_base, *allocated_regs, 0, false); tcg_out_addi_ptr(s, reg, ref_base, ref_off); tcg_out_st(s, TCG_TYPE_PTR, reg, TCG_REG_CALL_STACK, - TCG_TARGET_CALL_STACK_OFFSET - + stk_slot * sizeof(tcg_target_long)); + arg_slot_stk_ofs(arg_slot)); } } @@ -XXX,XX +XXX,XX @@ static void tcg_reg_alloc_call(TCGContext *s, TCGOp *op) case TCG_CALL_ARG_BY_REF: load_arg_stk(s, loc->ref_slot, ts, allocated_regs); load_arg_ref(s, loc->arg_slot, TCG_REG_CALL_STACK, - TCG_TARGET_CALL_STACK_OFFSET - + loc->ref_slot * sizeof(tcg_target_long), + arg_slot_stk_ofs(loc->ref_slot), &allocated_regs); break; case TCG_CALL_ARG_BY_REF_N: -- 2.34.1 While the old type was correct in the ideal sense, some ABIs require the argument to be zero-extended. Using uint32_t for all such values is a decent compromise. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/tcg/tcg-ldst.h | 10 +++++++--- accel/tcg/cputlb.c | 6 +++--- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/tcg/tcg-ldst.h b/include/tcg/tcg-ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg-ldst.h +++ b/include/tcg/tcg-ldst.h @@ -XXX,XX +XXX,XX @@ tcg_target_ulong helper_be_ldsw_mmu(CPUArchState *env, target_ulong addr, tcg_target_ulong helper_be_ldsl_mmu(CPUArchState *env, target_ulong addr, MemOpIdx oi, uintptr_t retaddr); -void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val, +/* + * Value extended to at least uint32_t, so that some ABIs do not require + * zero-extension from uint8_t or uint16_t. + */ +void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr); -void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, +void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr); void helper_le_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr); void helper_le_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, MemOpIdx oi, uintptr_t retaddr); -void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, +void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr); void helper_be_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr); 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 @@ full_stb_mmu(CPUArchState *env, target_ulong addr, uint64_t val, store_helper(env, addr, val, oi, retaddr, MO_UB); } -void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val, +void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr) { full_stb_mmu(env, addr, val, oi, retaddr); @@ -XXX,XX +XXX,XX @@ static void full_le_stw_mmu(CPUArchState *env, target_ulong addr, uint64_t val, store_helper(env, addr, val, oi, retaddr, MO_LEUW); } -void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, +void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr) { full_le_stw_mmu(env, addr, val, oi, retaddr); @@ -XXX,XX +XXX,XX @@ static void full_be_stw_mmu(CPUArchState *env, target_ulong addr, uint64_t val, store_helper(env, addr, val, oi, retaddr, MO_BEUW); } -void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, +void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr) { full_be_stw_mmu(env, addr, val, oi, retaddr); -- 2.34.1