diff options
Diffstat (limited to 'accel')
-rw-r--r-- | accel/stubs/tcg-stub.c | 2 | ||||
-rw-r--r-- | accel/tcg/cpu-exec.c | 64 | ||||
-rw-r--r-- | accel/tcg/cputlb.c | 21 | ||||
-rw-r--r-- | accel/tcg/internal.h | 10 | ||||
-rw-r--r-- | accel/tcg/perf.c | 2 | ||||
-rw-r--r-- | accel/tcg/plugin-gen.c | 32 | ||||
-rw-r--r-- | accel/tcg/tb-jmp-cache.h | 42 | ||||
-rw-r--r-- | accel/tcg/tb-maint.c | 10 | ||||
-rw-r--r-- | accel/tcg/translate-all.c | 18 | ||||
-rw-r--r-- | accel/tcg/translator.c | 6 | ||||
-rw-r--r-- | accel/tcg/user-exec.c | 5 |
11 files changed, 106 insertions, 106 deletions
diff --git a/accel/stubs/tcg-stub.c b/accel/stubs/tcg-stub.c index c1b0576..96af23d 100644 --- a/accel/stubs/tcg-stub.c +++ b/accel/stubs/tcg-stub.c @@ -25,7 +25,7 @@ void tcg_flush_jmp_cache(CPUState *cpu) { } -int probe_access_flags(CPUArchState *env, target_ulong addr, +int probe_access_flags(CPUArchState *env, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t retaddr) { diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index ef557e5..56aaf58 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -183,7 +183,7 @@ static bool tb_lookup_cmp(const void *p, const void *d) const TranslationBlock *tb = p; const struct tb_desc *desc = d; - if ((TARGET_TB_PCREL || tb_pc(tb) == desc->pc) && + if ((tb_cflags(tb) & CF_PCREL || tb->pc == desc->pc) && tb_page_addr0(tb) == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && @@ -235,7 +235,7 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, return NULL; } desc.page_addr0 = phys_pc; - h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : pc), + h = tb_hash_func(phys_pc, (cflags & CF_PCREL ? 0 : pc), flags, cflags, *cpu->trace_dstate); return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp); } @@ -254,21 +254,46 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, hash = tb_jmp_cache_hash_func(pc); jc = cpu->tb_jmp_cache; - tb = tb_jmp_cache_get_tb(jc, hash); - - if (likely(tb && - tb_jmp_cache_get_pc(jc, hash, tb) == pc && - tb->cs_base == cs_base && - tb->flags == flags && - tb->trace_vcpu_dstate == *cpu->trace_dstate && - tb_cflags(tb) == cflags)) { - return tb; - } - tb = tb_htable_lookup(cpu, pc, cs_base, flags, cflags); - if (tb == NULL) { - return NULL; + + if (cflags & CF_PCREL) { + /* Use acquire to ensure current load of pc from jc. */ + tb = qatomic_load_acquire(&jc->array[hash].tb); + + if (likely(tb && + jc->array[hash].pc == pc && + tb->cs_base == cs_base && + tb->flags == flags && + tb->trace_vcpu_dstate == *cpu->trace_dstate && + tb_cflags(tb) == cflags)) { + return tb; + } + tb = tb_htable_lookup(cpu, pc, cs_base, flags, cflags); + if (tb == NULL) { + return NULL; + } + jc->array[hash].pc = pc; + /* Use store_release on tb to ensure pc is written first. */ + qatomic_store_release(&jc->array[hash].tb, tb); + } else { + /* Use rcu_read to ensure current load of pc from *tb. */ + tb = qatomic_rcu_read(&jc->array[hash].tb); + + if (likely(tb && + tb->pc == pc && + tb->cs_base == cs_base && + tb->flags == flags && + tb->trace_vcpu_dstate == *cpu->trace_dstate && + tb_cflags(tb) == cflags)) { + return tb; + } + tb = tb_htable_lookup(cpu, pc, cs_base, flags, cflags); + if (tb == NULL) { + return NULL; + } + /* Use the pc value already stored in tb->pc. */ + qatomic_set(&jc->array[hash].tb, tb); } - tb_jmp_cache_set(jc, hash, tb, pc); + return tb; } @@ -457,9 +482,9 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) if (cc->tcg_ops->synchronize_from_tb) { cc->tcg_ops->synchronize_from_tb(cpu, last_tb); } else { - assert(!TARGET_TB_PCREL); + tcg_debug_assert(!(tb_cflags(last_tb) & CF_PCREL)); assert(cc->set_pc); - cc->set_pc(cpu, tb_pc(last_tb)); + cc->set_pc(cpu, last_tb->pc); } if (qemu_loglevel_mask(CPU_LOG_EXEC)) { target_ulong pc = log_pc(cpu, last_tb); @@ -957,7 +982,8 @@ cpu_exec_loop(CPUState *cpu, SyncClocks *sc) * for the fast lookup */ h = tb_jmp_cache_hash_func(pc); - tb_jmp_cache_set(cpu->tb_jmp_cache, h, tb, pc); + /* Use the pc value already stored in tb->pc. */ + qatomic_set(&cpu->tb_jmp_cache->array[h].tb, tb); } #ifndef CONFIG_USER_ONLY diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 4812d83..008ae7a 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -1589,12 +1589,12 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, return flags; } -int probe_access_full(CPUArchState *env, target_ulong addr, +int probe_access_full(CPUArchState *env, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, CPUTLBEntryFull **pfull, uintptr_t retaddr) { - int flags = probe_access_internal(env, addr, 0, access_type, mmu_idx, + int flags = probe_access_internal(env, addr, size, access_type, mmu_idx, nonfault, phost, pfull, retaddr); /* Handle clean RAM pages. */ @@ -1606,14 +1606,25 @@ int probe_access_full(CPUArchState *env, target_ulong addr, return flags; } -int probe_access_flags(CPUArchState *env, target_ulong addr, +int probe_access_flags(CPUArchState *env, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t retaddr) { CPUTLBEntryFull *full; + int flags; + + g_assert(-(addr | TARGET_PAGE_MASK) >= size); + + flags = probe_access_internal(env, addr, size, access_type, mmu_idx, + nonfault, phost, &full, retaddr); - return probe_access_full(env, addr, access_type, mmu_idx, - nonfault, phost, &full, retaddr); + /* Handle clean RAM pages. */ + if (unlikely(flags & TLB_NOTDIRTY)) { + notdirty_write(env_cpu(env), addr, 1, full, retaddr); + flags &= ~TLB_NOTDIRTY; + } + + return flags; } void *probe_access(CPUArchState *env, target_ulong addr, int size, diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index 130d7fd..96f198b 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -57,11 +57,11 @@ void cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, /* Return the current PC from CPU, which may be cached in TB. */ static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb) { -#if TARGET_TB_PCREL - return cpu->cc->get_pc(cpu); -#else - return tb_pc(tb); -#endif + if (tb_cflags(tb) & CF_PCREL) { + return cpu->cc->get_pc(cpu); + } else { + return tb->pc; + } } extern int64_t max_delay; diff --git a/accel/tcg/perf.c b/accel/tcg/perf.c index ae19f6e..65e35ea 100644 --- a/accel/tcg/perf.c +++ b/accel/tcg/perf.c @@ -328,7 +328,7 @@ void perf_report_code(uint64_t guest_pc, TranslationBlock *tb, for (insn = 0; insn < tb->icount; insn++) { /* FIXME: This replicates the restore_state_to_opc() logic. */ q[insn].address = tcg_ctx->gen_insn_data[insn][0]; - if (TARGET_TB_PCREL) { + if (tb_cflags(tb) & CF_PCREL) { q[insn].address |= (guest_pc & TARGET_PAGE_MASK); } else { #if defined(TARGET_I386) diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index 17a686b..c42a436 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -93,11 +93,13 @@ void HELPER(plugin_vcpu_mem_cb)(unsigned int vcpu_index, static void do_gen_mem_cb(TCGv vaddr, uint32_t info) { - TCGv_i32 cpu_index = tcg_temp_new_i32(); - TCGv_i32 meminfo = tcg_const_i32(info); - TCGv_i64 vaddr64 = tcg_temp_new_i64(); - TCGv_ptr udata = tcg_const_ptr(NULL); + TCGv_i32 cpu_index = tcg_temp_ebb_new_i32(); + TCGv_i32 meminfo = tcg_temp_ebb_new_i32(); + TCGv_i64 vaddr64 = tcg_temp_ebb_new_i64(); + TCGv_ptr udata = tcg_temp_ebb_new_ptr(); + tcg_gen_movi_i32(meminfo, info); + tcg_gen_movi_ptr(udata, 0); tcg_gen_ld_i32(cpu_index, cpu_env, -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index)); tcg_gen_extu_tl_i64(vaddr64, vaddr); @@ -112,9 +114,10 @@ static void do_gen_mem_cb(TCGv vaddr, uint32_t info) static void gen_empty_udata_cb(void) { - TCGv_i32 cpu_index = tcg_temp_new_i32(); - TCGv_ptr udata = tcg_const_ptr(NULL); /* will be overwritten later */ + TCGv_i32 cpu_index = tcg_temp_ebb_new_i32(); + TCGv_ptr udata = tcg_temp_ebb_new_ptr(); + tcg_gen_movi_ptr(udata, 0); tcg_gen_ld_i32(cpu_index, cpu_env, -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index)); gen_helper_plugin_vcpu_udata_cb(cpu_index, udata); @@ -129,9 +132,10 @@ static void gen_empty_udata_cb(void) */ static void gen_empty_inline_cb(void) { - TCGv_i64 val = tcg_temp_new_i64(); - TCGv_ptr ptr = tcg_const_ptr(NULL); /* overwritten later */ + TCGv_i64 val = tcg_temp_ebb_new_i64(); + TCGv_ptr ptr = tcg_temp_ebb_new_ptr(); + tcg_gen_movi_ptr(ptr, 0); tcg_gen_ld_i64(val, ptr, 0); /* pass an immediate != 0 so that it doesn't get optimized away */ tcg_gen_addi_i64(val, val, 0xdeadface); @@ -151,9 +155,9 @@ static void gen_empty_mem_cb(TCGv addr, uint32_t info) */ static void gen_empty_mem_helper(void) { - TCGv_ptr ptr; + TCGv_ptr ptr = tcg_temp_ebb_new_ptr(); - ptr = tcg_const_ptr(NULL); + tcg_gen_movi_ptr(ptr, 0); tcg_gen_st_ptr(ptr, cpu_env, offsetof(CPUState, plugin_mem_cbs) - offsetof(ArchCPU, env)); tcg_temp_free_ptr(ptr); @@ -626,8 +630,6 @@ static void inject_mem_disable_helper(struct qemu_plugin_insn *plugin_insn, /* called before finishing a TB with exit_tb, goto_tb or goto_ptr */ void plugin_gen_disable_mem_helpers(void) { - TCGv_ptr ptr; - /* * We could emit the clearing unconditionally and be done. However, this can * be wasteful if for instance plugins don't track memory accesses, or if @@ -640,10 +642,8 @@ void plugin_gen_disable_mem_helpers(void) if (!tcg_ctx->plugin_tb->mem_helper) { return; } - ptr = tcg_const_ptr(NULL); - tcg_gen_st_ptr(ptr, cpu_env, offsetof(CPUState, plugin_mem_cbs) - - offsetof(ArchCPU, env)); - tcg_temp_free_ptr(ptr); + tcg_gen_st_ptr(tcg_constant_ptr(NULL), cpu_env, + offsetof(CPUState, plugin_mem_cbs) - offsetof(ArchCPU, env)); } static void plugin_gen_tb_udata(const struct qemu_plugin_tb *ptb, diff --git a/accel/tcg/tb-jmp-cache.h b/accel/tcg/tb-jmp-cache.h index b3f6e78..bee87eb 100644 --- a/accel/tcg/tb-jmp-cache.h +++ b/accel/tcg/tb-jmp-cache.h @@ -14,53 +14,15 @@ /* * Accessed in parallel; all accesses to 'tb' must be atomic. - * For TARGET_TB_PCREL, accesses to 'pc' must be protected by - * a load_acquire/store_release to 'tb'. + * For CF_PCREL, accesses to 'pc' must be protected by a + * load_acquire/store_release to 'tb'. */ struct CPUJumpCache { struct rcu_head rcu; struct { TranslationBlock *tb; -#if TARGET_TB_PCREL target_ulong pc; -#endif } array[TB_JMP_CACHE_SIZE]; }; -static inline TranslationBlock * -tb_jmp_cache_get_tb(CPUJumpCache *jc, uint32_t hash) -{ -#if TARGET_TB_PCREL - /* Use acquire to ensure current load of pc from jc. */ - return qatomic_load_acquire(&jc->array[hash].tb); -#else - /* Use rcu_read to ensure current load of pc from *tb. */ - return qatomic_rcu_read(&jc->array[hash].tb); -#endif -} - -static inline target_ulong -tb_jmp_cache_get_pc(CPUJumpCache *jc, uint32_t hash, TranslationBlock *tb) -{ -#if TARGET_TB_PCREL - return jc->array[hash].pc; -#else - return tb_pc(tb); -#endif -} - -static inline void -tb_jmp_cache_set(CPUJumpCache *jc, uint32_t hash, - TranslationBlock *tb, target_ulong pc) -{ -#if TARGET_TB_PCREL - jc->array[hash].pc = pc; - /* Use store_release on tb to ensure pc is written first. */ - qatomic_store_release(&jc->array[hash].tb, tb); -#else - /* Use the pc value already stored in tb->pc. */ - qatomic_set(&jc->array[hash].tb, tb); -#endif -} - #endif /* ACCEL_TCG_TB_JMP_CACHE_H */ diff --git a/accel/tcg/tb-maint.c b/accel/tcg/tb-maint.c index b3d6529..efefa08 100644 --- a/accel/tcg/tb-maint.c +++ b/accel/tcg/tb-maint.c @@ -44,7 +44,7 @@ static bool tb_cmp(const void *ap, const void *bp) const TranslationBlock *a = ap; const TranslationBlock *b = bp; - return ((TARGET_TB_PCREL || tb_pc(a) == tb_pc(b)) && + return ((tb_cflags(a) & CF_PCREL || a->pc == b->pc) && a->cs_base == b->cs_base && a->flags == b->flags && (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && @@ -847,13 +847,13 @@ static void tb_jmp_cache_inval_tb(TranslationBlock *tb) { CPUState *cpu; - if (TARGET_TB_PCREL) { + if (tb_cflags(tb) & CF_PCREL) { /* A TB may be at any virtual address */ CPU_FOREACH(cpu) { tcg_flush_jmp_cache(cpu); } } else { - uint32_t h = tb_jmp_cache_hash_func(tb_pc(tb)); + uint32_t h = tb_jmp_cache_hash_func(tb->pc); CPU_FOREACH(cpu) { CPUJumpCache *jc = cpu->tb_jmp_cache; @@ -885,7 +885,7 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ phys_pc = tb_page_addr0(tb); - h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)), + h = tb_hash_func(phys_pc, (orig_cflags & CF_PCREL ? 0 : tb->pc), tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { return; @@ -966,7 +966,7 @@ TranslationBlock *tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, tb_record(tb, p, p2); /* add in the hash table */ - h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)), + h = tb_hash_func(phys_pc, (tb->cflags & CF_PCREL ? 0 : tb->pc), tb->flags, tb->cflags, tb->trace_vcpu_dstate); qht_insert(&tb_ctx.htable, tb, h, &existing_tb); diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 84f1293..4b5abc0 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -134,7 +134,7 @@ static int encode_search(TranslationBlock *tb, uint8_t *block) for (j = 0; j < TARGET_INSN_START_WORDS; ++j) { if (i == 0) { - prev = (!TARGET_TB_PCREL && j == 0 ? tb_pc(tb) : 0); + prev = (!(tb_cflags(tb) & CF_PCREL) && j == 0 ? tb->pc : 0); } else { prev = tcg_ctx->gen_insn_data[i - 1][j]; } @@ -169,8 +169,8 @@ static int cpu_unwind_data_from_tb(TranslationBlock *tb, uintptr_t host_pc, } memset(data, 0, sizeof(uint64_t) * TARGET_INSN_START_WORDS); - if (!TARGET_TB_PCREL) { - data[0] = tb_pc(tb); + if (!(tb_cflags(tb) & CF_PCREL)) { + data[0] = tb->pc; } /* @@ -280,7 +280,7 @@ static int setjmp_gen_code(CPUArchState *env, TranslationBlock *tb, tcg_func_start(tcg_ctx); tcg_ctx->cpu = env_cpu(env); - gen_intermediate_code(env_cpu(env), tb, *max_insns, pc, host_pc); + gen_intermediate_code(env_cpu(env), tb, max_insns, pc, host_pc); assert(tb->size != 0); tcg_ctx->cpu = NULL; *max_insns = tb->icount; @@ -340,9 +340,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu, gen_code_buf = tcg_ctx->code_gen_ptr; tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf); -#if !TARGET_TB_PCREL - tb->pc = pc; -#endif + if (!(cflags & CF_PCREL)) { + tb->pc = pc; + } tb->cs_base = cs_base; tb->flags = flags; tb->cflags = cflags; @@ -407,8 +407,8 @@ TranslationBlock *tb_gen_code(CPUState *cpu, tb->tc.size = gen_code_size; /* - * For TARGET_TB_PCREL, attribute all executions of the generated - * code to its first mapping. + * For CF_PCREL, attribute all executions of the generated code + * to its first mapping. */ perf_report_code(pc, tb, tcg_splitwx_to_rx(gen_code_buf)); diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index 15d11fa..d0babfe 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -42,7 +42,7 @@ bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest) return ((db->pc_first ^ dest) & TARGET_PAGE_MASK) == 0; } -void translator_loop(CPUState *cpu, TranslationBlock *tb, int max_insns, +void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns, target_ulong pc, void *host_pc, const TranslatorOps *ops, DisasContextBase *db) { @@ -55,7 +55,7 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int max_insns, db->pc_next = pc; db->is_jmp = DISAS_NEXT; db->num_insns = 0; - db->max_insns = max_insns; + db->max_insns = *max_insns; db->singlestep_enabled = cflags & CF_SINGLE_STEP; db->host_addr[0] = host_pc; db->host_addr[1] = NULL; @@ -78,7 +78,7 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int max_insns, plugin_enabled = plugin_gen_tb_start(cpu, db, cflags & CF_MEMI_ONLY); while (true) { - db->num_insns++; + *max_insns = ++db->num_insns; ops->insn_start(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index ae67d84..7b37fd2 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -761,13 +761,14 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, cpu_loop_exit_sigsegv(env_cpu(env), addr, access_type, maperr, ra); } -int probe_access_flags(CPUArchState *env, target_ulong addr, +int probe_access_flags(CPUArchState *env, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t ra) { int flags; - flags = probe_access_internal(env, addr, 0, access_type, nonfault, ra); + g_assert(-(addr | TARGET_PAGE_MASK) >= size); + flags = probe_access_internal(env, addr, size, access_type, nonfault, ra); *phost = flags ? NULL : g2h(env_cpu(env), addr); return flags; } |