diff options
60 files changed, 1070 insertions, 2066 deletions
diff --git a/.gitlab-ci.d/container-template.yml b/.gitlab-ci.d/container-template.yml index 519b8a9..9ac4a0e 100644 --- a/.gitlab-ci.d/container-template.yml +++ b/.gitlab-ci.d/container-template.yml @@ -3,13 +3,13 @@ image: docker:stable stage: containers services: - - docker:dind + - docker:stable-dind before_script: - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/qemu/$NAME:latest" - apk add python3 - - docker info - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" + - until docker info; do sleep 1; done script: - echo "TAG:$TAG" - echo "COMMON_TAG:$COMMON_TAG" diff --git a/.gitlab-ci.d/opensbi.yml b/.gitlab-ci.d/opensbi.yml index 9a65146..2e9d517 100644 --- a/.gitlab-ci.d/opensbi.yml +++ b/.gitlab-ci.d/opensbi.yml @@ -48,11 +48,9 @@ docker-opensbi: variables: GIT_DEPTH: 3 IMAGE_TAG: $CI_REGISTRY_IMAGE:opensbi-cross-build - # We don't use TLS - DOCKER_HOST: tcp://docker:2375 - DOCKER_TLS_CERTDIR: "" before_script: - docker login -u $CI_REGISTRY_USER -p $CI_REGISTRY_PASSWORD $CI_REGISTRY + - until docker info; do sleep 1; done script: - docker pull $IMAGE_TAG || true - docker build --cache-from $IMAGE_TAG --tag $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA diff --git a/.gitlab-ci.d/qemu-project.yml b/.gitlab-ci.d/qemu-project.yml index a7ed447..4d914c4 100644 --- a/.gitlab-ci.d/qemu-project.yml +++ b/.gitlab-ci.d/qemu-project.yml @@ -1,6 +1,13 @@ # This file contains the set of jobs run by the QEMU project: # https://gitlab.com/qemu-project/qemu/-/pipelines +variables: + RUNNER_TAG: "" + +default: + tags: + - $RUNNER_TAG + include: - local: '/.gitlab-ci.d/base.yml' - local: '/.gitlab-ci.d/stages.yml' diff --git a/MAINTAINERS b/MAINTAINERS index 6addabd..1c93ab0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -157,6 +157,9 @@ F: include/exec/helper*.h F: include/sysemu/cpus.h F: include/sysemu/tcg.h F: include/hw/core/tcg-cpu-ops.h +F: host/include/*/host/cpuinfo.h +F: util/cpuinfo-*.c +F: include/tcg/ FPU emulation M: Aurelien Jarno <aurelien@aurel32.net> diff --git a/accel/tcg/atomic_common.c.inc b/accel/tcg/atomic_common.c.inc index fe0eea0..ee222fd 100644 --- a/accel/tcg/atomic_common.c.inc +++ b/accel/tcg/atomic_common.c.inc @@ -19,20 +19,6 @@ static void atomic_trace_rmw_post(CPUArchState *env, uint64_t addr, qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_RW); } -#if HAVE_ATOMIC128 -static void atomic_trace_ld_post(CPUArchState *env, uint64_t addr, - MemOpIdx oi) -{ - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); -} - -static void atomic_trace_st_post(CPUArchState *env, uint64_t addr, - MemOpIdx oi) -{ - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); -} -#endif - /* * Atomic helpers callable from TCG. * These have a common interface and all defer to cpu_atomic_* @@ -62,36 +48,16 @@ CMPXCHG_HELPER(cmpxchgo_le, Int128) #undef CMPXCHG_HELPER -Int128 HELPER(nonatomic_cmpxchgo_be)(CPUArchState *env, uint64_t addr, - Int128 cmpv, Int128 newv, uint32_t oi) -{ -#if TCG_TARGET_REG_BITS == 32 - uintptr_t ra = GETPC(); - Int128 oldv; - - oldv = cpu_ld16_be_mmu(env, addr, oi, ra); - if (int128_eq(oldv, cmpv)) { - cpu_st16_be_mmu(env, addr, newv, oi, ra); - } else { - /* Even with comparison failure, still need a write cycle. */ - probe_write(env, addr, 16, get_mmuidx(oi), ra); - } - return oldv; -#else - g_assert_not_reached(); -#endif -} - -Int128 HELPER(nonatomic_cmpxchgo_le)(CPUArchState *env, uint64_t addr, - Int128 cmpv, Int128 newv, uint32_t oi) +Int128 HELPER(nonatomic_cmpxchgo)(CPUArchState *env, uint64_t addr, + Int128 cmpv, Int128 newv, uint32_t oi) { #if TCG_TARGET_REG_BITS == 32 uintptr_t ra = GETPC(); Int128 oldv; - oldv = cpu_ld16_le_mmu(env, addr, oi, ra); + oldv = cpu_ld16_mmu(env, addr, oi, ra); if (int128_eq(oldv, cmpv)) { - cpu_st16_le_mmu(env, addr, newv, oi, ra); + cpu_st16_mmu(env, addr, newv, oi, ra); } else { /* Even with comparison failure, still need a write cycle. */ probe_write(env, addr, 16, get_mmuidx(oi), ra); diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h index 404a530..e312acd 100644 --- a/accel/tcg/atomic_template.h +++ b/accel/tcg/atomic_template.h @@ -73,8 +73,7 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, ABI_TYPE cmpv, ABI_TYPE newv, MemOpIdx oi, uintptr_t retaddr) { - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_READ | PAGE_WRITE, retaddr); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); DATA_TYPE ret; #if DATA_SIZE == 16 @@ -87,38 +86,11 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, return ret; } -#if DATA_SIZE >= 16 -#if HAVE_ATOMIC128 -ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr, - MemOpIdx oi, uintptr_t retaddr) -{ - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_READ, retaddr); - DATA_TYPE val; - - val = atomic16_read(haddr); - ATOMIC_MMU_CLEANUP; - atomic_trace_ld_post(env, addr, oi); - return val; -} - -void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val, - MemOpIdx oi, uintptr_t retaddr) -{ - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_WRITE, retaddr); - - atomic16_set(haddr, val); - ATOMIC_MMU_CLEANUP; - atomic_trace_st_post(env, addr, oi); -} -#endif -#else +#if DATA_SIZE < 16 ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) { - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_READ | PAGE_WRITE, retaddr); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); DATA_TYPE ret; ret = qatomic_xchg__nocheck(haddr, val); @@ -131,9 +103,8 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \ { \ - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ - PAGE_READ | PAGE_WRITE, retaddr); \ - DATA_TYPE ret; \ + DATA_TYPE *haddr, ret; \ + haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \ ret = qatomic_##X(haddr, val); \ ATOMIC_MMU_CLEANUP; \ atomic_trace_rmw_post(env, addr, oi); \ @@ -163,9 +134,8 @@ GEN_ATOMIC_HELPER(xor_fetch) ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \ { \ - XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ - PAGE_READ | PAGE_WRITE, retaddr); \ - XDATA_TYPE cmp, old, new, val = xval; \ + XDATA_TYPE *haddr, cmp, old, new, val = xval; \ + haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \ smp_mb(); \ cmp = qatomic_read__nocheck(haddr); \ do { \ @@ -188,7 +158,7 @@ GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) #undef GEN_ATOMIC_HELPER_FN -#endif /* DATA SIZE >= 16 */ +#endif /* DATA SIZE < 16 */ #undef END @@ -206,8 +176,7 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, ABI_TYPE cmpv, ABI_TYPE newv, MemOpIdx oi, uintptr_t retaddr) { - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_READ | PAGE_WRITE, retaddr); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); DATA_TYPE ret; #if DATA_SIZE == 16 @@ -220,39 +189,11 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, return BSWAP(ret); } -#if DATA_SIZE >= 16 -#if HAVE_ATOMIC128 -ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr, - MemOpIdx oi, uintptr_t retaddr) -{ - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_READ, retaddr); - DATA_TYPE val; - - val = atomic16_read(haddr); - ATOMIC_MMU_CLEANUP; - atomic_trace_ld_post(env, addr, oi); - return BSWAP(val); -} - -void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val, - MemOpIdx oi, uintptr_t retaddr) -{ - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_WRITE, retaddr); - - val = BSWAP(val); - atomic16_set(haddr, val); - ATOMIC_MMU_CLEANUP; - atomic_trace_st_post(env, addr, oi); -} -#endif -#else +#if DATA_SIZE < 16 ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) { - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, - PAGE_READ | PAGE_WRITE, retaddr); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); ABI_TYPE ret; ret = qatomic_xchg__nocheck(haddr, BSWAP(val)); @@ -265,9 +206,8 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \ { \ - DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ - PAGE_READ | PAGE_WRITE, retaddr); \ - DATA_TYPE ret; \ + DATA_TYPE *haddr, ret; \ + haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \ ret = qatomic_##X(haddr, BSWAP(val)); \ ATOMIC_MMU_CLEANUP; \ atomic_trace_rmw_post(env, addr, oi); \ @@ -294,9 +234,8 @@ GEN_ATOMIC_HELPER(xor_fetch) ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \ { \ - XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ - PAGE_READ | PAGE_WRITE, retaddr); \ - XDATA_TYPE ldo, ldn, old, new, val = xval; \ + XDATA_TYPE *haddr, ldo, ldn, old, new, val = xval; \ + haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \ smp_mb(); \ ldn = qatomic_read__nocheck(haddr); \ do { \ @@ -326,7 +265,7 @@ GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new) #undef ADD #undef GEN_ATOMIC_HELPER_FN -#endif /* DATA_SIZE >= 16 */ +#endif /* DATA_SIZE < 16 */ #undef END #endif /* DATA_SIZE > 1 */ diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index bc0e1c3..0e74196 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -307,7 +307,6 @@ static void log_cpu_exec(target_ulong pc, CPUState *cpu, cpu->cpu_index, tb->tc.ptr, tb->cs_base, pc, tb->flags, tb->cflags, lookup_symbol(pc)); -#if defined(DEBUG_DISAS) if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) { FILE *logfile = qemu_log_trylock(); if (logfile) { @@ -323,7 +322,6 @@ static void log_cpu_exec(target_ulong pc, CPUState *cpu, qemu_log_unlock(logfile); } } -#endif /* DEBUG_DISAS */ } } diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index ae0fbcd..90c72c9 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -1896,12 +1896,9 @@ static bool mmu_lookup(CPUArchState *env, target_ulong addr, MemOpIdx oi, /* * Probe for an atomic operation. Do not allow unaligned operations, * or io operations to proceed. Return the host address. - * - * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE. */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, - MemOpIdx oi, int size, int prot, - uintptr_t retaddr) + MemOpIdx oi, int size, uintptr_t retaddr) { uintptr_t mmu_idx = get_mmuidx(oi); MemOp mop = get_memop(oi); @@ -1937,53 +1934,36 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, tlbe = tlb_entry(env, mmu_idx, addr); /* Check TLB entry and enforce page permissions. */ - if (prot & PAGE_WRITE) { - tlb_addr = tlb_addr_write(tlbe); - if (!tlb_hit(tlb_addr, addr)) { - if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_STORE, - addr & TARGET_PAGE_MASK)) { - tlb_fill(env_cpu(env), addr, size, - MMU_DATA_STORE, mmu_idx, retaddr); - index = tlb_index(env, mmu_idx, addr); - tlbe = tlb_entry(env, mmu_idx, addr); - } - tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK; + tlb_addr = tlb_addr_write(tlbe); + if (!tlb_hit(tlb_addr, addr)) { + if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_STORE, + addr & TARGET_PAGE_MASK)) { + tlb_fill(env_cpu(env), addr, size, + MMU_DATA_STORE, mmu_idx, retaddr); + index = tlb_index(env, mmu_idx, addr); + tlbe = tlb_entry(env, mmu_idx, addr); } + tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK; + } - if (prot & PAGE_READ) { - /* - * Let the guest notice RMW on a write-only page. - * We have just verified that the page is writable. - * Subpage lookups may have left TLB_INVALID_MASK set, - * but addr_read will only be -1 if PAGE_READ was unset. - */ - if (unlikely(tlbe->addr_read == -1)) { - tlb_fill(env_cpu(env), addr, size, - MMU_DATA_LOAD, mmu_idx, retaddr); - /* - * Since we don't support reads and writes to different - * addresses, and we do have the proper page loaded for - * write, this shouldn't ever return. But just in case, - * handle via stop-the-world. - */ - goto stop_the_world; - } - /* Collect TLB_WATCHPOINT for read. */ - tlb_addr |= tlbe->addr_read; - } - } else /* if (prot & PAGE_READ) */ { - tlb_addr = tlbe->addr_read; - if (!tlb_hit(tlb_addr, addr)) { - if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_LOAD, - addr & TARGET_PAGE_MASK)) { - tlb_fill(env_cpu(env), addr, size, - MMU_DATA_LOAD, mmu_idx, retaddr); - index = tlb_index(env, mmu_idx, addr); - tlbe = tlb_entry(env, mmu_idx, addr); - } - tlb_addr = tlbe->addr_read & ~TLB_INVALID_MASK; - } + /* + * Let the guest notice RMW on a write-only page. + * We have just verified that the page is writable. + * Subpage lookups may have left TLB_INVALID_MASK set, + * but addr_read will only be -1 if PAGE_READ was unset. + */ + if (unlikely(tlbe->addr_read == -1)) { + tlb_fill(env_cpu(env), addr, size, MMU_DATA_LOAD, mmu_idx, retaddr); + /* + * Since we don't support reads and writes to different + * addresses, and we do have the proper page loaded for + * write, this shouldn't ever return. But just in case, + * handle via stop-the-world. + */ + goto stop_the_world; } + /* Collect TLB_WATCHPOINT for read. */ + tlb_addr |= tlbe->addr_read; /* Notice an IO access or a needs-MMU-lookup access */ if (unlikely(tlb_addr & (TLB_MMIO | TLB_DISCARD_WRITE))) { @@ -2000,11 +1980,8 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, } if (unlikely(tlb_addr & TLB_WATCHPOINT)) { - QEMU_BUILD_BUG_ON(PAGE_READ != BP_MEM_READ); - QEMU_BUILD_BUG_ON(PAGE_WRITE != BP_MEM_WRITE); - /* therefore prot == watchpoint bits */ - cpu_check_watchpoint(env_cpu(env), addr, size, - full->attrs, prot, retaddr); + cpu_check_watchpoint(env_cpu(env), addr, size, full->attrs, + BP_MEM_READ | BP_MEM_WRITE, retaddr); } return hostaddr; @@ -2575,89 +2552,45 @@ uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra) return ret; } -uint16_t cpu_ldw_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) -{ - uint16_t ret; - - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_BEUW); - ret = do_ld2_mmu(env, addr, oi, ra, MMU_DATA_LOAD); - plugin_load_cb(env, addr, oi); - return ret; -} - -uint32_t cpu_ldl_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) -{ - uint32_t ret; - - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_BEUL); - ret = do_ld4_mmu(env, addr, oi, ra, MMU_DATA_LOAD); - plugin_load_cb(env, addr, oi); - return ret; -} - -uint64_t cpu_ldq_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) -{ - uint64_t ret; - - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_BEUQ); - ret = do_ld8_mmu(env, addr, oi, ra, MMU_DATA_LOAD); - plugin_load_cb(env, addr, oi); - return ret; -} - -uint16_t cpu_ldw_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { uint16_t ret; - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_LEUW); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16); ret = do_ld2_mmu(env, addr, oi, ra, MMU_DATA_LOAD); plugin_load_cb(env, addr, oi); return ret; } -uint32_t cpu_ldl_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { uint32_t ret; - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_LEUL); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32); ret = do_ld4_mmu(env, addr, oi, ra, MMU_DATA_LOAD); plugin_load_cb(env, addr, oi); return ret; } -uint64_t cpu_ldq_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { uint64_t ret; - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_LEUQ); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64); ret = do_ld8_mmu(env, addr, oi, ra, MMU_DATA_LOAD); plugin_load_cb(env, addr, oi); return ret; } -Int128 cpu_ld16_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) -{ - Int128 ret; - - tcg_debug_assert((get_memop(oi) & (MO_BSWAP|MO_SIZE)) == (MO_BE|MO_128)); - ret = do_ld16_mmu(env, addr, oi, ra); - plugin_load_cb(env, addr, oi); - return ret; -} - -Int128 cpu_ld16_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { Int128 ret; - tcg_debug_assert((get_memop(oi) & (MO_BSWAP|MO_SIZE)) == (MO_LE|MO_128)); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128); ret = do_ld16_mmu(env, addr, oi, ra); plugin_load_cb(env, addr, oi); return ret; @@ -2779,7 +2712,7 @@ static uint64_t do_st16_leN(CPUArchState *env, MMULookupPageData *p, case MO_ATOM_WITHIN16_PAIR: /* Since size > 8, this is the half that must be atomic. */ - if (!HAVE_al16) { + if (!HAVE_ATOMIC128_RW) { cpu_loop_exit_atomic(env_cpu(env), ra); } return store_whole_le16(p->haddr, p->size, val_le); @@ -3045,66 +2978,34 @@ void cpu_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val, plugin_store_cb(env, addr, oi); } -void cpu_stw_be_mmu(CPUArchState *env, target_ulong addr, uint16_t val, - MemOpIdx oi, uintptr_t retaddr) -{ - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_BEUW); - do_st2_mmu(env, addr, val, oi, retaddr); - plugin_store_cb(env, addr, oi); -} - -void cpu_stl_be_mmu(CPUArchState *env, target_ulong addr, uint32_t val, - MemOpIdx oi, uintptr_t retaddr) -{ - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_BEUL); - do_st4_mmu(env, addr, val, oi, retaddr); - plugin_store_cb(env, addr, oi); -} - -void cpu_stq_be_mmu(CPUArchState *env, target_ulong addr, uint64_t val, - MemOpIdx oi, uintptr_t retaddr) -{ - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_BEUQ); - do_st8_mmu(env, addr, val, oi, retaddr); - plugin_store_cb(env, addr, oi); -} - -void cpu_stw_le_mmu(CPUArchState *env, target_ulong addr, uint16_t val, - MemOpIdx oi, uintptr_t retaddr) +void cpu_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, + MemOpIdx oi, uintptr_t retaddr) { - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_LEUW); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16); do_st2_mmu(env, addr, val, oi, retaddr); plugin_store_cb(env, addr, oi); } -void cpu_stl_le_mmu(CPUArchState *env, target_ulong addr, uint32_t val, +void cpu_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, MemOpIdx oi, uintptr_t retaddr) { - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_LEUL); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32); do_st4_mmu(env, addr, val, oi, retaddr); plugin_store_cb(env, addr, oi); } -void cpu_stq_le_mmu(CPUArchState *env, target_ulong addr, uint64_t val, - MemOpIdx oi, uintptr_t retaddr) +void cpu_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, + MemOpIdx oi, uintptr_t retaddr) { - tcg_debug_assert((get_memop(oi) & (MO_BSWAP | MO_SIZE)) == MO_LEUQ); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64); do_st8_mmu(env, addr, val, oi, retaddr); plugin_store_cb(env, addr, oi); } -void cpu_st16_be_mmu(CPUArchState *env, target_ulong addr, Int128 val, - MemOpIdx oi, uintptr_t retaddr) -{ - tcg_debug_assert((get_memop(oi) & (MO_BSWAP|MO_SIZE)) == (MO_BE|MO_128)); - do_st16_mmu(env, addr, val, oi, retaddr); - plugin_store_cb(env, addr, oi); -} - -void cpu_st16_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, - MemOpIdx oi, uintptr_t retaddr) +void cpu_st16_mmu(CPUArchState *env, target_ulong addr, Int128 val, + MemOpIdx oi, uintptr_t retaddr) { - tcg_debug_assert((get_memop(oi) & (MO_BSWAP|MO_SIZE)) == (MO_LE|MO_128)); + tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128); do_st16_mmu(env, addr, val, oi, retaddr); plugin_store_cb(env, addr, oi); } @@ -3137,7 +3038,7 @@ void cpu_st16_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, #include "atomic_template.h" #endif -#if HAVE_CMPXCHG128 || HAVE_ATOMIC128 +#if defined(CONFIG_ATOMIC128) || defined(CONFIG_CMPXCHG128) #define DATA_SIZE 16 #include "atomic_template.h" #endif diff --git a/accel/tcg/ldst_atomicity.c.inc b/accel/tcg/ldst_atomicity.c.inc index ba5db7c..0f6b3f8 100644 --- a/accel/tcg/ldst_atomicity.c.inc +++ b/accel/tcg/ldst_atomicity.c.inc @@ -16,35 +16,6 @@ #endif #define HAVE_al8_fast (ATOMIC_REG_SIZE >= 8) -/* - * If __alignof(unsigned __int128) < 16, GCC may refuse to inline atomics - * that are supported by the host, e.g. s390x. We can force the pointer to - * have our known alignment with __builtin_assume_aligned, however prior to - * GCC 13 that was only reliable with optimization enabled. See - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107389 - */ -#if defined(CONFIG_ATOMIC128_OPT) -# if !defined(__OPTIMIZE__) -# define ATTRIBUTE_ATOMIC128_OPT __attribute__((optimize("O1"))) -# endif -# define CONFIG_ATOMIC128 -#endif -#ifndef ATTRIBUTE_ATOMIC128_OPT -# define ATTRIBUTE_ATOMIC128_OPT -#endif - -#if defined(CONFIG_ATOMIC128) -# define HAVE_al16_fast true -#else -# define HAVE_al16_fast false -#endif -#if defined(CONFIG_ATOMIC128) || defined(CONFIG_CMPXCHG128) -# define HAVE_al16 true -#else -# define HAVE_al16 false -#endif - - /** * required_atomicity: * @@ -164,26 +135,6 @@ static inline uint64_t load_atomic8(void *pv) } /** - * load_atomic16: - * @pv: host address - * - * Atomically load 16 aligned bytes from @pv. - */ -static inline Int128 ATTRIBUTE_ATOMIC128_OPT -load_atomic16(void *pv) -{ -#ifdef CONFIG_ATOMIC128 - __uint128_t *p = __builtin_assume_aligned(pv, 16); - Int128Alias r; - - r.u = qatomic_read__nocheck(p); - return r.s; -#else - qemu_build_not_reached(); -#endif -} - -/** * load_atomic8_or_exit: * @env: cpu context * @ra: host unwind address @@ -228,8 +179,8 @@ static Int128 load_atomic16_or_exit(CPUArchState *env, uintptr_t ra, void *pv) { Int128 *p = __builtin_assume_aligned(pv, 16); - if (HAVE_al16_fast) { - return load_atomic16(p); + if (HAVE_ATOMIC128_RO) { + return atomic16_read_ro(p); } #ifdef CONFIG_USER_ONLY @@ -249,14 +200,9 @@ static Int128 load_atomic16_or_exit(CPUArchState *env, uintptr_t ra, void *pv) * In system mode all guest pages are writable, and for user-only * we have just checked writability. Try cmpxchg. */ -#if defined(CONFIG_CMPXCHG128) - /* Swap 0 with 0, with the side-effect of returning the old value. */ - { - Int128Alias r; - r.u = __sync_val_compare_and_swap_16((__uint128_t *)p, 0, 0); - return r.s; + if (HAVE_ATOMIC128_RW) { + return atomic16_read_rw(p); } -#endif /* Ultimate fallback: re-execute in serial context. */ cpu_loop_exit_atomic(env_cpu(env), ra); @@ -377,11 +323,10 @@ static uint64_t load_atom_extract_al16_or_exit(CPUArchState *env, uintptr_t ra, static inline uint64_t ATTRIBUTE_ATOMIC128_OPT load_atom_extract_al16_or_al8(void *pv, int s) { -#if defined(CONFIG_ATOMIC128) uintptr_t pi = (uintptr_t)pv; int o = pi & 7; int shr = (HOST_BIG_ENDIAN ? 16 - s - o : o) * 8; - __uint128_t r; + Int128 r; pv = (void *)(pi & ~7); if (pi & 8) { @@ -390,18 +335,14 @@ load_atom_extract_al16_or_al8(void *pv, int s) uint64_t b = qatomic_read__nocheck(p8 + 1); if (HOST_BIG_ENDIAN) { - r = ((__uint128_t)a << 64) | b; + r = int128_make128(b, a); } else { - r = ((__uint128_t)b << 64) | a; + r = int128_make128(a, b); } } else { - __uint128_t *p16 = __builtin_assume_aligned(pv, 16, 0); - r = qatomic_read__nocheck(p16); + r = atomic16_read_ro(pv); } - return r >> shr; -#else - qemu_build_not_reached(); -#endif + return int128_getlo(int128_urshift(r, shr)); } /** @@ -489,7 +430,7 @@ static uint16_t load_atom_2(CPUArchState *env, uintptr_t ra, if (likely((pi & 1) == 0)) { return load_atomic2(pv); } - if (HAVE_al16_fast) { + if (HAVE_ATOMIC128_RO) { return load_atom_extract_al16_or_al8(pv, 2); } @@ -528,7 +469,7 @@ static uint32_t load_atom_4(CPUArchState *env, uintptr_t ra, if (likely((pi & 3) == 0)) { return load_atomic4(pv); } - if (HAVE_al16_fast) { + if (HAVE_ATOMIC128_RO) { return load_atom_extract_al16_or_al8(pv, 4); } @@ -574,7 +515,7 @@ static uint64_t load_atom_8(CPUArchState *env, uintptr_t ra, if (HAVE_al8 && likely((pi & 7) == 0)) { return load_atomic8(pv); } - if (HAVE_al16_fast) { + if (HAVE_ATOMIC128_RO) { return load_atom_extract_al16_or_al8(pv, 8); } @@ -624,8 +565,8 @@ static Int128 load_atom_16(CPUArchState *env, uintptr_t ra, * If the host does not support 16-byte atomics, wait until we have * examined the atomicity parameters below. */ - if (HAVE_al16_fast && likely((pi & 15) == 0)) { - return load_atomic16(pv); + if (HAVE_ATOMIC128_RO && likely((pi & 15) == 0)) { + return atomic16_read_ro(pv); } atmax = required_atomicity(env, pi, memop); @@ -705,36 +646,6 @@ static inline void store_atomic8(void *pv, uint64_t val) } /** - * store_atomic16: - * @pv: host address - * @val: value to store - * - * Atomically store 16 aligned bytes to @pv. - */ -static inline void ATTRIBUTE_ATOMIC128_OPT -store_atomic16(void *pv, Int128Alias val) -{ -#if defined(CONFIG_ATOMIC128) - __uint128_t *pu = __builtin_assume_aligned(pv, 16); - qatomic_set__nocheck(pu, val.u); -#elif defined(CONFIG_CMPXCHG128) - __uint128_t *pu = __builtin_assume_aligned(pv, 16); - __uint128_t o; - - /* - * Without CONFIG_ATOMIC128, __atomic_compare_exchange_n will always - * defer to libatomic, so we must use __sync_*_compare_and_swap_16 - * and accept the sequential consistency that comes with it. - */ - do { - o = *pu; - } while (!__sync_bool_compare_and_swap_16(pu, o, val.u)); -#else - qemu_build_not_reached(); -#endif -} - -/** * store_atom_4x2 */ static inline void store_atom_4_by_2(void *pv, uint32_t val) @@ -974,7 +885,7 @@ static uint64_t store_whole_le16(void *pv, int size, Int128 val_le) int sh = o * 8; Int128 m, v; - qemu_build_assert(HAVE_al16); + qemu_build_assert(HAVE_ATOMIC128_RW); /* Like MAKE_64BIT_MASK(0, sz), but larger. */ if (sz <= 64) { @@ -1034,7 +945,7 @@ static void store_atom_2(CPUArchState *env, uintptr_t ra, return; } } else if ((pi & 15) == 7) { - if (HAVE_al16) { + if (HAVE_ATOMIC128_RW) { Int128 v = int128_lshift(int128_make64(val), 56); Int128 m = int128_lshift(int128_make64(0xffff), 56); store_atom_insert_al16(pv - 7, v, m); @@ -1103,7 +1014,7 @@ static void store_atom_4(CPUArchState *env, uintptr_t ra, return; } } else { - if (HAVE_al16) { + if (HAVE_ATOMIC128_RW) { store_whole_le16(pv, 4, int128_make64(cpu_to_le32(val))); return; } @@ -1168,7 +1079,7 @@ static void store_atom_8(CPUArchState *env, uintptr_t ra, } break; case MO_64: - if (HAVE_al16) { + if (HAVE_ATOMIC128_RW) { store_whole_le16(pv, 8, int128_make64(cpu_to_le64(val))); return; } @@ -1194,8 +1105,8 @@ static void store_atom_16(CPUArchState *env, uintptr_t ra, uint64_t a, b; int atmax; - if (HAVE_al16_fast && likely((pi & 15) == 0)) { - store_atomic16(pv, val); + if (HAVE_ATOMIC128_RW && likely((pi & 15) == 0)) { + atomic16_set(pv, val); return; } @@ -1223,7 +1134,7 @@ static void store_atom_16(CPUArchState *env, uintptr_t ra, } break; case -MO_64: - if (HAVE_al16) { + if (HAVE_ATOMIC128_RW) { uint64_t val_le; int s2 = pi & 15; int s1 = 16 - s2; @@ -1250,8 +1161,8 @@ static void store_atom_16(CPUArchState *env, uintptr_t ra, } break; case MO_128: - if (HAVE_al16) { - store_atomic16(pv, val); + if (HAVE_ATOMIC128_RW) { + atomic16_set(pv, val); return; } break; diff --git a/accel/tcg/ldst_common.c.inc b/accel/tcg/ldst_common.c.inc index 6ac8d87..5f8144b 100644 --- a/accel/tcg/ldst_common.c.inc +++ b/accel/tcg/ldst_common.c.inc @@ -26,7 +26,7 @@ uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_BEUW | MO_UNALN, mmu_idx); - return cpu_ldw_be_mmu(env, addr, oi, ra); + return cpu_ldw_mmu(env, addr, oi, ra); } int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, @@ -39,21 +39,21 @@ uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_BEUL | MO_UNALN, mmu_idx); - return cpu_ldl_be_mmu(env, addr, oi, ra); + return cpu_ldl_mmu(env, addr, oi, ra); } uint64_t cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_BEUQ | MO_UNALN, mmu_idx); - return cpu_ldq_be_mmu(env, addr, oi, ra); + return cpu_ldq_mmu(env, addr, oi, ra); } uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_LEUW | MO_UNALN, mmu_idx); - return cpu_ldw_le_mmu(env, addr, oi, ra); + return cpu_ldw_mmu(env, addr, oi, ra); } int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, @@ -66,14 +66,14 @@ uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_LEUL | MO_UNALN, mmu_idx); - return cpu_ldl_le_mmu(env, addr, oi, ra); + return cpu_ldl_mmu(env, addr, oi, ra); } uint64_t cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_LEUQ | MO_UNALN, mmu_idx); - return cpu_ldq_le_mmu(env, addr, oi, ra); + return cpu_ldq_mmu(env, addr, oi, ra); } void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, @@ -87,42 +87,42 @@ void cpu_stw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_BEUW | MO_UNALN, mmu_idx); - cpu_stw_be_mmu(env, addr, val, oi, ra); + cpu_stw_mmu(env, addr, val, oi, ra); } void cpu_stl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_BEUL | MO_UNALN, mmu_idx); - cpu_stl_be_mmu(env, addr, val, oi, ra); + cpu_stl_mmu(env, addr, val, oi, ra); } void cpu_stq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_BEUQ | MO_UNALN, mmu_idx); - cpu_stq_be_mmu(env, addr, val, oi, ra); + cpu_stq_mmu(env, addr, val, oi, ra); } void cpu_stw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_LEUW | MO_UNALN, mmu_idx); - cpu_stw_le_mmu(env, addr, val, oi, ra); + cpu_stw_mmu(env, addr, val, oi, ra); } void cpu_stl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_LEUL | MO_UNALN, mmu_idx); - cpu_stl_le_mmu(env, addr, val, oi, ra); + cpu_stl_mmu(env, addr, val, oi, ra); } void cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, int mmu_idx, uintptr_t ra) { MemOpIdx oi = make_memop_idx(MO_LEUQ | MO_UNALN, mmu_idx); - cpu_stq_le_mmu(env, addr, val, oi, ra); + cpu_stq_mmu(env, addr, val, oi, ra); } /*--------------------------*/ diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h index 6f8c206..39e6800 100644 --- a/accel/tcg/tcg-runtime.h +++ b/accel/tcg/tcg-runtime.h @@ -65,9 +65,7 @@ DEF_HELPER_FLAGS_5(atomic_cmpxchgo_le, TCG_CALL_NO_WG, i128, env, i64, i128, i128, i32) #endif -DEF_HELPER_FLAGS_5(nonatomic_cmpxchgo_be, TCG_CALL_NO_WG, - i128, env, i64, i128, i128, i32) -DEF_HELPER_FLAGS_5(nonatomic_cmpxchgo_le, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_5(nonatomic_cmpxchgo, TCG_CALL_NO_WG, i128, env, i64, i128, i128, i32) #ifdef CONFIG_ATOMIC64 diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 353849c..c87648b 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -432,7 +432,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu, qatomic_set(&prof->search_out_len, prof->search_out_len + search_size); #endif -#ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) && qemu_log_in_addr_range(pc)) { FILE *logfile = qemu_log_trylock(); @@ -505,7 +504,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu, qemu_log_unlock(logfile); } } -#endif qatomic_set(&tcg_ctx->code_gen_ptr, (void *) ROUND_UP((uintptr_t)gen_code_buf + gen_code_size + search_size, diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index 7bda43f..6120ef2 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -122,7 +122,6 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, tb->size = db->pc_next - db->pc_first; tb->icount = db->num_insns; -#ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM) && qemu_log_in_addr_range(db->pc_first)) { FILE *logfile = qemu_log_trylock(); @@ -133,7 +132,6 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, qemu_log_unlock(logfile); } } -#endif } static void *translator_access(CPUArchState *env, DisasContextBase *db, diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index 36ad828..dc8d6b5 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -940,8 +940,8 @@ uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, return ret; } -static uint16_t do_ld2_he_mmu(CPUArchState *env, abi_ptr addr, - MemOp mop, uintptr_t ra) +static uint16_t do_ld2_mmu(CPUArchState *env, abi_ptr addr, + MemOp mop, uintptr_t ra) { void *haddr; uint16_t ret; @@ -950,14 +950,6 @@ static uint16_t do_ld2_he_mmu(CPUArchState *env, abi_ptr addr, haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD); ret = load_atom_2(env, ra, haddr, mop); clear_helper_retaddr(); - return ret; -} - -tcg_target_ulong helper_lduw_mmu(CPUArchState *env, uint64_t addr, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); - uint16_t ret = do_ld2_he_mmu(env, addr, mop, ra); if (mop & MO_BSWAP) { ret = bswap16(ret); @@ -965,44 +957,28 @@ tcg_target_ulong helper_lduw_mmu(CPUArchState *env, uint64_t addr, return ret; } -tcg_target_ulong helper_ldsw_mmu(CPUArchState *env, uint64_t addr, +tcg_target_ulong helper_lduw_mmu(CPUArchState *env, uint64_t addr, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - int16_t ret = do_ld2_he_mmu(env, addr, mop, ra); - - if (mop & MO_BSWAP) { - ret = bswap16(ret); - } - return ret; + return do_ld2_mmu(env, addr, get_memop(oi), ra); } -uint16_t cpu_ldw_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +tcg_target_ulong helper_ldsw_mmu(CPUArchState *env, uint64_t addr, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - uint16_t ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - ret = do_ld2_he_mmu(env, addr, mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - return cpu_to_be16(ret); + return (int16_t)do_ld2_mmu(env, addr, get_memop(oi), ra); } -uint16_t cpu_ldw_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - uint16_t ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - ret = do_ld2_he_mmu(env, addr, mop, ra); + uint16_t ret = do_ld2_mmu(env, addr, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - return cpu_to_le16(ret); + return ret; } -static uint32_t do_ld4_he_mmu(CPUArchState *env, abi_ptr addr, - MemOp mop, uintptr_t ra) +static uint32_t do_ld4_mmu(CPUArchState *env, abi_ptr addr, + MemOp mop, uintptr_t ra) { void *haddr; uint32_t ret; @@ -1011,14 +987,6 @@ static uint32_t do_ld4_he_mmu(CPUArchState *env, abi_ptr addr, haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD); ret = load_atom_4(env, ra, haddr, mop); clear_helper_retaddr(); - return ret; -} - -tcg_target_ulong helper_ldul_mmu(CPUArchState *env, uint64_t addr, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); - uint32_t ret = do_ld4_he_mmu(env, addr, mop, ra); if (mop & MO_BSWAP) { ret = bswap32(ret); @@ -1026,44 +994,28 @@ tcg_target_ulong helper_ldul_mmu(CPUArchState *env, uint64_t addr, return ret; } -tcg_target_ulong helper_ldsl_mmu(CPUArchState *env, uint64_t addr, +tcg_target_ulong helper_ldul_mmu(CPUArchState *env, uint64_t addr, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - int32_t ret = do_ld4_he_mmu(env, addr, mop, ra); - - if (mop & MO_BSWAP) { - ret = bswap32(ret); - } - return ret; + return do_ld4_mmu(env, addr, get_memop(oi), ra); } -uint32_t cpu_ldl_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +tcg_target_ulong helper_ldsl_mmu(CPUArchState *env, uint64_t addr, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - uint32_t ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - ret = do_ld4_he_mmu(env, addr, mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - return cpu_to_be32(ret); + return (int32_t)do_ld4_mmu(env, addr, get_memop(oi), ra); } -uint32_t cpu_ldl_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - uint32_t ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - ret = do_ld4_he_mmu(env, addr, mop, ra); + uint32_t ret = do_ld4_mmu(env, addr, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - return cpu_to_le32(ret); + return ret; } -static uint64_t do_ld8_he_mmu(CPUArchState *env, abi_ptr addr, - MemOp mop, uintptr_t ra) +static uint64_t do_ld8_mmu(CPUArchState *env, abi_ptr addr, + MemOp mop, uintptr_t ra) { void *haddr; uint64_t ret; @@ -1072,14 +1024,6 @@ static uint64_t do_ld8_he_mmu(CPUArchState *env, abi_ptr addr, haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD); ret = load_atom_8(env, ra, haddr, mop); clear_helper_retaddr(); - return ret; -} - -uint64_t helper_ldq_mmu(CPUArchState *env, uint64_t addr, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); - uint64_t ret = do_ld8_he_mmu(env, addr, mop, ra); if (mop & MO_BSWAP) { ret = bswap64(ret); @@ -1087,32 +1031,22 @@ uint64_t helper_ldq_mmu(CPUArchState *env, uint64_t addr, return ret; } -uint64_t cpu_ldq_be_mmu(CPUArchState *env, abi_ptr addr, +uint64_t helper_ldq_mmu(CPUArchState *env, uint64_t addr, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - uint64_t ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - ret = do_ld8_he_mmu(env, addr, mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - return cpu_to_be64(ret); + return do_ld8_mmu(env, addr, get_memop(oi), ra); } -uint64_t cpu_ldq_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - uint64_t ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - ret = do_ld8_he_mmu(env, addr, mop, ra); + uint64_t ret = do_ld8_mmu(env, addr, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - return cpu_to_le64(ret); + return ret; } -static Int128 do_ld16_he_mmu(CPUArchState *env, abi_ptr addr, - MemOp mop, uintptr_t ra) +static Int128 do_ld16_mmu(CPUArchState *env, abi_ptr addr, + MemOp mop, uintptr_t ra) { void *haddr; Int128 ret; @@ -1121,14 +1055,6 @@ static Int128 do_ld16_he_mmu(CPUArchState *env, abi_ptr addr, haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD); ret = load_atom_16(env, ra, haddr, mop); clear_helper_retaddr(); - return ret; -} - -Int128 helper_ld16_mmu(CPUArchState *env, uint64_t addr, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); - Int128 ret = do_ld16_he_mmu(env, addr, mop, ra); if (mop & MO_BSWAP) { ret = bswap128(ret); @@ -1136,38 +1062,22 @@ Int128 helper_ld16_mmu(CPUArchState *env, uint64_t addr, return ret; } -Int128 helper_ld_i128(CPUArchState *env, uint64_t addr, MemOpIdx oi) +Int128 helper_ld16_mmu(CPUArchState *env, uint64_t addr, + MemOpIdx oi, uintptr_t ra) { - return helper_ld16_mmu(env, addr, oi, GETPC()); + return do_ld16_mmu(env, addr, get_memop(oi), ra); } -Int128 cpu_ld16_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +Int128 helper_ld_i128(CPUArchState *env, uint64_t addr, MemOpIdx oi) { - MemOp mop = get_memop(oi); - Int128 ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - ret = do_ld16_he_mmu(env, addr, mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - if (!HOST_BIG_ENDIAN) { - ret = bswap128(ret); - } - return ret; + return helper_ld16_mmu(env, addr, oi, GETPC()); } -Int128 cpu_ld16_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra) +Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - Int128 ret; - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - ret = do_ld16_he_mmu(env, addr, mop, ra); + Int128 ret = do_ld16_mmu(env, addr, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); - if (HOST_BIG_ENDIAN) { - ret = bswap128(ret); - } return ret; } @@ -1195,139 +1105,101 @@ void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val, qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } -static void do_st2_he_mmu(CPUArchState *env, abi_ptr addr, uint16_t val, - MemOp mop, uintptr_t ra) +static void do_st2_mmu(CPUArchState *env, abi_ptr addr, uint16_t val, + MemOp mop, uintptr_t ra) { void *haddr; tcg_debug_assert((mop & MO_SIZE) == MO_16); haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE); - store_atom_2(env, ra, haddr, mop, val); - clear_helper_retaddr(); -} - -void helper_stw_mmu(CPUArchState *env, uint64_t addr, uint32_t val, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); if (mop & MO_BSWAP) { val = bswap16(val); } - do_st2_he_mmu(env, addr, val, mop, ra); + store_atom_2(env, ra, haddr, mop, val); + clear_helper_retaddr(); } -void cpu_stw_be_mmu(CPUArchState *env, abi_ptr addr, uint16_t val, +void helper_stw_mmu(CPUArchState *env, uint64_t addr, uint32_t val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - do_st2_he_mmu(env, addr, be16_to_cpu(val), mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); + do_st2_mmu(env, addr, val, get_memop(oi), ra); } -void cpu_stw_le_mmu(CPUArchState *env, abi_ptr addr, uint16_t val, +void cpu_stw_mmu(CPUArchState *env, abi_ptr addr, uint16_t val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - do_st2_he_mmu(env, addr, le16_to_cpu(val), mop, ra); + do_st2_mmu(env, addr, val, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } -static void do_st4_he_mmu(CPUArchState *env, abi_ptr addr, uint32_t val, - MemOp mop, uintptr_t ra) +static void do_st4_mmu(CPUArchState *env, abi_ptr addr, uint32_t val, + MemOp mop, uintptr_t ra) { void *haddr; tcg_debug_assert((mop & MO_SIZE) == MO_32); haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE); - store_atom_4(env, ra, haddr, mop, val); - clear_helper_retaddr(); -} - -void helper_stl_mmu(CPUArchState *env, uint64_t addr, uint32_t val, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); if (mop & MO_BSWAP) { val = bswap32(val); } - do_st4_he_mmu(env, addr, val, mop, ra); + store_atom_4(env, ra, haddr, mop, val); + clear_helper_retaddr(); } -void cpu_stl_be_mmu(CPUArchState *env, abi_ptr addr, uint32_t val, +void helper_stl_mmu(CPUArchState *env, uint64_t addr, uint32_t val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - do_st4_he_mmu(env, addr, be32_to_cpu(val), mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); + do_st4_mmu(env, addr, val, get_memop(oi), ra); } -void cpu_stl_le_mmu(CPUArchState *env, abi_ptr addr, uint32_t val, - MemOpIdx oi, uintptr_t ra) +void cpu_stl_mmu(CPUArchState *env, abi_ptr addr, uint32_t val, + MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - do_st4_he_mmu(env, addr, le32_to_cpu(val), mop, ra); + do_st4_mmu(env, addr, val, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } -static void do_st8_he_mmu(CPUArchState *env, abi_ptr addr, uint64_t val, - MemOp mop, uintptr_t ra) +static void do_st8_mmu(CPUArchState *env, abi_ptr addr, uint64_t val, + MemOp mop, uintptr_t ra) { void *haddr; tcg_debug_assert((mop & MO_SIZE) == MO_64); haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE); - store_atom_8(env, ra, haddr, mop, val); - clear_helper_retaddr(); -} - -void helper_stq_mmu(CPUArchState *env, uint64_t addr, uint64_t val, - MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); if (mop & MO_BSWAP) { val = bswap64(val); } - do_st8_he_mmu(env, addr, val, mop, ra); + store_atom_8(env, ra, haddr, mop, val); + clear_helper_retaddr(); } -void cpu_stq_be_mmu(CPUArchState *env, abi_ptr addr, uint64_t val, +void helper_stq_mmu(CPUArchState *env, uint64_t addr, uint64_t val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - do_st8_he_mmu(env, addr, cpu_to_be64(val), mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); + do_st8_mmu(env, addr, val, get_memop(oi), ra); } -void cpu_stq_le_mmu(CPUArchState *env, abi_ptr addr, uint64_t val, +void cpu_stq_mmu(CPUArchState *env, abi_ptr addr, uint64_t val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - do_st8_he_mmu(env, addr, cpu_to_le64(val), mop, ra); + do_st8_mmu(env, addr, val, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } -static void do_st16_he_mmu(CPUArchState *env, abi_ptr addr, Int128 val, - MemOp mop, uintptr_t ra) +static void do_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val, + MemOp mop, uintptr_t ra) { void *haddr; tcg_debug_assert((mop & MO_SIZE) == MO_128); haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE); + + if (mop & MO_BSWAP) { + val = bswap128(val); + } store_atom_16(env, ra, haddr, mop, val); clear_helper_retaddr(); } @@ -1335,12 +1207,7 @@ static void do_st16_he_mmu(CPUArchState *env, abi_ptr addr, Int128 val, void helper_st16_mmu(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - if (mop & MO_BSWAP) { - val = bswap128(val); - } - do_st16_he_mmu(env, addr, val, mop, ra); + do_st16_mmu(env, addr, val, get_memop(oi), ra); } void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi) @@ -1348,29 +1215,10 @@ void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi) helper_st16_mmu(env, addr, val, oi, GETPC()); } -void cpu_st16_be_mmu(CPUArchState *env, abi_ptr addr, - Int128 val, MemOpIdx oi, uintptr_t ra) +void cpu_st16_mmu(CPUArchState *env, abi_ptr addr, + Int128 val, MemOpIdx oi, uintptr_t ra) { - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_BE); - if (!HOST_BIG_ENDIAN) { - val = bswap128(val); - } - do_st16_he_mmu(env, addr, val, mop, ra); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); -} - -void cpu_st16_le_mmu(CPUArchState *env, abi_ptr addr, - Int128 val, MemOpIdx oi, uintptr_t ra) -{ - MemOp mop = get_memop(oi); - - tcg_debug_assert((mop & MO_BSWAP) == MO_LE); - if (HOST_BIG_ENDIAN) { - val = bswap128(val); - } - do_st16_he_mmu(env, addr, val, mop, ra); + do_st16_mmu(env, addr, val, get_memop(oi), ra); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } @@ -1475,12 +1323,9 @@ uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr, /* * Do not allow unaligned operations to proceed. Return the host address. - * - * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE. */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, - MemOpIdx oi, int size, int prot, - uintptr_t retaddr) + MemOpIdx oi, int size, uintptr_t retaddr) { MemOp mop = get_memop(oi); int a_bits = get_alignment_bits(mop); @@ -1488,8 +1333,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, /* Enforce guest required alignment. */ if (unlikely(addr & ((1 << a_bits) - 1))) { - MMUAccessType t = prot == PAGE_READ ? MMU_DATA_LOAD : MMU_DATA_STORE; - cpu_loop_exit_sigbus(env_cpu(env), addr, t, retaddr); + cpu_loop_exit_sigbus(env_cpu(env), addr, MMU_DATA_STORE, retaddr); } /* Enforce qemu required alignment. */ @@ -1527,7 +1371,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, #include "atomic_template.h" #endif -#if HAVE_ATOMIC128 || HAVE_CMPXCHG128 +#if defined(CONFIG_ATOMIC128) || defined(CONFIG_CMPXCHG128) #define DATA_SIZE 16 #include "atomic_template.h" #endif diff --git a/host/include/aarch64/host/atomic128-cas.h b/host/include/aarch64/host/atomic128-cas.h new file mode 100644 index 0000000..5863010 --- /dev/null +++ b/host/include/aarch64/host/atomic128-cas.h @@ -0,0 +1,45 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Compare-and-swap for 128-bit atomic operations, AArch64 version. + * + * Copyright (C) 2018, 2023 Linaro, Ltd. + * + * See docs/devel/atomics.rst for discussion about the guarantees each + * atomic primitive is meant to provide. + */ + +#ifndef AARCH64_ATOMIC128_CAS_H +#define AARCH64_ATOMIC128_CAS_H + +/* Through gcc 10, aarch64 has no support for 128-bit atomics. */ +#if defined(CONFIG_ATOMIC128) || defined(CONFIG_CMPXCHG128) +#include "host/include/generic/host/atomic128-cas.h" +#else +static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) +{ + uint64_t cmpl = int128_getlo(cmp), cmph = int128_gethi(cmp); + uint64_t newl = int128_getlo(new), newh = int128_gethi(new); + uint64_t oldl, oldh; + uint32_t tmp; + + asm("0: ldaxp %[oldl], %[oldh], %[mem]\n\t" + "cmp %[oldl], %[cmpl]\n\t" + "ccmp %[oldh], %[cmph], #0, eq\n\t" + "b.ne 1f\n\t" + "stlxp %w[tmp], %[newl], %[newh], %[mem]\n\t" + "cbnz %w[tmp], 0b\n" + "1:" + : [mem] "+m"(*ptr), [tmp] "=&r"(tmp), + [oldl] "=&r"(oldl), [oldh] "=&r"(oldh) + : [cmpl] "r"(cmpl), [cmph] "r"(cmph), + [newl] "r"(newl), [newh] "r"(newh) + : "memory", "cc"); + + return int128_make128(oldl, oldh); +} + +# define CONFIG_CMPXCHG128 1 +# define HAVE_CMPXCHG128 1 +#endif + +#endif /* AARCH64_ATOMIC128_CAS_H */ diff --git a/host/include/aarch64/host/atomic128-ldst.h b/host/include/aarch64/host/atomic128-ldst.h new file mode 100644 index 0000000..a08f62c --- /dev/null +++ b/host/include/aarch64/host/atomic128-ldst.h @@ -0,0 +1,79 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Load/store for 128-bit atomic operations, AArch64 version. + * + * Copyright (C) 2018, 2023 Linaro, Ltd. + * + * See docs/devel/atomics.rst for discussion about the guarantees each + * atomic primitive is meant to provide. + */ + +#ifndef AARCH64_ATOMIC128_LDST_H +#define AARCH64_ATOMIC128_LDST_H + +#include "host/cpuinfo.h" +#include "tcg/debug-assert.h" + +/* + * Through gcc 10, aarch64 has no support for 128-bit atomics. + * Through clang 16, without -march=armv8.4-a, __atomic_load_16 + * is incorrectly expanded to a read-write operation. + * + * Anyway, this method allows runtime detection of FEAT_LSE2. + */ + +#define HAVE_ATOMIC128_RO (cpuinfo & CPUINFO_LSE2) +#define HAVE_ATOMIC128_RW 1 + +static inline Int128 atomic16_read_ro(const Int128 *ptr) +{ + uint64_t l, h; + + tcg_debug_assert(HAVE_ATOMIC128_RO); + /* With FEAT_LSE2, 16-byte aligned LDP is atomic. */ + asm("ldp %[l], %[h], %[mem]" + : [l] "=r"(l), [h] "=r"(h) : [mem] "m"(*ptr)); + + return int128_make128(l, h); +} + +static inline Int128 atomic16_read_rw(Int128 *ptr) +{ + uint64_t l, h; + uint32_t tmp; + + if (cpuinfo & CPUINFO_LSE2) { + /* With FEAT_LSE2, 16-byte aligned LDP is atomic. */ + asm("ldp %[l], %[h], %[mem]" + : [l] "=r"(l), [h] "=r"(h) : [mem] "m"(*ptr)); + } else { + /* The load must be paired with the store to guarantee not tearing. */ + asm("0: ldxp %[l], %[h], %[mem]\n\t" + "stxp %w[tmp], %[l], %[h], %[mem]\n\t" + "cbnz %w[tmp], 0b" + : [mem] "+m"(*ptr), [tmp] "=&r"(tmp), [l] "=&r"(l), [h] "=&r"(h)); + } + + return int128_make128(l, h); +} + +static inline void atomic16_set(Int128 *ptr, Int128 val) +{ + uint64_t l = int128_getlo(val), h = int128_gethi(val); + uint64_t t1, t2; + + if (cpuinfo & CPUINFO_LSE2) { + /* With FEAT_LSE2, 16-byte aligned STP is atomic. */ + asm("stp %[l], %[h], %[mem]" + : [mem] "=m"(*ptr) : [l] "r"(l), [h] "r"(h)); + } else { + /* Load into temporaries to acquire the exclusive access lock. */ + asm("0: ldxp %[t1], %[t2], %[mem]\n\t" + "stxp %w[t1], %[l], %[h], %[mem]\n\t" + "cbnz %w[t1], 0b" + : [mem] "+m"(*ptr), [t1] "=&r"(t1), [t2] "=&r"(t2) + : [l] "r"(l), [h] "r"(h)); + } +} + +#endif /* AARCH64_ATOMIC128_LDST_H */ diff --git a/host/include/aarch64/host/cpuinfo.h b/host/include/aarch64/host/cpuinfo.h new file mode 100644 index 0000000..8222789 --- /dev/null +++ b/host/include/aarch64/host/cpuinfo.h @@ -0,0 +1,22 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Host specific cpu indentification for AArch64. + */ + +#ifndef HOST_CPUINFO_H +#define HOST_CPUINFO_H + +#define CPUINFO_ALWAYS (1u << 0) /* so cpuinfo is nonzero */ +#define CPUINFO_LSE (1u << 1) +#define CPUINFO_LSE2 (1u << 2) + +/* Initialized with a constructor. */ +extern unsigned cpuinfo; + +/* + * We cannot rely on constructor ordering, so other constructors must + * use the function interface rather than the variable above. + */ +unsigned cpuinfo_init(void); + +#endif /* HOST_CPUINFO_H */ diff --git a/host/include/generic/host/atomic128-cas.h b/host/include/generic/host/atomic128-cas.h new file mode 100644 index 0000000..991d3da --- /dev/null +++ b/host/include/generic/host/atomic128-cas.h @@ -0,0 +1,47 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Compare-and-swap for 128-bit atomic operations, generic version. + * + * Copyright (C) 2018, 2023 Linaro, Ltd. + * + * See docs/devel/atomics.rst for discussion about the guarantees each + * atomic primitive is meant to provide. + */ + +#ifndef HOST_ATOMIC128_CAS_H +#define HOST_ATOMIC128_CAS_H + +#if defined(CONFIG_ATOMIC128) +static inline Int128 ATTRIBUTE_ATOMIC128_OPT +atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) +{ + __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16); + Int128Alias r, c, n; + + c.s = cmp; + n.s = new; + r.i = qatomic_cmpxchg__nocheck(ptr_align, c.i, n.i); + return r.s; +} +# define HAVE_CMPXCHG128 1 +#elif defined(CONFIG_CMPXCHG128) +static inline Int128 ATTRIBUTE_ATOMIC128_OPT +atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) +{ + __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16); + Int128Alias r, c, n; + + c.s = cmp; + n.s = new; + r.i = __sync_val_compare_and_swap_16(ptr_align, c.i, n.i); + return r.s; +} +# define HAVE_CMPXCHG128 1 +#else +/* Fallback definition that must be optimized away, or error. */ +Int128 QEMU_ERROR("unsupported atomic") + atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new); +# define HAVE_CMPXCHG128 0 +#endif + +#endif /* HOST_ATOMIC128_CAS_H */ diff --git a/host/include/generic/host/atomic128-ldst.h b/host/include/generic/host/atomic128-ldst.h new file mode 100644 index 0000000..80fff06 --- /dev/null +++ b/host/include/generic/host/atomic128-ldst.h @@ -0,0 +1,81 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Load/store for 128-bit atomic operations, generic version. + * + * Copyright (C) 2018, 2023 Linaro, Ltd. + * + * See docs/devel/atomics.rst for discussion about the guarantees each + * atomic primitive is meant to provide. + */ + +#ifndef HOST_ATOMIC128_LDST_H +#define HOST_ATOMIC128_LDST_H + +#if defined(CONFIG_ATOMIC128) +# define HAVE_ATOMIC128_RO 1 +# define HAVE_ATOMIC128_RW 1 + +static inline Int128 ATTRIBUTE_ATOMIC128_OPT +atomic16_read_ro(const Int128 *ptr) +{ + const __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16); + Int128Alias r; + + r.i = qatomic_read__nocheck(ptr_align); + return r.s; +} + +static inline Int128 ATTRIBUTE_ATOMIC128_OPT +atomic16_read_rw(Int128 *ptr) +{ + return atomic16_read_ro(ptr); +} + +static inline void ATTRIBUTE_ATOMIC128_OPT +atomic16_set(Int128 *ptr, Int128 val) +{ + __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16); + Int128Alias v; + + v.s = val; + qatomic_set__nocheck(ptr_align, v.i); +} + +#elif defined(CONFIG_CMPXCHG128) +# define HAVE_ATOMIC128_RO 0 +# define HAVE_ATOMIC128_RW 1 + +Int128 QEMU_ERROR("unsupported atomic") atomic16_read_ro(const Int128 *ptr); + +static inline Int128 ATTRIBUTE_ATOMIC128_OPT +atomic16_read_rw(Int128 *ptr) +{ + /* Maybe replace 0 with 0, returning the old value. */ + Int128 z = int128_make64(0); + return atomic16_cmpxchg(ptr, z, z); +} + +static inline void ATTRIBUTE_ATOMIC128_OPT +atomic16_set(Int128 *ptr, Int128 val) +{ + __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16); + __int128_t old; + Int128Alias new; + + new.s = val; + do { + old = *ptr_align; + } while (!__sync_bool_compare_and_swap_16(ptr_align, old, new.i)); +} + +#else +# define HAVE_ATOMIC128_RO 0 +# define HAVE_ATOMIC128_RW 0 + +/* Fallback definitions that must be optimized away, or error. */ +Int128 QEMU_ERROR("unsupported atomic") atomic16_read_ro(const Int128 *ptr); +Int128 QEMU_ERROR("unsupported atomic") atomic16_read_rw(Int128 *ptr); +void QEMU_ERROR("unsupported atomic") atomic16_set(Int128 *ptr, Int128 val); +#endif + +#endif /* HOST_ATOMIC128_LDST_H */ diff --git a/host/include/generic/host/cpuinfo.h b/host/include/generic/host/cpuinfo.h new file mode 100644 index 0000000..eca6720 --- /dev/null +++ b/host/include/generic/host/cpuinfo.h @@ -0,0 +1,4 @@ +/* + * No host specific cpu indentification. + * SPDX-License-Identifier: GPL-2.0-or-later + */ diff --git a/host/include/i386/host/cpuinfo.h b/host/include/i386/host/cpuinfo.h new file mode 100644 index 0000000..a653712 --- /dev/null +++ b/host/include/i386/host/cpuinfo.h @@ -0,0 +1,39 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Host specific cpu indentification for x86. + */ + +#ifndef HOST_CPUINFO_H +#define HOST_CPUINFO_H + +/* Digested version of <cpuid.h> */ + +#define CPUINFO_ALWAYS (1u << 0) /* so cpuinfo is nonzero */ +#define CPUINFO_CMOV (1u << 1) +#define CPUINFO_MOVBE (1u << 2) +#define CPUINFO_LZCNT (1u << 3) +#define CPUINFO_POPCNT (1u << 4) +#define CPUINFO_BMI1 (1u << 5) +#define CPUINFO_BMI2 (1u << 6) +#define CPUINFO_SSE2 (1u << 7) +#define CPUINFO_SSE4 (1u << 8) +#define CPUINFO_AVX1 (1u << 9) +#define CPUINFO_AVX2 (1u << 10) +#define CPUINFO_AVX512F (1u << 11) +#define CPUINFO_AVX512VL (1u << 12) +#define CPUINFO_AVX512BW (1u << 13) +#define CPUINFO_AVX512DQ (1u << 14) +#define CPUINFO_AVX512VBMI2 (1u << 15) +#define CPUINFO_ATOMIC_VMOVDQA (1u << 16) +#define CPUINFO_ATOMIC_VMOVDQU (1u << 17) + +/* Initialized with a constructor. */ +extern unsigned cpuinfo; + +/* + * We cannot rely on constructor ordering, so other constructors must + * use the function interface rather than the variable above. + */ +unsigned cpuinfo_init(void); + +#endif /* HOST_CPUINFO_H */ diff --git a/host/include/x86_64/host/cpuinfo.h b/host/include/x86_64/host/cpuinfo.h new file mode 100644 index 0000000..67debab --- /dev/null +++ b/host/include/x86_64/host/cpuinfo.h @@ -0,0 +1 @@ +#include "host/include/i386/host/cpuinfo.h" diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index 7c867c9..5939688 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -207,43 +207,21 @@ void cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint64_t val, int mmu_idx, uintptr_t ra); uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); -uint16_t cpu_ldw_be_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint32_t cpu_ldl_be_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint64_t cpu_ldq_be_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint16_t cpu_ldw_le_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint32_t cpu_ldl_le_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint64_t cpu_ldq_le_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); - -Int128 cpu_ld16_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); -Int128 cpu_ld16_le_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); +uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); +uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); +uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); +Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra); void cpu_stb_mmu(CPUArchState *env, abi_ptr ptr, uint8_t val, MemOpIdx oi, uintptr_t ra); -void cpu_stw_be_mmu(CPUArchState *env, abi_ptr ptr, uint16_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stl_be_mmu(CPUArchState *env, abi_ptr ptr, uint32_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stq_be_mmu(CPUArchState *env, abi_ptr ptr, uint64_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stw_le_mmu(CPUArchState *env, abi_ptr ptr, uint16_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stl_le_mmu(CPUArchState *env, abi_ptr ptr, uint32_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stq_le_mmu(CPUArchState *env, abi_ptr ptr, uint64_t val, - MemOpIdx oi, uintptr_t ra); - -void cpu_st16_be_mmu(CPUArchState *env, abi_ptr addr, Int128 val, - MemOpIdx oi, uintptr_t ra); -void cpu_st16_le_mmu(CPUArchState *env, abi_ptr addr, Int128 val, - MemOpIdx oi, uintptr_t ra); +void cpu_stw_mmu(CPUArchState *env, abi_ptr ptr, uint16_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_stl_mmu(CPUArchState *env, abi_ptr ptr, uint32_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_stq_mmu(CPUArchState *env, abi_ptr ptr, uint64_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val, + MemOpIdx oi, uintptr_t ra); uint32_t cpu_atomic_cmpxchgb_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, @@ -322,15 +300,6 @@ Int128 cpu_atomic_cmpxchgo_be_mmu(CPUArchState *env, target_ulong addr, Int128 cmpv, Int128 newv, MemOpIdx oi, uintptr_t retaddr); -Int128 cpu_atomic_ldo_le_mmu(CPUArchState *env, target_ulong addr, - MemOpIdx oi, uintptr_t retaddr); -Int128 cpu_atomic_ldo_be_mmu(CPUArchState *env, target_ulong addr, - MemOpIdx oi, uintptr_t retaddr); -void cpu_atomic_sto_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, - MemOpIdx oi, uintptr_t retaddr); -void cpu_atomic_sto_be_mmu(CPUArchState *env, target_ulong addr, Int128 val, - MemOpIdx oi, uintptr_t retaddr); - #if defined(CONFIG_USER_ONLY) extern __thread uintptr_t helper_retaddr; @@ -416,9 +385,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # define cpu_ldsw_mmuidx_ra cpu_ldsw_be_mmuidx_ra # define cpu_ldl_mmuidx_ra cpu_ldl_be_mmuidx_ra # define cpu_ldq_mmuidx_ra cpu_ldq_be_mmuidx_ra -# define cpu_ldw_mmu cpu_ldw_be_mmu -# define cpu_ldl_mmu cpu_ldl_be_mmu -# define cpu_ldq_mmu cpu_ldq_be_mmu # define cpu_stw_data cpu_stw_be_data # define cpu_stl_data cpu_stl_be_data # define cpu_stq_data cpu_stq_be_data @@ -428,9 +394,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # define cpu_stw_mmuidx_ra cpu_stw_be_mmuidx_ra # define cpu_stl_mmuidx_ra cpu_stl_be_mmuidx_ra # define cpu_stq_mmuidx_ra cpu_stq_be_mmuidx_ra -# define cpu_stw_mmu cpu_stw_be_mmu -# define cpu_stl_mmu cpu_stl_be_mmu -# define cpu_stq_mmu cpu_stq_be_mmu #else # define cpu_lduw_data cpu_lduw_le_data # define cpu_ldsw_data cpu_ldsw_le_data @@ -444,9 +407,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # define cpu_ldsw_mmuidx_ra cpu_ldsw_le_mmuidx_ra # define cpu_ldl_mmuidx_ra cpu_ldl_le_mmuidx_ra # define cpu_ldq_mmuidx_ra cpu_ldq_le_mmuidx_ra -# define cpu_ldw_mmu cpu_ldw_le_mmu -# define cpu_ldl_mmu cpu_ldl_le_mmu -# define cpu_ldq_mmu cpu_ldq_le_mmu # define cpu_stw_data cpu_stw_le_data # define cpu_stl_data cpu_stl_le_data # define cpu_stq_data cpu_stq_le_data @@ -456,9 +416,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # define cpu_stw_mmuidx_ra cpu_stw_le_mmuidx_ra # define cpu_stl_mmuidx_ra cpu_stl_le_mmuidx_ra # define cpu_stq_mmuidx_ra cpu_stq_le_mmuidx_ra -# define cpu_stw_mmu cpu_stw_le_mmu -# define cpu_stl_mmu cpu_stl_le_mmu -# define cpu_stq_mmu cpu_stq_le_mmu #endif uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr, diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index ecded1f..4d2b151 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -27,9 +27,6 @@ #include "qemu/interval-tree.h" #include "qemu/clang-tsa.h" -/* allow to see translation results - the slowdown should be negligible, so we leave it */ -#define DEBUG_DISAS - /* Page tracking code uses ram addresses in system mode, and virtual addresses in userspace mode. Define tb_page_addr_t to be an appropriate type. */ diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h index d0ba0b9..34554bf 100644 --- a/include/qemu/atomic128.h +++ b/include/qemu/atomic128.h @@ -16,6 +16,23 @@ #include "qemu/int128.h" /* + * If __alignof(unsigned __int128) < 16, GCC may refuse to inline atomics + * that are supported by the host, e.g. s390x. We can force the pointer to + * have our known alignment with __builtin_assume_aligned, however prior to + * GCC 13 that was only reliable with optimization enabled. See + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107389 + */ +#if defined(CONFIG_ATOMIC128_OPT) +# if !defined(__OPTIMIZE__) +# define ATTRIBUTE_ATOMIC128_OPT __attribute__((optimize("O1"))) +# endif +# define CONFIG_ATOMIC128 +#endif +#ifndef ATTRIBUTE_ATOMIC128_OPT +# define ATTRIBUTE_ATOMIC128_OPT +#endif + +/* * GCC is a house divided about supporting large atomic operations. * * For hosts that only have large compare-and-swap, a legalistic reading @@ -41,132 +58,7 @@ * Therefore, special case each platform. */ -#if defined(CONFIG_ATOMIC128) -static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) -{ - Int128Alias r, c, n; - - c.s = cmp; - n.s = new; - r.i = qatomic_cmpxchg__nocheck((__int128_t *)ptr, c.i, n.i); - return r.s; -} -# define HAVE_CMPXCHG128 1 -#elif defined(CONFIG_CMPXCHG128) -static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) -{ - Int128Alias r, c, n; - - c.s = cmp; - n.s = new; - r.i = __sync_val_compare_and_swap_16((__int128_t *)ptr, c.i, n.i); - return r.s; -} -# define HAVE_CMPXCHG128 1 -#elif defined(__aarch64__) -/* Through gcc 8, aarch64 has no support for 128-bit at all. */ -static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) -{ - uint64_t cmpl = int128_getlo(cmp), cmph = int128_gethi(cmp); - uint64_t newl = int128_getlo(new), newh = int128_gethi(new); - uint64_t oldl, oldh; - uint32_t tmp; - - asm("0: ldaxp %[oldl], %[oldh], %[mem]\n\t" - "cmp %[oldl], %[cmpl]\n\t" - "ccmp %[oldh], %[cmph], #0, eq\n\t" - "b.ne 1f\n\t" - "stlxp %w[tmp], %[newl], %[newh], %[mem]\n\t" - "cbnz %w[tmp], 0b\n" - "1:" - : [mem] "+m"(*ptr), [tmp] "=&r"(tmp), - [oldl] "=&r"(oldl), [oldh] "=&r"(oldh) - : [cmpl] "r"(cmpl), [cmph] "r"(cmph), - [newl] "r"(newl), [newh] "r"(newh) - : "memory", "cc"); - - return int128_make128(oldl, oldh); -} -# define HAVE_CMPXCHG128 1 -#else -/* Fallback definition that must be optimized away, or error. */ -Int128 QEMU_ERROR("unsupported atomic") - atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new); -# define HAVE_CMPXCHG128 0 -#endif /* Some definition for HAVE_CMPXCHG128 */ - - -#if defined(CONFIG_ATOMIC128) -static inline Int128 atomic16_read(Int128 *ptr) -{ - Int128Alias r; - - r.i = qatomic_read__nocheck((__int128_t *)ptr); - return r.s; -} - -static inline void atomic16_set(Int128 *ptr, Int128 val) -{ - Int128Alias v; - - v.s = val; - qatomic_set__nocheck((__int128_t *)ptr, v.i); -} - -# define HAVE_ATOMIC128 1 -#elif !defined(CONFIG_USER_ONLY) && defined(__aarch64__) -/* We can do better than cmpxchg for AArch64. */ -static inline Int128 atomic16_read(Int128 *ptr) -{ - uint64_t l, h; - uint32_t tmp; - - /* The load must be paired with the store to guarantee not tearing. */ - asm("0: ldxp %[l], %[h], %[mem]\n\t" - "stxp %w[tmp], %[l], %[h], %[mem]\n\t" - "cbnz %w[tmp], 0b" - : [mem] "+m"(*ptr), [tmp] "=r"(tmp), [l] "=r"(l), [h] "=r"(h)); - - return int128_make128(l, h); -} - -static inline void atomic16_set(Int128 *ptr, Int128 val) -{ - uint64_t l = int128_getlo(val), h = int128_gethi(val); - uint64_t t1, t2; - - /* Load into temporaries to acquire the exclusive access lock. */ - asm("0: ldxp %[t1], %[t2], %[mem]\n\t" - "stxp %w[t1], %[l], %[h], %[mem]\n\t" - "cbnz %w[t1], 0b" - : [mem] "+m"(*ptr), [t1] "=&r"(t1), [t2] "=&r"(t2) - : [l] "r"(l), [h] "r"(h)); -} - -# define HAVE_ATOMIC128 1 -#elif !defined(CONFIG_USER_ONLY) && HAVE_CMPXCHG128 -static inline Int128 atomic16_read(Int128 *ptr) -{ - /* Maybe replace 0 with 0, returning the old value. */ - Int128 z = int128_make64(0); - return atomic16_cmpxchg(ptr, z, z); -} - -static inline void atomic16_set(Int128 *ptr, Int128 val) -{ - Int128 old = *ptr, cmp; - do { - cmp = old; - old = atomic16_cmpxchg(ptr, cmp, val); - } while (int128_ne(old, cmp)); -} - -# define HAVE_ATOMIC128 1 -#else -/* Fallback definitions that must be optimized away, or error. */ -Int128 QEMU_ERROR("unsupported atomic") atomic16_read(Int128 *ptr); -void QEMU_ERROR("unsupported atomic") atomic16_set(Int128 *ptr, Int128 val); -# define HAVE_ATOMIC128 0 -#endif /* Some definition for HAVE_ATOMIC128 */ +#include "host/atomic128-cas.h" +#include "host/atomic128-ldst.h" #endif /* QEMU_ATOMIC128_H */ diff --git a/include/tcg/debug-assert.h b/include/tcg/debug-assert.h new file mode 100644 index 0000000..596765a --- /dev/null +++ b/include/tcg/debug-assert.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define tcg_debug_assert + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef TCG_DEBUG_ASSERT_H +#define TCG_DEBUG_ASSERT_H + +#if defined CONFIG_DEBUG_TCG || defined QEMU_STATIC_ANALYSIS +# define tcg_debug_assert(X) do { assert(X); } while (0) +#else +# define tcg_debug_assert(X) \ + do { if (!(X)) { __builtin_unreachable(); } } while (0) +#endif + +#endif diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index cd6327b..072c35f 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -34,6 +34,7 @@ #include "tcg/tcg-mo.h" #include "tcg-target.h" #include "tcg/tcg-cond.h" +#include "tcg/debug-assert.h" /* XXX: make safe guess about sizes */ #define MAX_OP_PER_INSTR 266 @@ -222,14 +223,6 @@ typedef uint64_t tcg_insn_unit; /* The port better have done this. */ #endif - -#if defined CONFIG_DEBUG_TCG || defined QEMU_STATIC_ANALYSIS -# define tcg_debug_assert(X) do { assert(X); } while (0) -#else -# define tcg_debug_assert(X) \ - do { if (!(X)) { __builtin_unreachable(); } } while (0) -#endif - typedef struct TCGRelocation TCGRelocation; struct TCGRelocation { QSIMPLEQ_ENTRY(TCGRelocation) next; diff --git a/meson.build b/meson.build index 0a5cdef..ef181ff 100644 --- a/meson.build +++ b/meson.build @@ -512,6 +512,16 @@ add_project_arguments('-iquote', '.', '-iquote', meson.current_source_dir() / 'include', language: all_languages) +# If a host-specific include directory exists, list that first... +host_include = meson.current_source_dir() / 'host/include/' +if fs.is_dir(host_include / host_arch) + add_project_arguments('-iquote', host_include / host_arch, + language: all_languages) +endif +# ... followed by the generic fallback. +add_project_arguments('-iquote', host_include / 'generic', + language: all_languages) + sparse = find_program('cgcc', required: get_option('sparse')) if sparse.found() run_target('sparse', @@ -2547,7 +2557,7 @@ if has_int128 # __alignof(unsigned __int128) for the host. atomic_test_128 = ''' int main(int ac, char **av) { - unsigned __int128 *p = __builtin_assume_aligned(av[ac - 1], sizeof(16)); + unsigned __int128 *p = __builtin_assume_aligned(av[ac - 1], 16); p[1] = __atomic_load_n(&p[0], __ATOMIC_RELAXED); __atomic_store_n(&p[2], p[3], __ATOMIC_RELAXED); __atomic_compare_exchange_n(&p[4], &p[5], p[6], 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED); diff --git a/migration/meson.build b/migration/meson.build index a8e01e7..8ba6e42 100644 --- a/migration/meson.build +++ b/migration/meson.build @@ -8,7 +8,6 @@ migration_files = files( 'qemu-file.c', 'yank_functions.c', ) -softmmu_ss.add(migration_files) softmmu_ss.add(files( 'block-dirty-bitmap.c', diff --git a/migration/ram.c b/migration/ram.c index 9fb076f..88a6c82 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -90,34 +90,6 @@ #define RAM_SAVE_FLAG_MULTIFD_FLUSH 0x200 /* We can't use any flag that is bigger than 0x200 */ -int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int, - uint8_t *, int) = xbzrle_encode_buffer; -#if defined(CONFIG_AVX512BW_OPT) -#include "qemu/cpuid.h" -static void __attribute__((constructor)) init_cpu_flag(void) -{ - unsigned max = __get_cpuid_max(0, NULL); - int a, b, c, d; - if (max >= 1) { - __cpuid(1, a, b, c, d); - /* We must check that AVX is not just available, but usable. */ - if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) { - int bv; - __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0)); - __cpuid_count(7, 0, a, b, c, d); - /* 0xe6: - * XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15 - * and ZMM16-ZMM31 state are enabled by OS) - * XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS) - */ - if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512BW)) { - xbzrle_encode_buffer_func = xbzrle_encode_buffer_avx512; - } - } - } -} -#endif - XBZRLECacheStats xbzrle_counters; /* used by the search for pages to send */ @@ -660,9 +632,9 @@ static int save_xbzrle_page(RAMState *rs, PageSearchStatus *pss, memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE); /* XBZRLE encoding (if there is no overflow) */ - encoded_len = xbzrle_encode_buffer_func(prev_cached_page, XBZRLE.current_buf, - TARGET_PAGE_SIZE, XBZRLE.encoded_buf, - TARGET_PAGE_SIZE); + encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf, + TARGET_PAGE_SIZE, XBZRLE.encoded_buf, + TARGET_PAGE_SIZE); /* * Update the cache contents, so that it corresponds to the data diff --git a/migration/xbzrle.c b/migration/xbzrle.c index 258e495..3eddcf2 100644 --- a/migration/xbzrle.c +++ b/migration/xbzrle.c @@ -15,6 +15,152 @@ #include "qemu/host-utils.h" #include "xbzrle.h" +#if defined(CONFIG_AVX512BW_OPT) +#include <immintrin.h> +#include "host/cpuinfo.h" + +static int __attribute__((target("avx512bw"))) +xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, + uint8_t *dst, int dlen) +{ + uint32_t zrun_len = 0, nzrun_len = 0; + int d = 0, i = 0, num = 0; + uint8_t *nzrun_start = NULL; + /* add 1 to include residual part in main loop */ + uint32_t count512s = (slen >> 6) + 1; + /* countResidual is tail of data, i.e., countResidual = slen % 64 */ + uint32_t count_residual = slen & 0b111111; + bool never_same = true; + uint64_t mask_residual = 1; + mask_residual <<= count_residual; + mask_residual -= 1; + __m512i r = _mm512_set1_epi32(0); + + while (count512s) { + int bytes_to_check = 64; + uint64_t mask = 0xffffffffffffffff; + if (count512s == 1) { + bytes_to_check = count_residual; + mask = mask_residual; + } + __m512i old_data = _mm512_mask_loadu_epi8(r, + mask, old_buf + i); + __m512i new_data = _mm512_mask_loadu_epi8(r, + mask, new_buf + i); + uint64_t comp = _mm512_cmpeq_epi8_mask(old_data, new_data); + count512s--; + + bool is_same = (comp & 0x1); + while (bytes_to_check) { + if (d + 2 > dlen) { + return -1; + } + if (is_same) { + if (nzrun_len) { + d += uleb128_encode_small(dst + d, nzrun_len); + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + } + /* 64 data at a time for speed */ + if (count512s && (comp == 0xffffffffffffffff)) { + i += 64; + zrun_len += 64; + break; + } + never_same = false; + num = ctz64(~comp); + num = (num < bytes_to_check) ? num : bytes_to_check; + zrun_len += num; + bytes_to_check -= num; + comp >>= num; + i += num; + if (bytes_to_check) { + /* still has different data after same data */ + d += uleb128_encode_small(dst + d, zrun_len); + zrun_len = 0; + } else { + break; + } + } + if (never_same || zrun_len) { + /* + * never_same only acts if + * data begins with diff in first count512s + */ + d += uleb128_encode_small(dst + d, zrun_len); + zrun_len = 0; + never_same = false; + } + /* has diff, 64 data at a time for speed */ + if ((bytes_to_check == 64) && (comp == 0x0)) { + i += 64; + nzrun_len += 64; + break; + } + num = ctz64(comp); + num = (num < bytes_to_check) ? num : bytes_to_check; + nzrun_len += num; + bytes_to_check -= num; + comp >>= num; + i += num; + if (bytes_to_check) { + /* mask like 111000 */ + d += uleb128_encode_small(dst + d, nzrun_len); + /* overflow */ + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + is_same = true; + } + } + } + + if (nzrun_len != 0) { + d += uleb128_encode_small(dst + d, nzrun_len); + /* overflow */ + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + } + return d; +} + +static int xbzrle_encode_buffer_int(uint8_t *old_buf, uint8_t *new_buf, + int slen, uint8_t *dst, int dlen); + +static int (*accel_func)(uint8_t *, uint8_t *, int, uint8_t *, int); + +static void __attribute__((constructor)) init_accel(void) +{ + unsigned info = cpuinfo_init(); + if (info & CPUINFO_AVX512BW) { + accel_func = xbzrle_encode_buffer_avx512; + } else { + accel_func = xbzrle_encode_buffer_int; + } +} + +int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen, + uint8_t *dst, int dlen) +{ + return accel_func(old_buf, new_buf, slen, dst, dlen); +} + +#define xbzrle_encode_buffer xbzrle_encode_buffer_int +#endif + /* page = zrun nzrun | zrun nzrun page @@ -175,125 +321,3 @@ int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen) return d; } - -#if defined(CONFIG_AVX512BW_OPT) -#include <immintrin.h> - -int __attribute__((target("avx512bw"))) -xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, - uint8_t *dst, int dlen) -{ - uint32_t zrun_len = 0, nzrun_len = 0; - int d = 0, i = 0, num = 0; - uint8_t *nzrun_start = NULL; - /* add 1 to include residual part in main loop */ - uint32_t count512s = (slen >> 6) + 1; - /* countResidual is tail of data, i.e., countResidual = slen % 64 */ - uint32_t count_residual = slen & 0b111111; - bool never_same = true; - uint64_t mask_residual = 1; - mask_residual <<= count_residual; - mask_residual -= 1; - __m512i r = _mm512_set1_epi32(0); - - while (count512s) { - int bytes_to_check = 64; - uint64_t mask = 0xffffffffffffffff; - if (count512s == 1) { - bytes_to_check = count_residual; - mask = mask_residual; - } - __m512i old_data = _mm512_mask_loadu_epi8(r, - mask, old_buf + i); - __m512i new_data = _mm512_mask_loadu_epi8(r, - mask, new_buf + i); - uint64_t comp = _mm512_cmpeq_epi8_mask(old_data, new_data); - count512s--; - - bool is_same = (comp & 0x1); - while (bytes_to_check) { - if (d + 2 > dlen) { - return -1; - } - if (is_same) { - if (nzrun_len) { - d += uleb128_encode_small(dst + d, nzrun_len); - if (d + nzrun_len > dlen) { - return -1; - } - nzrun_start = new_buf + i - nzrun_len; - memcpy(dst + d, nzrun_start, nzrun_len); - d += nzrun_len; - nzrun_len = 0; - } - /* 64 data at a time for speed */ - if (count512s && (comp == 0xffffffffffffffff)) { - i += 64; - zrun_len += 64; - break; - } - never_same = false; - num = ctz64(~comp); - num = (num < bytes_to_check) ? num : bytes_to_check; - zrun_len += num; - bytes_to_check -= num; - comp >>= num; - i += num; - if (bytes_to_check) { - /* still has different data after same data */ - d += uleb128_encode_small(dst + d, zrun_len); - zrun_len = 0; - } else { - break; - } - } - if (never_same || zrun_len) { - /* - * never_same only acts if - * data begins with diff in first count512s - */ - d += uleb128_encode_small(dst + d, zrun_len); - zrun_len = 0; - never_same = false; - } - /* has diff, 64 data at a time for speed */ - if ((bytes_to_check == 64) && (comp == 0x0)) { - i += 64; - nzrun_len += 64; - break; - } - num = ctz64(comp); - num = (num < bytes_to_check) ? num : bytes_to_check; - nzrun_len += num; - bytes_to_check -= num; - comp >>= num; - i += num; - if (bytes_to_check) { - /* mask like 111000 */ - d += uleb128_encode_small(dst + d, nzrun_len); - /* overflow */ - if (d + nzrun_len > dlen) { - return -1; - } - nzrun_start = new_buf + i - nzrun_len; - memcpy(dst + d, nzrun_start, nzrun_len); - d += nzrun_len; - nzrun_len = 0; - is_same = true; - } - } - } - - if (nzrun_len != 0) { - d += uleb128_encode_small(dst + d, nzrun_len); - /* overflow */ - if (d + nzrun_len > dlen) { - return -1; - } - nzrun_start = new_buf + i - nzrun_len; - memcpy(dst + d, nzrun_start, nzrun_len); - d += nzrun_len; - } - return d; -} -#endif diff --git a/migration/xbzrle.h b/migration/xbzrle.h index 6feb491..39e651b 100644 --- a/migration/xbzrle.h +++ b/migration/xbzrle.h @@ -18,8 +18,5 @@ int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen, uint8_t *dst, int dlen); int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen); -#if defined(CONFIG_AVX512BW_OPT) -int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, - uint8_t *dst, int dlen); -#endif + #endif diff --git a/scripts/ci/gitlab-kubernetes-runners/values.yaml b/scripts/ci/gitlab-kubernetes-runners/values.yaml new file mode 100644 index 0000000..204a96a --- /dev/null +++ b/scripts/ci/gitlab-kubernetes-runners/values.yaml @@ -0,0 +1,30 @@ +gitlabUrl: "https://gitlab.com/" +runnerRegistrationToken: "" +rbac: + create: true +concurrent: 200 +runners: + privileged: true + config: | + [[runners]] + limit = 100 + environment = [ + "DOCKER_HOST=tcp://docker:2376", + "DOCKER_TLS_CERTDIR=/certs", + "DOCKER_TLS_VERIFY=1", + "DOCKER_CERT_PATH=/certs/client" + ] + [runners.kubernetes] + poll_timeout = 1200 + image = "ubuntu:20.04" + cpu_request = "0.5" + service_cpu_request = "0.5" + helper_cpu_request = "0.25" + cpu_request_overwrite_max_allowed = "7" + memory_request_overwrite_max_allowed = "30Gi" + [[runners.kubernetes.volumes.empty_dir]] + name = "docker-certs" + mount_path = "/certs/client" + medium = "Memory" + [runners.kubernetes.node_selector] + agentpool = "jobs" diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index 9758f22..9cef70e 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -1937,8 +1937,8 @@ static bool do_v7m_function_return(ARMCPU *cpu) */ mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true); oi = make_memop_idx(MO_LEUL, arm_to_core_mmu_idx(mmu_idx)); - newpc = cpu_ldl_le_mmu(env, frameptr, oi, 0); - newpsr = cpu_ldl_le_mmu(env, frameptr + 4, oi, 0); + newpc = cpu_ldl_mmu(env, frameptr, oi, 0); + newpsr = cpu_ldl_mmu(env, frameptr + 4, oi, 0); /* Consistency checks on new IPSR */ newpsr_exc = newpsr & XPSR_EXCP; diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 1c02596..0f9f2e1 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -1124,7 +1124,6 @@ struct CPUArchState { /* used to speed-up TLB assist handlers */ target_ulong nip; /* next instruction pointer */ - uint64_t retxh; /* high part of 128-bit helper return */ /* when a memory exception occurs, the access type is stored here */ int access_type; diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 0beaca5..38efbc3 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -810,12 +810,3 @@ DEF_HELPER_4(DSCLIQ, void, env, fprp, fprp, i32) DEF_HELPER_1(tbegin, void, env) DEF_HELPER_FLAGS_1(fixup_thrm, TCG_CALL_NO_RWG, void, env) - -#ifdef TARGET_PPC64 -DEF_HELPER_FLAGS_3(lq_le_parallel, TCG_CALL_NO_WG, i64, env, tl, i32) -DEF_HELPER_FLAGS_3(lq_be_parallel, TCG_CALL_NO_WG, i64, env, tl, i32) -DEF_HELPER_FLAGS_5(stq_le_parallel, TCG_CALL_NO_WG, - void, env, tl, i64, i64, i32) -DEF_HELPER_FLAGS_5(stq_be_parallel, TCG_CALL_NO_WG, - void, env, tl, i64, i64, i32) -#endif diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c index 1578887..46eae65 100644 --- a/target/ppc/mem_helper.c +++ b/target/ppc/mem_helper.c @@ -367,54 +367,6 @@ target_ulong helper_lscbx(CPUPPCState *env, target_ulong addr, uint32_t reg, return i; } -#ifdef TARGET_PPC64 -uint64_t helper_lq_le_parallel(CPUPPCState *env, target_ulong addr, - uint32_t opidx) -{ - Int128 ret; - - /* We will have raised EXCP_ATOMIC from the translator. */ - assert(HAVE_ATOMIC128); - ret = cpu_atomic_ldo_le_mmu(env, addr, opidx, GETPC()); - env->retxh = int128_gethi(ret); - return int128_getlo(ret); -} - -uint64_t helper_lq_be_parallel(CPUPPCState *env, target_ulong addr, - uint32_t opidx) -{ - Int128 ret; - - /* We will have raised EXCP_ATOMIC from the translator. */ - assert(HAVE_ATOMIC128); - ret = cpu_atomic_ldo_be_mmu(env, addr, opidx, GETPC()); - env->retxh = int128_gethi(ret); - return int128_getlo(ret); -} - -void helper_stq_le_parallel(CPUPPCState *env, target_ulong addr, - uint64_t lo, uint64_t hi, uint32_t opidx) -{ - Int128 val; - - /* We will have raised EXCP_ATOMIC from the translator. */ - assert(HAVE_ATOMIC128); - val = int128_make128(lo, hi); - cpu_atomic_sto_le_mmu(env, addr, val, opidx, GETPC()); -} - -void helper_stq_be_parallel(CPUPPCState *env, target_ulong addr, - uint64_t lo, uint64_t hi, uint32_t opidx) -{ - Int128 val; - - /* We will have raised EXCP_ATOMIC from the translator. */ - assert(HAVE_ATOMIC128); - val = int128_make128(lo, hi); - cpu_atomic_sto_be_mmu(env, addr, val, opidx, GETPC()); -} -#endif - /*****************************************************************************/ /* Altivec extension helpers */ #if HOST_BIG_ENDIAN diff --git a/target/ppc/translate.c b/target/ppc/translate.c index f603f1a..1720570 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -3757,6 +3757,7 @@ static void gen_lqarx(DisasContext *ctx) { int rd = rD(ctx->opcode); TCGv EA, hi, lo; + TCGv_i128 t16; if (unlikely((rd & 1) || (rd == rA(ctx->opcode)) || (rd == rB(ctx->opcode)))) { @@ -3772,36 +3773,9 @@ static void gen_lqarx(DisasContext *ctx) lo = cpu_gpr[rd + 1]; hi = cpu_gpr[rd]; - if (tb_cflags(ctx->base.tb) & CF_PARALLEL) { - if (HAVE_ATOMIC128) { - TCGv_i32 oi = tcg_temp_new_i32(); - if (ctx->le_mode) { - tcg_gen_movi_i32(oi, make_memop_idx(MO_LE | MO_128 | MO_ALIGN, - ctx->mem_idx)); - gen_helper_lq_le_parallel(lo, cpu_env, EA, oi); - } else { - tcg_gen_movi_i32(oi, make_memop_idx(MO_BE | MO_128 | MO_ALIGN, - ctx->mem_idx)); - gen_helper_lq_be_parallel(lo, cpu_env, EA, oi); - } - tcg_gen_ld_i64(hi, cpu_env, offsetof(CPUPPCState, retxh)); - } else { - /* Restart with exclusive lock. */ - gen_helper_exit_atomic(cpu_env); - ctx->base.is_jmp = DISAS_NORETURN; - return; - } - } else if (ctx->le_mode) { - tcg_gen_qemu_ld_i64(lo, EA, ctx->mem_idx, MO_LEUQ | MO_ALIGN_16); - tcg_gen_mov_tl(cpu_reserve, EA); - gen_addr_add(ctx, EA, EA, 8); - tcg_gen_qemu_ld_i64(hi, EA, ctx->mem_idx, MO_LEUQ); - } else { - tcg_gen_qemu_ld_i64(hi, EA, ctx->mem_idx, MO_BEUQ | MO_ALIGN_16); - tcg_gen_mov_tl(cpu_reserve, EA); - gen_addr_add(ctx, EA, EA, 8); - tcg_gen_qemu_ld_i64(lo, EA, ctx->mem_idx, MO_BEUQ); - } + t16 = tcg_temp_new_i128(); + tcg_gen_qemu_ld_i128(t16, EA, ctx->mem_idx, DEF_MEMOP(MO_128 | MO_ALIGN)); + tcg_gen_extr_i128_i64(lo, hi, t16); tcg_gen_st_tl(hi, cpu_env, offsetof(CPUPPCState, reserve_val)); tcg_gen_st_tl(lo, cpu_env, offsetof(CPUPPCState, reserve_val2)); diff --git a/target/ppc/translate/fixedpoint-impl.c.inc b/target/ppc/translate/fixedpoint-impl.c.inc index 02d86b7..f47f1a5 100644 --- a/target/ppc/translate/fixedpoint-impl.c.inc +++ b/target/ppc/translate/fixedpoint-impl.c.inc @@ -72,7 +72,7 @@ static bool do_ldst_quad(DisasContext *ctx, arg_D *a, bool store, bool prefixed) #if defined(TARGET_PPC64) TCGv ea; TCGv_i64 low_addr_gpr, high_addr_gpr; - MemOp mop; + TCGv_i128 t16; REQUIRE_INSNS_FLAGS(ctx, 64BX); @@ -101,51 +101,14 @@ static bool do_ldst_quad(DisasContext *ctx, arg_D *a, bool store, bool prefixed) low_addr_gpr = cpu_gpr[a->rt + 1]; high_addr_gpr = cpu_gpr[a->rt]; } + t16 = tcg_temp_new_i128(); - if (tb_cflags(ctx->base.tb) & CF_PARALLEL) { - if (HAVE_ATOMIC128) { - mop = DEF_MEMOP(MO_128); - TCGv_i32 oi = tcg_constant_i32(make_memop_idx(mop, ctx->mem_idx)); - if (store) { - if (ctx->le_mode) { - gen_helper_stq_le_parallel(cpu_env, ea, low_addr_gpr, - high_addr_gpr, oi); - } else { - gen_helper_stq_be_parallel(cpu_env, ea, high_addr_gpr, - low_addr_gpr, oi); - - } - } else { - if (ctx->le_mode) { - gen_helper_lq_le_parallel(low_addr_gpr, cpu_env, ea, oi); - tcg_gen_ld_i64(high_addr_gpr, cpu_env, - offsetof(CPUPPCState, retxh)); - } else { - gen_helper_lq_be_parallel(high_addr_gpr, cpu_env, ea, oi); - tcg_gen_ld_i64(low_addr_gpr, cpu_env, - offsetof(CPUPPCState, retxh)); - } - } - } else { - /* Restart with exclusive lock. */ - gen_helper_exit_atomic(cpu_env); - ctx->base.is_jmp = DISAS_NORETURN; - } + if (store) { + tcg_gen_concat_i64_i128(t16, low_addr_gpr, high_addr_gpr); + tcg_gen_qemu_st_i128(t16, ea, ctx->mem_idx, DEF_MEMOP(MO_128)); } else { - mop = DEF_MEMOP(MO_UQ); - if (store) { - tcg_gen_qemu_st_i64(low_addr_gpr, ea, ctx->mem_idx, mop); - } else { - tcg_gen_qemu_ld_i64(low_addr_gpr, ea, ctx->mem_idx, mop); - } - - gen_addr_add(ctx, ea, ea, 8); - - if (store) { - tcg_gen_qemu_st_i64(high_addr_gpr, ea, ctx->mem_idx, mop); - } else { - tcg_gen_qemu_ld_i64(high_addr_gpr, ea, ctx->mem_idx, mop); - } + tcg_gen_qemu_ld_i128(t16, ea, ctx->mem_idx, DEF_MEMOP(MO_128)); + tcg_gen_extr_i128_i64(low_addr_gpr, high_addr_gpr, t16); } #else qemu_build_not_reached(); diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index c47e7ad..f130c29 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -76,9 +76,6 @@ struct CPUArchState { float_status fpu_status; /* passed to softfloat lib */ - /* The low part of a 128-bit return, or remainder of a divide. */ - uint64_t retxl; - PSW psw; S390CrashReason crash_reason; diff --git a/target/s390x/helper.h b/target/s390x/helper.h index 341bc51..7529e72 100644 --- a/target/s390x/helper.h +++ b/target/s390x/helper.h @@ -108,10 +108,6 @@ DEF_HELPER_FLAGS_2(sfas, TCG_CALL_NO_WG, void, env, i64) DEF_HELPER_FLAGS_2(srnm, TCG_CALL_NO_WG, void, env, i64) DEF_HELPER_FLAGS_1(popcnt, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_2(stfle, i32, env, i64) -DEF_HELPER_FLAGS_2(lpq, TCG_CALL_NO_WG, i64, env, i64) -DEF_HELPER_FLAGS_2(lpq_parallel, TCG_CALL_NO_WG, i64, env, i64) -DEF_HELPER_FLAGS_4(stpq, TCG_CALL_NO_WG, void, env, i64, i64, i64) -DEF_HELPER_FLAGS_4(stpq_parallel, TCG_CALL_NO_WG, void, env, i64, i64, i64) DEF_HELPER_4(mvcos, i32, env, i64, i64, i64) DEF_HELPER_4(cu12, i32, env, i32, i32, i32) DEF_HELPER_4(cu14, i32, env, i32, i32, i32) diff --git a/target/s390x/tcg/insn-data.h.inc b/target/s390x/tcg/insn-data.h.inc index 1f1ac74..bcc70d9 100644 --- a/target/s390x/tcg/insn-data.h.inc +++ b/target/s390x/tcg/insn-data.h.inc @@ -570,7 +570,7 @@ D(0xc804, LPD, SSF, ILA, 0, 0, new_P, r3_P32, lpd, 0, MO_TEUL) D(0xc805, LPDG, SSF, ILA, 0, 0, new_P, r3_P64, lpd, 0, MO_TEUQ) /* LOAD PAIR FROM QUADWORD */ - C(0xe38f, LPQ, RXY_a, Z, 0, a2, r1_P, 0, lpq, 0) + C(0xe38f, LPQ, RXY_a, Z, 0, a2, 0, r1_D64, lpq, 0) /* LOAD POSITIVE */ C(0x1000, LPR, RR_a, Z, 0, r2_32s, new, r1_32, abs, abs32) C(0xb900, LPGR, RRE, Z, 0, r2, r1, 0, abs, abs64) diff --git a/target/s390x/tcg/mem_helper.c b/target/s390x/tcg/mem_helper.c index 8b58b8d..d02ec86 100644 --- a/target/s390x/tcg/mem_helper.c +++ b/target/s390x/tcg/mem_helper.c @@ -1737,6 +1737,11 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, uint64_t a2, bool parallel) { uint32_t mem_idx = cpu_mmu_index(env, false); + MemOpIdx oi16 = make_memop_idx(MO_TE | MO_128, mem_idx); + MemOpIdx oi8 = make_memop_idx(MO_TE | MO_64, mem_idx); + MemOpIdx oi4 = make_memop_idx(MO_TE | MO_32, mem_idx); + MemOpIdx oi2 = make_memop_idx(MO_TE | MO_16, mem_idx); + MemOpIdx oi1 = make_memop_idx(MO_8, mem_idx); uintptr_t ra = GETPC(); uint32_t fc = extract32(env->regs[0], 0, 8); uint32_t sc = extract32(env->regs[0], 8, 8); @@ -1775,34 +1780,30 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, max = 3; #endif if ((HAVE_CMPXCHG128 ? 0 : fc + 2 > max) || - (HAVE_ATOMIC128 ? 0 : sc > max)) { + (HAVE_ATOMIC128_RW ? 0 : sc > max)) { cpu_loop_exit_atomic(env_cpu(env), ra); } } - /* All loads happen before all stores. For simplicity, load the entire - store value area from the parameter list. */ - svh = cpu_ldq_data_ra(env, pl + 16, ra); - svl = cpu_ldq_data_ra(env, pl + 24, ra); + /* + * All loads happen before all stores. For simplicity, load the entire + * store value area from the parameter list. + */ + svh = cpu_ldq_mmu(env, pl + 16, oi8, ra); + svl = cpu_ldq_mmu(env, pl + 24, oi8, ra); switch (fc) { case 0: { - uint32_t nv = cpu_ldl_data_ra(env, pl, ra); + uint32_t nv = cpu_ldl_mmu(env, pl, oi4, ra); uint32_t cv = env->regs[r3]; uint32_t ov; if (parallel) { -#ifdef CONFIG_USER_ONLY - uint32_t *haddr = g2h(env_cpu(env), a1); - ov = qatomic_cmpxchg__nocheck(haddr, cv, nv); -#else - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mem_idx); - ov = cpu_atomic_cmpxchgl_be_mmu(env, a1, cv, nv, oi, ra); -#endif + ov = cpu_atomic_cmpxchgl_be_mmu(env, a1, cv, nv, oi4, ra); } else { - ov = cpu_ldl_data_ra(env, a1, ra); - cpu_stl_data_ra(env, a1, (ov == cv ? nv : ov), ra); + ov = cpu_ldl_mmu(env, a1, oi4, ra); + cpu_stl_mmu(env, a1, (ov == cv ? nv : ov), oi4, ra); } cc = (ov != cv); env->regs[r3] = deposit64(env->regs[r3], 32, 32, ov); @@ -1811,21 +1812,20 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, case 1: { - uint64_t nv = cpu_ldq_data_ra(env, pl, ra); + uint64_t nv = cpu_ldq_mmu(env, pl, oi8, ra); uint64_t cv = env->regs[r3]; uint64_t ov; if (parallel) { #ifdef CONFIG_ATOMIC64 - MemOpIdx oi = make_memop_idx(MO_TEUQ | MO_ALIGN, mem_idx); - ov = cpu_atomic_cmpxchgq_be_mmu(env, a1, cv, nv, oi, ra); + ov = cpu_atomic_cmpxchgq_be_mmu(env, a1, cv, nv, oi8, ra); #else /* Note that we asserted !parallel above. */ g_assert_not_reached(); #endif } else { - ov = cpu_ldq_data_ra(env, a1, ra); - cpu_stq_data_ra(env, a1, (ov == cv ? nv : ov), ra); + ov = cpu_ldq_mmu(env, a1, oi8, ra); + cpu_stq_mmu(env, a1, (ov == cv ? nv : ov), oi8, ra); } cc = (ov != cv); env->regs[r3] = ov; @@ -1834,27 +1834,19 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, case 2: { - uint64_t nvh = cpu_ldq_data_ra(env, pl, ra); - uint64_t nvl = cpu_ldq_data_ra(env, pl + 8, ra); - Int128 nv = int128_make128(nvl, nvh); + Int128 nv = cpu_ld16_mmu(env, pl, oi16, ra); Int128 cv = int128_make128(env->regs[r3 + 1], env->regs[r3]); Int128 ov; if (!parallel) { - uint64_t oh = cpu_ldq_data_ra(env, a1 + 0, ra); - uint64_t ol = cpu_ldq_data_ra(env, a1 + 8, ra); - - ov = int128_make128(ol, oh); + ov = cpu_ld16_mmu(env, a1, oi16, ra); cc = !int128_eq(ov, cv); if (cc) { nv = ov; } - - cpu_stq_data_ra(env, a1 + 0, int128_gethi(nv), ra); - cpu_stq_data_ra(env, a1 + 8, int128_getlo(nv), ra); + cpu_st16_mmu(env, a1, nv, oi16, ra); } else if (HAVE_CMPXCHG128) { - MemOpIdx oi = make_memop_idx(MO_TE | MO_128 | MO_ALIGN, mem_idx); - ov = cpu_atomic_cmpxchgo_be_mmu(env, a1, cv, nv, oi, ra); + ov = cpu_atomic_cmpxchgo_be_mmu(env, a1, cv, nv, oi16, ra); cc = !int128_eq(ov, cv); } else { /* Note that we asserted !parallel above. */ @@ -1876,29 +1868,19 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, if (cc == 0) { switch (sc) { case 0: - cpu_stb_data_ra(env, a2, svh >> 56, ra); + cpu_stb_mmu(env, a2, svh >> 56, oi1, ra); break; case 1: - cpu_stw_data_ra(env, a2, svh >> 48, ra); + cpu_stw_mmu(env, a2, svh >> 48, oi2, ra); break; case 2: - cpu_stl_data_ra(env, a2, svh >> 32, ra); + cpu_stl_mmu(env, a2, svh >> 32, oi4, ra); break; case 3: - cpu_stq_data_ra(env, a2, svh, ra); + cpu_stq_mmu(env, a2, svh, oi8, ra); break; case 4: - if (!parallel) { - cpu_stq_data_ra(env, a2 + 0, svh, ra); - cpu_stq_data_ra(env, a2 + 8, svl, ra); - } else if (HAVE_ATOMIC128) { - MemOpIdx oi = make_memop_idx(MO_TEUQ | MO_ALIGN_16, mem_idx); - Int128 sv = int128_make128(svl, svh); - cpu_atomic_sto_be_mmu(env, a2, sv, oi, ra); - } else { - /* Note that we asserted !parallel above. */ - g_assert_not_reached(); - } + cpu_st16_mmu(env, a2, int128_make128(svl, svh), oi16, ra); break; default: g_assert_not_reached(); @@ -2398,67 +2380,6 @@ uint64_t HELPER(lra)(CPUS390XState *env, uint64_t addr) } #endif -/* load pair from quadword */ -uint64_t HELPER(lpq)(CPUS390XState *env, uint64_t addr) -{ - uintptr_t ra = GETPC(); - uint64_t hi, lo; - - check_alignment(env, addr, 16, ra); - hi = cpu_ldq_data_ra(env, addr + 0, ra); - lo = cpu_ldq_data_ra(env, addr + 8, ra); - - env->retxl = lo; - return hi; -} - -uint64_t HELPER(lpq_parallel)(CPUS390XState *env, uint64_t addr) -{ - uintptr_t ra = GETPC(); - uint64_t hi, lo; - int mem_idx; - MemOpIdx oi; - Int128 v; - - assert(HAVE_ATOMIC128); - - mem_idx = cpu_mmu_index(env, false); - oi = make_memop_idx(MO_TEUQ | MO_ALIGN_16, mem_idx); - v = cpu_atomic_ldo_be_mmu(env, addr, oi, ra); - hi = int128_gethi(v); - lo = int128_getlo(v); - - env->retxl = lo; - return hi; -} - -/* store pair to quadword */ -void HELPER(stpq)(CPUS390XState *env, uint64_t addr, - uint64_t low, uint64_t high) -{ - uintptr_t ra = GETPC(); - - check_alignment(env, addr, 16, ra); - cpu_stq_data_ra(env, addr + 0, high, ra); - cpu_stq_data_ra(env, addr + 8, low, ra); -} - -void HELPER(stpq_parallel)(CPUS390XState *env, uint64_t addr, - uint64_t low, uint64_t high) -{ - uintptr_t ra = GETPC(); - int mem_idx; - MemOpIdx oi; - Int128 v; - - assert(HAVE_ATOMIC128); - - mem_idx = cpu_mmu_index(env, false); - oi = make_memop_idx(MO_TEUQ | MO_ALIGN_16, mem_idx); - v = int128_make128(low, high); - cpu_atomic_sto_be_mmu(env, addr, v, oi, ra); -} - /* Execute instruction. This instruction executes an insn modified with the contents of r1. It does not change the executed instruction in memory; it does not change the program counter. diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c index d6670e6..3eb3708 100644 --- a/target/s390x/tcg/translate.c +++ b/target/s390x/tcg/translate.c @@ -335,11 +335,6 @@ static void store_freg32_i64(int reg, TCGv_i64 v) tcg_gen_st32_i64(v, cpu_env, freg32_offset(reg)); } -static void return_low128(TCGv_i64 dest) -{ - tcg_gen_ld_i64(dest, cpu_env, offsetof(CPUS390XState, retxl)); -} - static void update_psw_addr(DisasContext *s) { /* psw.addr */ @@ -3130,15 +3125,9 @@ static DisasJumpType op_lpd(DisasContext *s, DisasOps *o) static DisasJumpType op_lpq(DisasContext *s, DisasOps *o) { - if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { - gen_helper_lpq(o->out, cpu_env, o->in2); - } else if (HAVE_ATOMIC128) { - gen_helper_lpq_parallel(o->out, cpu_env, o->in2); - } else { - gen_helper_exit_atomic(cpu_env); - return DISAS_NORETURN; - } - return_low128(o->out2); + o->out_128 = tcg_temp_new_i128(); + tcg_gen_qemu_ld_i128(o->out_128, o->in2, get_mem_index(s), + MO_TE | MO_128 | MO_ALIGN); return DISAS_NEXT; } @@ -4533,14 +4522,11 @@ static DisasJumpType op_stmh(DisasContext *s, DisasOps *o) static DisasJumpType op_stpq(DisasContext *s, DisasOps *o) { - if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { - gen_helper_stpq(cpu_env, o->in2, o->out2, o->out); - } else if (HAVE_ATOMIC128) { - gen_helper_stpq_parallel(cpu_env, o->in2, o->out2, o->out); - } else { - gen_helper_exit_atomic(cpu_env); - return DISAS_NORETURN; - } + TCGv_i128 t16 = tcg_temp_new_i128(); + + tcg_gen_concat_i64_i128(t16, o->out2, o->out); + tcg_gen_qemu_st_i128(t16, o->in2, get_mem_index(s), + MO_TE | MO_128 | MO_ALIGN); return DISAS_NEXT; } diff --git a/target/sh4/translate.c b/target/sh4/translate.c index 0dedbb8..d9accfa 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -17,8 +17,6 @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -#define DEBUG_DISAS - #include "qemu/osdep.h" #include "cpu.h" #include "disas/disas.h" diff --git a/target/sparc/ldst_helper.c b/target/sparc/ldst_helper.c index 7972d56..981a47d 100644 --- a/target/sparc/ldst_helper.c +++ b/target/sparc/ldst_helper.c @@ -1334,25 +1334,13 @@ uint64_t helper_ld_asi(CPUSPARCState *env, target_ulong addr, ret = cpu_ldb_mmu(env, addr, oi, GETPC()); break; case 2: - if (asi & 8) { - ret = cpu_ldw_le_mmu(env, addr, oi, GETPC()); - } else { - ret = cpu_ldw_be_mmu(env, addr, oi, GETPC()); - } + ret = cpu_ldw_mmu(env, addr, oi, GETPC()); break; case 4: - if (asi & 8) { - ret = cpu_ldl_le_mmu(env, addr, oi, GETPC()); - } else { - ret = cpu_ldl_be_mmu(env, addr, oi, GETPC()); - } + ret = cpu_ldl_mmu(env, addr, oi, GETPC()); break; case 8: - if (asi & 8) { - ret = cpu_ldq_le_mmu(env, addr, oi, GETPC()); - } else { - ret = cpu_ldq_be_mmu(env, addr, oi, GETPC()); - } + ret = cpu_ldq_mmu(env, addr, oi, GETPC()); break; default: g_assert_not_reached(); diff --git a/target/sparc/translate.c b/target/sparc/translate.c index 414e014..93777984 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -34,8 +34,6 @@ #include "asi.h" -#define DEBUG_DISAS - #define DYNAMIC_PC 1 /* dynamic pc value */ #define JUMP_PC 2 /* dynamic pc value which takes only two values according to jump_pc[T2] */ diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc index bc6b99a..8428366 100644 --- a/tcg/aarch64/tcg-target.c.inc +++ b/tcg/aarch64/tcg-target.c.inc @@ -13,12 +13,6 @@ #include "../tcg-ldst.c.inc" #include "../tcg-pool.c.inc" #include "qemu/bitops.h" -#ifdef __linux__ -#include <asm/hwcap.h> -#endif -#ifdef CONFIG_DARWIN -#include <sys/sysctl.h> -#endif /* We're going to re-use TCGType in setting of the SF bit, which controls the size of the operation performed. If we know the values match, it @@ -77,9 +71,6 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot) return TCG_REG_X0 + slot; } -bool have_lse; -bool have_lse2; - #define TCG_REG_TMP TCG_REG_X30 #define TCG_VEC_TMP TCG_REG_V31 @@ -2878,39 +2869,8 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) } } -#ifdef CONFIG_DARWIN -static bool sysctl_for_bool(const char *name) -{ - int val = 0; - size_t len = sizeof(val); - - if (sysctlbyname(name, &val, &len, NULL, 0) == 0) { - return val != 0; - } - - /* - * We might in the future ask for properties not present in older kernels, - * but we're only asking about static properties, all of which should be - * 'int'. So we shouln't see ENOMEM (val too small), or any of the other - * more exotic errors. - */ - assert(errno == ENOENT); - return false; -} -#endif - static void tcg_target_init(TCGContext *s) { -#ifdef __linux__ - unsigned long hwcap = qemu_getauxval(AT_HWCAP); - have_lse = hwcap & HWCAP_ATOMICS; - have_lse2 = hwcap & HWCAP_USCAT; -#endif -#ifdef CONFIG_DARWIN - have_lse = sysctl_for_bool("hw.optional.arm.FEAT_LSE"); - have_lse2 = sysctl_for_bool("hw.optional.arm.FEAT_LSE2"); -#endif - tcg_target_available_regs[TCG_TYPE_I32] = 0xffffffffu; tcg_target_available_regs[TCG_TYPE_I64] = 0xffffffffu; tcg_target_available_regs[TCG_TYPE_V64] = 0xffffffff00000000ull; diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h index 74ee2ed..d5f7614 100644 --- a/tcg/aarch64/tcg-target.h +++ b/tcg/aarch64/tcg-target.h @@ -13,6 +13,8 @@ #ifndef AARCH64_TCG_TARGET_H #define AARCH64_TCG_TARGET_H +#include "host/cpuinfo.h" + #define TCG_TARGET_INSN_UNIT_SIZE 4 #define TCG_TARGET_TLB_DISPLACEMENT_BITS 24 #define MAX_CODE_GEN_BUFFER_SIZE ((size_t)-1) @@ -57,8 +59,8 @@ typedef enum { #define TCG_TARGET_CALL_ARG_I128 TCG_CALL_ARG_EVEN #define TCG_TARGET_CALL_RET_I128 TCG_CALL_RET_NORMAL -extern bool have_lse; -extern bool have_lse2; +#define have_lse (cpuinfo & CPUINFO_LSE) +#define have_lse2 (cpuinfo & CPUINFO_LSE2) /* optional instructions */ #define TCG_TARGET_HAS_div_i32 1 diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 8b9a5f0..bfe9d98 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -158,42 +158,14 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot) # define SOFTMMU_RESERVE_REGS 0 #endif -/* The host compiler should supply <cpuid.h> to enable runtime features - detection, as we're not going to go so far as our own inline assembly. - If not available, default values will be assumed. */ -#if defined(CONFIG_CPUID_H) -#include "qemu/cpuid.h" -#endif - /* For 64-bit, we always know that CMOV is available. */ #if TCG_TARGET_REG_BITS == 64 -# define have_cmov 1 -#elif defined(CONFIG_CPUID_H) -static bool have_cmov; -#else -# define have_cmov 0 -#endif - -/* We need these symbols in tcg-target.h, and we can't properly conditionalize - it there. Therefore we always define the variable. */ -bool have_bmi1; -bool have_popcnt; -bool have_avx1; -bool have_avx2; -bool have_avx512bw; -bool have_avx512dq; -bool have_avx512vbmi2; -bool have_avx512vl; -bool have_movbe; -bool have_atomic16; - -#ifdef CONFIG_CPUID_H -static bool have_bmi2; -static bool have_lzcnt; +# define have_cmov true #else -# define have_bmi2 0 -# define have_lzcnt 0 +# define have_cmov (cpuinfo & CPUINFO_CMOV) #endif +#define have_bmi2 (cpuinfo & CPUINFO_BMI2) +#define have_lzcnt (cpuinfo & CPUINFO_LZCNT) static const tcg_insn_unit *tb_ret_addr; @@ -3961,93 +3933,6 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) static void tcg_target_init(TCGContext *s) { -#ifdef CONFIG_CPUID_H - unsigned a, b, c, d, b7 = 0, c7 = 0; - unsigned max = __get_cpuid_max(0, 0); - - if (max >= 7) { - /* BMI1 is available on AMD Piledriver and Intel Haswell CPUs. */ - __cpuid_count(7, 0, a, b7, c7, d); - have_bmi1 = (b7 & bit_BMI) != 0; - have_bmi2 = (b7 & bit_BMI2) != 0; - } - - if (max >= 1) { - __cpuid(1, a, b, c, d); -#ifndef have_cmov - /* For 32-bit, 99% certainty that we're running on hardware that - supports cmov, but we still need to check. In case cmov is not - available, we'll use a small forward branch. */ - have_cmov = (d & bit_CMOV) != 0; -#endif - - /* MOVBE is only available on Intel Atom and Haswell CPUs, so we - need to probe for it. */ - have_movbe = (c & bit_MOVBE) != 0; - have_popcnt = (c & bit_POPCNT) != 0; - - /* There are a number of things we must check before we can be - sure of not hitting invalid opcode. */ - if (c & bit_OSXSAVE) { - unsigned bv = xgetbv_low(0); - - if ((bv & 6) == 6) { - have_avx1 = (c & bit_AVX) != 0; - have_avx2 = (b7 & bit_AVX2) != 0; - - /* - * There are interesting instructions in AVX512, so long - * as we have AVX512VL, which indicates support for EVEX - * on sizes smaller than 512 bits. We are required to - * check that OPMASK and all extended ZMM state are enabled - * even if we're not using them -- the insns will fault. - */ - if ((bv & 0xe0) == 0xe0 - && (b7 & bit_AVX512F) - && (b7 & bit_AVX512VL)) { - have_avx512vl = true; - have_avx512bw = (b7 & bit_AVX512BW) != 0; - have_avx512dq = (b7 & bit_AVX512DQ) != 0; - have_avx512vbmi2 = (c7 & bit_AVX512VBMI2) != 0; - } - - /* - * The Intel SDM has added: - * Processors that enumerate support for Intel® AVX - * (by setting the feature flag CPUID.01H:ECX.AVX[bit 28]) - * guarantee that the 16-byte memory operations performed - * by the following instructions will always be carried - * out atomically: - * - MOVAPD, MOVAPS, and MOVDQA. - * - VMOVAPD, VMOVAPS, and VMOVDQA when encoded with VEX.128. - * - VMOVAPD, VMOVAPS, VMOVDQA32, and VMOVDQA64 when encoded - * with EVEX.128 and k0 (masking disabled). - * Note that these instructions require the linear addresses - * of their memory operands to be 16-byte aligned. - * - * AMD has provided an even stronger guarantee that processors - * with AVX provide 16-byte atomicity for all cachable, - * naturally aligned single loads and stores, e.g. MOVDQU. - * - * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104688 - */ - if (have_avx1) { - __cpuid(0, a, b, c, d); - have_atomic16 = (c == signature_INTEL_ecx || - c == signature_AMD_ecx); - } - } - } - } - - max = __get_cpuid_max(0x8000000, 0); - if (max >= 1) { - __cpuid(0x80000001, a, b, c, d); - /* LZCNT was introduced with AMD Barcelona and Intel Haswell CPUs. */ - have_lzcnt = (c & bit_LZCNT) != 0; - } -#endif /* CONFIG_CPUID_H */ - tcg_target_available_regs[TCG_TYPE_I32] = ALL_GENERAL_REGS; if (TCG_TARGET_REG_BITS == 64) { tcg_target_available_regs[TCG_TYPE_I64] = ALL_GENERAL_REGS; diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index 0b5a2c6..0106946 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -25,6 +25,8 @@ #ifndef I386_TCG_TARGET_H #define I386_TCG_TARGET_H +#include "host/cpuinfo.h" + #define TCG_TARGET_INSN_UNIT_SIZE 1 #define TCG_TARGET_TLB_DISPLACEMENT_BITS 31 @@ -111,16 +113,22 @@ typedef enum { # define TCG_TARGET_CALL_RET_I128 TCG_CALL_RET_BY_REF #endif -extern bool have_bmi1; -extern bool have_popcnt; -extern bool have_avx1; -extern bool have_avx2; -extern bool have_avx512bw; -extern bool have_avx512dq; -extern bool have_avx512vbmi2; -extern bool have_avx512vl; -extern bool have_movbe; -extern bool have_atomic16; +#define have_bmi1 (cpuinfo & CPUINFO_BMI1) +#define have_popcnt (cpuinfo & CPUINFO_POPCNT) +#define have_avx1 (cpuinfo & CPUINFO_AVX1) +#define have_avx2 (cpuinfo & CPUINFO_AVX2) +#define have_movbe (cpuinfo & CPUINFO_MOVBE) +#define have_atomic16 (cpuinfo & CPUINFO_ATOMIC_VMOVDQA) + +/* + * There are interesting instructions in AVX512, so long as we have AVX512VL, + * which indicates support for EVEX on sizes smaller than 512 bits. + */ +#define have_avx512vl ((cpuinfo & CPUINFO_AVX512VL) && \ + (cpuinfo & CPUINFO_AVX512F)) +#define have_avx512bw ((cpuinfo & CPUINFO_AVX512BW) && have_avx512vl) +#define have_avx512dq ((cpuinfo & CPUINFO_AVX512DQ) && have_avx512vl) +#define have_avx512vbmi2 ((cpuinfo & CPUINFO_AVX512VBMI2) && have_avx512vl) /* optional instructions */ #define TCG_TARGET_HAS_div2_i32 1 diff --git a/tcg/tcg-op-ldst.c b/tcg/tcg-op-ldst.c index f4e508c..3d27c34 100644 --- a/tcg/tcg-op-ldst.c +++ b/tcg/tcg-op-ldst.c @@ -975,13 +975,11 @@ static void tcg_gen_nonatomic_cmpxchg_i128_int(TCGv_i128 retv, TCGTemp *addr, { if (TCG_TARGET_REG_BITS == 32) { /* Inline expansion below is simply too large for 32-bit hosts. */ - gen_atomic_cx_i128 gen = ((memop & MO_BSWAP) == MO_LE - ? gen_helper_nonatomic_cmpxchgo_le - : gen_helper_nonatomic_cmpxchgo_be); MemOpIdx oi = make_memop_idx(memop, idx); TCGv_i64 a64 = maybe_extend_addr64(addr); - gen(retv, cpu_env, a64, cmpv, newv, tcg_constant_i32(oi)); + gen_helper_nonatomic_cmpxchgo(retv, cpu_env, a64, cmpv, newv, + tcg_constant_i32(oi)); maybe_free_addr64(a64); } else { TCGv_i128 oldv = tcg_temp_ebb_new_i128(); @@ -22,9 +22,6 @@ * THE SOFTWARE. */ -/* define it to use liveness analysis (better code) */ -#define USE_TCG_OPTIMIZATIONS - #include "qemu/osdep.h" /* Define to jump the ELF file used to communicate with GDB. */ @@ -1451,7 +1448,6 @@ void tcg_prologue_init(TCGContext *s) (uintptr_t)s->code_buf, prologue_size); #endif -#ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM)) { FILE *logfile = qemu_log_trylock(); if (logfile) { @@ -1483,7 +1479,6 @@ void tcg_prologue_init(TCGContext *s) qemu_log_unlock(logfile); } } -#endif #ifndef CONFIG_TCG_INTERPRETER /* @@ -5998,7 +5993,6 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) } #endif -#ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP) && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); @@ -6009,7 +6003,6 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) qemu_log_unlock(logfile); } } -#endif #ifdef CONFIG_DEBUG_TCG /* Ensure all labels referenced have been emitted. */ @@ -6032,9 +6025,7 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) qatomic_set(&prof->opt_time, prof->opt_time - profile_getclock()); #endif -#ifdef USE_TCG_OPTIMIZATIONS tcg_optimize(s); -#endif #ifdef CONFIG_PROFILER qatomic_set(&prof->opt_time, prof->opt_time + profile_getclock()); @@ -6046,7 +6037,6 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) liveness_pass_1(s); if (s->nb_indirects > 0) { -#ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_IND) && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); @@ -6057,7 +6047,7 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) qemu_log_unlock(logfile); } } -#endif + /* Replace indirect temps with direct temps. */ if (liveness_pass_2(s)) { /* If changes were made, re-run liveness. */ @@ -6069,7 +6059,6 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) qatomic_set(&prof->la_time, prof->la_time + profile_getclock()); #endif -#ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_OPT) && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); @@ -6080,7 +6069,6 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb, uint64_t pc_start) qemu_log_unlock(logfile); } } -#endif /* Initialize goto_tb jump offsets. */ tb->jmp_reset_offset[0] = TB_JMP_OFFSET_INVALID; diff --git a/tests/bench/meson.build b/tests/bench/meson.build index 4e6b469..3c799db 100644 --- a/tests/bench/meson.build +++ b/tests/bench/meson.build @@ -3,12 +3,6 @@ qht_bench = executable('qht-bench', sources: 'qht-bench.c', dependencies: [qemuutil]) -if have_system -xbzrle_bench = executable('xbzrle-bench', - sources: 'xbzrle-bench.c', - dependencies: [qemuutil,migration]) -endif - qtree_bench = executable('qtree-bench', sources: 'qtree-bench.c', dependencies: [qemuutil]) diff --git a/tests/bench/xbzrle-bench.c b/tests/bench/xbzrle-bench.c deleted file mode 100644 index 8848a3a..0000000 --- a/tests/bench/xbzrle-bench.c +++ /dev/null @@ -1,469 +0,0 @@ -/* - * Xor Based Zero Run Length Encoding unit tests. - * - * Copyright 2013 Red Hat, Inc. and/or its affiliates - * - * Authors: - * Orit Wasserman <owasserm@redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ -#include "qemu/osdep.h" -#include "qemu/cutils.h" -#include "../migration/xbzrle.h" - -#if defined(CONFIG_AVX512BW_OPT) -#define XBZRLE_PAGE_SIZE 4096 -static bool is_cpu_support_avx512bw; -#include "qemu/cpuid.h" -static void __attribute__((constructor)) init_cpu_flag(void) -{ - unsigned max = __get_cpuid_max(0, NULL); - int a, b, c, d; - is_cpu_support_avx512bw = false; - if (max >= 1) { - __cpuid(1, a, b, c, d); - /* We must check that AVX is not just available, but usable. */ - if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) { - int bv; - __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0)); - __cpuid_count(7, 0, a, b, c, d); - /* 0xe6: - * XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15 - * and ZMM16-ZMM31 state are enabled by OS) - * XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS) - */ - if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512BW)) { - is_cpu_support_avx512bw = true; - } - } - } - return ; -} - -struct ResTime { - float t_raw; - float t_512; -}; - - -/* Function prototypes -int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, - uint8_t *dst, int dlen); -*/ -static void encode_decode_zero(struct ResTime *res) -{ - uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0; - int dlen = 0, dlen512 = 0; - int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); - - for (i = diff_len; i > 0; i--) { - buffer[1000 + i] = i; - buffer512[1000 + i] = i; - } - - buffer[1000 + diff_len + 3] = 103; - buffer[1000 + diff_len + 5] = 105; - - buffer512[1000 + diff_len + 3] = 103; - buffer512[1000 + diff_len + 5] = 105; - - /* encode zero page */ - time_t t_start, t_end, t_start512, t_end512; - t_start = clock(); - dlen = xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); - t_end = clock(); - float time_val = difftime(t_end, t_start); - g_assert(dlen == 0); - - t_start512 = clock(); - dlen512 = xbzrle_encode_buffer_avx512(buffer512, buffer512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(dlen512 == 0); - - res->t_raw = time_val; - res->t_512 = time_val512; - - g_free(buffer); - g_free(compressed); - g_free(buffer512); - g_free(compressed512); - -} - -static void test_encode_decode_zero_avx512(void) -{ - int i; - float time_raw = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_zero(&res); - time_raw += res.t_raw; - time_512 += res.t_512; - } - printf("Zero test:\n"); - printf("Raw xbzrle_encode time is %f ms\n", time_raw); - printf("512 xbzrle_encode time is %f ms\n", time_512); -} - -static void encode_decode_unchanged(struct ResTime *res) -{ - uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0; - int dlen = 0, dlen512 = 0; - int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); - - for (i = diff_len; i > 0; i--) { - test[1000 + i] = i + 4; - test512[1000 + i] = i + 4; - } - - test[1000 + diff_len + 3] = 107; - test[1000 + diff_len + 5] = 109; - - test512[1000 + diff_len + 3] = 107; - test512[1000 + diff_len + 5] = 109; - - /* test unchanged buffer */ - time_t t_start, t_end, t_start512, t_end512; - t_start = clock(); - dlen = xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); - t_end = clock(); - float time_val = difftime(t_end, t_start); - g_assert(dlen == 0); - - t_start512 = clock(); - dlen512 = xbzrle_encode_buffer_avx512(test512, test512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(dlen512 == 0); - - res->t_raw = time_val; - res->t_512 = time_val512; - - g_free(test); - g_free(compressed); - g_free(test512); - g_free(compressed512); - -} - -static void test_encode_decode_unchanged_avx512(void) -{ - int i; - float time_raw = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_unchanged(&res); - time_raw += res.t_raw; - time_512 += res.t_512; - } - printf("Unchanged test:\n"); - printf("Raw xbzrle_encode time is %f ms\n", time_raw); - printf("512 xbzrle_encode time is %f ms\n", time_512); -} - -static void encode_decode_1_byte(struct ResTime *res) -{ - uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); - uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed512 = g_malloc(XBZRLE_PAGE_SIZE); - int dlen = 0, rc = 0, dlen512 = 0, rc512 = 0; - uint8_t buf[2]; - uint8_t buf512[2]; - - test[XBZRLE_PAGE_SIZE - 1] = 1; - test512[XBZRLE_PAGE_SIZE - 1] = 1; - - time_t t_start, t_end, t_start512, t_end512; - t_start = clock(); - dlen = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); - t_end = clock(); - float time_val = difftime(t_end, t_start); - g_assert(dlen == (uleb128_encode_small(&buf[0], 4095) + 2)); - - rc = xbzrle_decode_buffer(compressed, dlen, buffer, XBZRLE_PAGE_SIZE); - g_assert(rc == XBZRLE_PAGE_SIZE); - g_assert(memcmp(test, buffer, XBZRLE_PAGE_SIZE) == 0); - - t_start512 = clock(); - dlen512 = xbzrle_encode_buffer_avx512(buffer512, test512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(dlen512 == (uleb128_encode_small(&buf512[0], 4095) + 2)); - - rc512 = xbzrle_decode_buffer(compressed512, dlen512, buffer512, - XBZRLE_PAGE_SIZE); - g_assert(rc512 == XBZRLE_PAGE_SIZE); - g_assert(memcmp(test512, buffer512, XBZRLE_PAGE_SIZE) == 0); - - res->t_raw = time_val; - res->t_512 = time_val512; - - g_free(buffer); - g_free(compressed); - g_free(test); - g_free(buffer512); - g_free(compressed512); - g_free(test512); - -} - -static void test_encode_decode_1_byte_avx512(void) -{ - int i; - float time_raw = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_1_byte(&res); - time_raw += res.t_raw; - time_512 += res.t_512; - } - printf("1 byte test:\n"); - printf("Raw xbzrle_encode time is %f ms\n", time_raw); - printf("512 xbzrle_encode time is %f ms\n", time_512); -} - -static void encode_decode_overflow(struct ResTime *res) -{ - uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0, rc = 0, rc512 = 0; - - for (i = 0; i < XBZRLE_PAGE_SIZE / 2 - 1; i++) { - test[i * 2] = 1; - test512[i * 2] = 1; - } - - /* encode overflow */ - time_t t_start, t_end, t_start512, t_end512; - t_start = clock(); - rc = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); - t_end = clock(); - float time_val = difftime(t_end, t_start); - g_assert(rc == -1); - - t_start512 = clock(); - rc512 = xbzrle_encode_buffer_avx512(buffer512, test512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(rc512 == -1); - - res->t_raw = time_val; - res->t_512 = time_val512; - - g_free(buffer); - g_free(compressed); - g_free(test); - g_free(buffer512); - g_free(compressed512); - g_free(test512); - -} - -static void test_encode_decode_overflow_avx512(void) -{ - int i; - float time_raw = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_overflow(&res); - time_raw += res.t_raw; - time_512 += res.t_512; - } - printf("Overflow test:\n"); - printf("Raw xbzrle_encode time is %f ms\n", time_raw); - printf("512 xbzrle_encode time is %f ms\n", time_512); -} - -static void encode_decode_range_avx512(struct ResTime *res) -{ - uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed512 = g_malloc(XBZRLE_PAGE_SIZE); - uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0, rc = 0, rc512 = 0; - int dlen = 0, dlen512 = 0; - - int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); - - for (i = diff_len; i > 0; i--) { - buffer[1000 + i] = i; - test[1000 + i] = i + 4; - buffer512[1000 + i] = i; - test512[1000 + i] = i + 4; - } - - buffer[1000 + diff_len + 3] = 103; - test[1000 + diff_len + 3] = 107; - - buffer[1000 + diff_len + 5] = 105; - test[1000 + diff_len + 5] = 109; - - buffer512[1000 + diff_len + 3] = 103; - test512[1000 + diff_len + 3] = 107; - - buffer512[1000 + diff_len + 5] = 105; - test512[1000 + diff_len + 5] = 109; - - /* test encode/decode */ - time_t t_start, t_end, t_start512, t_end512; - t_start = clock(); - dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); - t_end = clock(); - float time_val = difftime(t_end, t_start); - rc = xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); - g_assert(rc < XBZRLE_PAGE_SIZE); - g_assert(memcmp(test, buffer, XBZRLE_PAGE_SIZE) == 0); - - t_start512 = clock(); - dlen512 = xbzrle_encode_buffer_avx512(test512, buffer512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - rc512 = xbzrle_decode_buffer(compressed512, dlen512, test512, XBZRLE_PAGE_SIZE); - g_assert(rc512 < XBZRLE_PAGE_SIZE); - g_assert(memcmp(test512, buffer512, XBZRLE_PAGE_SIZE) == 0); - - res->t_raw = time_val; - res->t_512 = time_val512; - - g_free(buffer); - g_free(compressed); - g_free(test); - g_free(buffer512); - g_free(compressed512); - g_free(test512); - -} - -static void test_encode_decode_avx512(void) -{ - int i; - float time_raw = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_range_avx512(&res); - time_raw += res.t_raw; - time_512 += res.t_512; - } - printf("Encode decode test:\n"); - printf("Raw xbzrle_encode time is %f ms\n", time_raw); - printf("512 xbzrle_encode time is %f ms\n", time_512); -} - -static void encode_decode_random(struct ResTime *res) -{ - uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed512 = g_malloc(XBZRLE_PAGE_SIZE); - uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0, rc = 0, rc512 = 0; - int dlen = 0, dlen512 = 0; - - int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1); - /* store the index of diff */ - int dirty_index[diff_len]; - for (int j = 0; j < diff_len; j++) { - dirty_index[j] = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1); - } - for (i = diff_len - 1; i >= 0; i--) { - buffer[dirty_index[i]] = i; - test[dirty_index[i]] = i + 4; - buffer512[dirty_index[i]] = i; - test512[dirty_index[i]] = i + 4; - } - - time_t t_start, t_end, t_start512, t_end512; - t_start = clock(); - dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); - t_end = clock(); - float time_val = difftime(t_end, t_start); - rc = xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); - g_assert(rc < XBZRLE_PAGE_SIZE); - - t_start512 = clock(); - dlen512 = xbzrle_encode_buffer_avx512(test512, buffer512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - rc512 = xbzrle_decode_buffer(compressed512, dlen512, test512, XBZRLE_PAGE_SIZE); - g_assert(rc512 < XBZRLE_PAGE_SIZE); - - res->t_raw = time_val; - res->t_512 = time_val512; - - g_free(buffer); - g_free(compressed); - g_free(test); - g_free(buffer512); - g_free(compressed512); - g_free(test512); - -} - -static void test_encode_decode_random_avx512(void) -{ - int i; - float time_raw = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_random(&res); - time_raw += res.t_raw; - time_512 += res.t_512; - } - printf("Random test:\n"); - printf("Raw xbzrle_encode time is %f ms\n", time_raw); - printf("512 xbzrle_encode time is %f ms\n", time_512); -} -#endif - -int main(int argc, char **argv) -{ - g_test_init(&argc, &argv, NULL); - g_test_rand_int(); - #if defined(CONFIG_AVX512BW_OPT) - if (likely(is_cpu_support_avx512bw)) { - g_test_add_func("/xbzrle/encode_decode_zero", test_encode_decode_zero_avx512); - g_test_add_func("/xbzrle/encode_decode_unchanged", - test_encode_decode_unchanged_avx512); - g_test_add_func("/xbzrle/encode_decode_1_byte", test_encode_decode_1_byte_avx512); - g_test_add_func("/xbzrle/encode_decode_overflow", - test_encode_decode_overflow_avx512); - g_test_add_func("/xbzrle/encode_decode", test_encode_decode_avx512); - g_test_add_func("/xbzrle/encode_decode_random", test_encode_decode_random_avx512); - } - #endif - return g_test_run(); -} diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c index 547046d..b6996de 100644 --- a/tests/unit/test-xbzrle.c +++ b/tests/unit/test-xbzrle.c @@ -16,35 +16,6 @@ #define XBZRLE_PAGE_SIZE 4096 -int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int, - uint8_t *, int) = xbzrle_encode_buffer; -#if defined(CONFIG_AVX512BW_OPT) -#include "qemu/cpuid.h" -static void __attribute__((constructor)) init_cpu_flag(void) -{ - unsigned max = __get_cpuid_max(0, NULL); - int a, b, c, d; - if (max >= 1) { - __cpuid(1, a, b, c, d); - /* We must check that AVX is not just available, but usable. */ - if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) { - int bv; - __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0)); - __cpuid_count(7, 0, a, b, c, d); - /* 0xe6: - * XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15 - * and ZMM16-ZMM31 state are enabled by OS) - * XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS) - */ - if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512BW)) { - xbzrle_encode_buffer_func = xbzrle_encode_buffer_avx512; - } - } - } - return ; -} -#endif - static void test_uleb(void) { uint32_t i, val; @@ -83,8 +54,8 @@ static void test_encode_decode_zero(void) buffer[1000 + diff_len + 5] = 105; /* encode zero page */ - dlen = xbzrle_encode_buffer_func(buffer, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == 0); g_free(buffer); @@ -107,8 +78,8 @@ static void test_encode_decode_unchanged(void) test[1000 + diff_len + 5] = 109; /* test unchanged buffer */ - dlen = xbzrle_encode_buffer_func(test, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == 0); g_free(test); @@ -125,8 +96,8 @@ static void test_encode_decode_1_byte(void) test[XBZRLE_PAGE_SIZE - 1] = 1; - dlen = xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == (uleb128_encode_small(&buf[0], 4095) + 2)); rc = xbzrle_decode_buffer(compressed, dlen, buffer, XBZRLE_PAGE_SIZE); @@ -150,8 +121,8 @@ static void test_encode_decode_overflow(void) } /* encode overflow */ - rc = xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + rc = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(rc == -1); g_free(buffer); @@ -181,8 +152,8 @@ static void encode_decode_range(void) test[1000 + diff_len + 5] = 109; /* test encode/decode */ - dlen = xbzrle_encode_buffer_func(test, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); rc = xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); g_assert(rc < XBZRLE_PAGE_SIZE); diff --git a/util/bufferiszero.c b/util/bufferiszero.c index 1886bc5..3e6a5df 100644 --- a/util/bufferiszero.c +++ b/util/bufferiszero.c @@ -24,6 +24,7 @@ #include "qemu/osdep.h" #include "qemu/cutils.h" #include "qemu/bswap.h" +#include "host/cpuinfo.h" static bool buffer_zero_int(const void *buf, size_t len) @@ -184,111 +185,75 @@ buffer_zero_avx512(const void *buf, size_t len) } #endif /* CONFIG_AVX512F_OPT */ - -/* Note that for test_buffer_is_zero_next_accel, the most preferred - * ISA must have the least significant bit. - */ -#define CACHE_AVX512F 1 -#define CACHE_AVX2 2 -#define CACHE_SSE4 4 -#define CACHE_SSE2 8 - -/* Make sure that these variables are appropriately initialized when +/* + * Make sure that these variables are appropriately initialized when * SSE2 is enabled on the compiler command-line, but the compiler is * too old to support CONFIG_AVX2_OPT. */ #if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT) -# define INIT_CACHE 0 -# define INIT_ACCEL buffer_zero_int +# define INIT_USED 0 +# define INIT_LENGTH 0 +# define INIT_ACCEL buffer_zero_int #else # ifndef __SSE2__ # error "ISA selection confusion" # endif -# define INIT_CACHE CACHE_SSE2 -# define INIT_ACCEL buffer_zero_sse2 +# define INIT_USED CPUINFO_SSE2 +# define INIT_LENGTH 64 +# define INIT_ACCEL buffer_zero_sse2 #endif -static unsigned cpuid_cache = INIT_CACHE; +static unsigned used_accel = INIT_USED; +static unsigned length_to_accel = INIT_LENGTH; static bool (*buffer_accel)(const void *, size_t) = INIT_ACCEL; -static int length_to_accel = 64; -static void init_accel(unsigned cache) +static unsigned __attribute__((noinline)) +select_accel_cpuinfo(unsigned info) { - bool (*fn)(const void *, size_t) = buffer_zero_int; - if (cache & CACHE_SSE2) { - fn = buffer_zero_sse2; - length_to_accel = 64; - } + /* Array is sorted in order of algorithm preference. */ + static const struct { + unsigned bit; + unsigned len; + bool (*fn)(const void *, size_t); + } all[] = { +#ifdef CONFIG_AVX512F_OPT + { CPUINFO_AVX512F, 256, buffer_zero_avx512 }, +#endif #ifdef CONFIG_AVX2_OPT - if (cache & CACHE_SSE4) { - fn = buffer_zero_sse4; - length_to_accel = 64; - } - if (cache & CACHE_AVX2) { - fn = buffer_zero_avx2; - length_to_accel = 128; - } + { CPUINFO_AVX2, 128, buffer_zero_avx2 }, + { CPUINFO_SSE4, 64, buffer_zero_sse4 }, #endif -#ifdef CONFIG_AVX512F_OPT - if (cache & CACHE_AVX512F) { - fn = buffer_zero_avx512; - length_to_accel = 256; + { CPUINFO_SSE2, 64, buffer_zero_sse2 }, + { CPUINFO_ALWAYS, 0, buffer_zero_int }, + }; + + for (unsigned i = 0; i < ARRAY_SIZE(all); ++i) { + if (info & all[i].bit) { + length_to_accel = all[i].len; + buffer_accel = all[i].fn; + return all[i].bit; + } } -#endif - buffer_accel = fn; + return 0; } #if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT) -#include "qemu/cpuid.h" - -static void __attribute__((constructor)) init_cpuid_cache(void) +static void __attribute__((constructor)) init_accel(void) { - unsigned max = __get_cpuid_max(0, NULL); - int a, b, c, d; - unsigned cache = 0; - - if (max >= 1) { - __cpuid(1, a, b, c, d); - if (d & bit_SSE2) { - cache |= CACHE_SSE2; - } - if (c & bit_SSE4_1) { - cache |= CACHE_SSE4; - } - - /* We must check that AVX is not just available, but usable. */ - if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) { - unsigned bv = xgetbv_low(0); - __cpuid_count(7, 0, a, b, c, d); - if ((bv & 0x6) == 0x6 && (b & bit_AVX2)) { - cache |= CACHE_AVX2; - } - /* 0xe6: - * XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15 - * and ZMM16-ZMM31 state are enabled by OS) - * XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS) - */ - if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512F)) { - cache |= CACHE_AVX512F; - } - } - } - cpuid_cache = cache; - init_accel(cache); + used_accel = select_accel_cpuinfo(cpuinfo_init()); } #endif /* CONFIG_AVX2_OPT */ bool test_buffer_is_zero_next_accel(void) { - /* If no bits set, we just tested buffer_zero_int, and there - are no more acceleration options to test. */ - if (cpuid_cache == 0) { - return false; - } - /* Disable the accelerator we used before and select a new one. */ - cpuid_cache &= cpuid_cache - 1; - init_accel(cpuid_cache); - return true; + /* + * Accumulate the accelerators that we've already tested, and + * remove them from the set to test this round. We'll get back + * a zero from select_accel_cpuinfo when there are no more. + */ + unsigned used = select_accel_cpuinfo(cpuinfo & ~used_accel); + used_accel |= used; + return used; } static bool select_accel_fn(const void *buf, size_t len) diff --git a/util/cpuinfo-aarch64.c b/util/cpuinfo-aarch64.c new file mode 100644 index 0000000..f99acb7 --- /dev/null +++ b/util/cpuinfo-aarch64.c @@ -0,0 +1,67 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Host specific cpu indentification for AArch64. + */ + +#include "qemu/osdep.h" +#include "host/cpuinfo.h" + +#ifdef CONFIG_LINUX +# ifdef CONFIG_GETAUXVAL +# include <sys/auxv.h> +# else +# include <asm/hwcap.h> +# include "elf.h" +# endif +#endif +#ifdef CONFIG_DARWIN +# include <sys/sysctl.h> +#endif + +unsigned cpuinfo; + +#ifdef CONFIG_DARWIN +static bool sysctl_for_bool(const char *name) +{ + int val = 0; + size_t len = sizeof(val); + + if (sysctlbyname(name, &val, &len, NULL, 0) == 0) { + return val != 0; + } + + /* + * We might in the future ask for properties not present in older kernels, + * but we're only asking about static properties, all of which should be + * 'int'. So we shouln't see ENOMEM (val too small), or any of the other + * more exotic errors. + */ + assert(errno == ENOENT); + return false; +} +#endif + +/* Called both as constructor and (possibly) via other constructors. */ +unsigned __attribute__((constructor)) cpuinfo_init(void) +{ + unsigned info = cpuinfo; + + if (info) { + return info; + } + + info = CPUINFO_ALWAYS; + +#ifdef CONFIG_LINUX + unsigned long hwcap = qemu_getauxval(AT_HWCAP); + info |= (hwcap & HWCAP_ATOMICS ? CPUINFO_LSE : 0); + info |= (hwcap & HWCAP_USCAT ? CPUINFO_LSE2 : 0); +#endif +#ifdef CONFIG_DARWIN + info |= sysctl_for_bool("hw.optional.arm.FEAT_LSE") * CPUINFO_LSE; + info |= sysctl_for_bool("hw.optional.arm.FEAT_LSE2") * CPUINFO_LSE2; +#endif + + cpuinfo = info; + return info; +} diff --git a/util/cpuinfo-i386.c b/util/cpuinfo-i386.c new file mode 100644 index 0000000..ab6143d --- /dev/null +++ b/util/cpuinfo-i386.c @@ -0,0 +1,99 @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * Host specific cpu indentification for x86. + */ + +#include "qemu/osdep.h" +#include "host/cpuinfo.h" +#ifdef CONFIG_CPUID_H +# include "qemu/cpuid.h" +#endif + +unsigned cpuinfo; + +/* Called both as constructor and (possibly) via other constructors. */ +unsigned __attribute__((constructor)) cpuinfo_init(void) +{ + unsigned info = cpuinfo; + + if (info) { + return info; + } + +#ifdef CONFIG_CPUID_H + unsigned max, a, b, c, d, b7 = 0, c7 = 0; + + max = __get_cpuid_max(0, 0); + + if (max >= 7) { + __cpuid_count(7, 0, a, b7, c7, d); + info |= (b7 & bit_BMI ? CPUINFO_BMI1 : 0); + info |= (b7 & bit_BMI2 ? CPUINFO_BMI2 : 0); + } + + if (max >= 1) { + __cpuid(1, a, b, c, d); + + info |= (d & bit_CMOV ? CPUINFO_CMOV : 0); + info |= (d & bit_SSE2 ? CPUINFO_SSE2 : 0); + info |= (c & bit_SSE4_1 ? CPUINFO_SSE4 : 0); + info |= (c & bit_MOVBE ? CPUINFO_MOVBE : 0); + info |= (c & bit_POPCNT ? CPUINFO_POPCNT : 0); + + /* For AVX features, we must check available and usable. */ + if ((c & bit_AVX) && (c & bit_OSXSAVE)) { + unsigned bv = xgetbv_low(0); + + if ((bv & 6) == 6) { + info |= CPUINFO_AVX1; + info |= (b7 & bit_AVX2 ? CPUINFO_AVX2 : 0); + + if ((bv & 0xe0) == 0xe0) { + info |= (b7 & bit_AVX512F ? CPUINFO_AVX512F : 0); + info |= (b7 & bit_AVX512VL ? CPUINFO_AVX512VL : 0); + info |= (b7 & bit_AVX512BW ? CPUINFO_AVX512BW : 0); + info |= (b7 & bit_AVX512DQ ? CPUINFO_AVX512DQ : 0); + info |= (c7 & bit_AVX512VBMI2 ? CPUINFO_AVX512VBMI2 : 0); + } + + /* + * The Intel SDM has added: + * Processors that enumerate support for Intel® AVX + * (by setting the feature flag CPUID.01H:ECX.AVX[bit 28]) + * guarantee that the 16-byte memory operations performed + * by the following instructions will always be carried + * out atomically: + * - MOVAPD, MOVAPS, and MOVDQA. + * - VMOVAPD, VMOVAPS, and VMOVDQA when encoded with VEX.128. + * - VMOVAPD, VMOVAPS, VMOVDQA32, and VMOVDQA64 when encoded + * with EVEX.128 and k0 (masking disabled). + * Note that these instructions require the linear addresses + * of their memory operands to be 16-byte aligned. + * + * AMD has provided an even stronger guarantee that processors + * with AVX provide 16-byte atomicity for all cachable, + * naturally aligned single loads and stores, e.g. MOVDQU. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104688 + */ + __cpuid(0, a, b, c, d); + if (c == signature_INTEL_ecx) { + info |= CPUINFO_ATOMIC_VMOVDQA; + } else if (c == signature_AMD_ecx) { + info |= CPUINFO_ATOMIC_VMOVDQA | CPUINFO_ATOMIC_VMOVDQU; + } + } + } + } + + max = __get_cpuid_max(0x8000000, 0); + if (max >= 1) { + __cpuid(0x80000001, a, b, c, d); + info |= (c & bit_LZCNT ? CPUINFO_LZCNT : 0); + } +#endif + + info |= CPUINFO_ALWAYS; + cpuinfo = info; + return info; +} diff --git a/util/meson.build b/util/meson.build index e1f1c39..3a93071 100644 --- a/util/meson.build +++ b/util/meson.build @@ -108,3 +108,9 @@ if have_block endif util_ss.add(when: 'CONFIG_LINUX', if_true: files('vfio-helpers.c')) endif + +if cpu == 'aarch64' + util_ss.add(files('cpuinfo-aarch64.c')) +elif cpu in ['x86', 'x86_64'] + util_ss.add(files('cpuinfo-i386.c')) +endif |