diff options
Diffstat (limited to 'accel')
| -rw-r--r-- | accel/accel.c | 3 | ||||
| -rw-r--r-- | accel/kvm/kvm-all.c | 4 | ||||
| -rw-r--r-- | accel/kvm/trace-events | 2 | ||||
| -rw-r--r-- | accel/tcg/cputlb.c | 5 | ||||
| -rw-r--r-- | accel/tcg/trace-events | 2 | ||||
| -rw-r--r-- | accel/tcg/translate-all.c | 102 | ||||
| -rw-r--r-- | accel/tcg/translator.c | 15 |
7 files changed, 81 insertions, 52 deletions
diff --git a/accel/accel.c b/accel/accel.c index 8deb475b5d..454fef9d92 100644 --- a/accel/accel.c +++ b/accel/accel.c @@ -65,8 +65,9 @@ static int accel_init_machine(AccelClass *acc, MachineState *ms) ms->accelerator = NULL; *(acc->allowed) = false; object_unref(OBJECT(accel)); + } else { + object_set_accelerator_compat_props(acc->compat_props); } - object_set_accelerator_compat_props(acc->compat_props); return ret; } diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 241db496c3..524c4ddfbd 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -1798,7 +1798,7 @@ static int kvm_handle_internal_error(CPUState *cpu, struct kvm_run *run) if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) { fprintf(stderr, "emulation failure\n"); if (!kvm_arch_stop_on_emulation_error(cpu)) { - cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_CODE); + cpu_dump_state(cpu, stderr, CPU_DUMP_CODE); return EXCP_INTERRUPT; } } @@ -2089,7 +2089,7 @@ int kvm_cpu_exec(CPUState *cpu) qemu_mutex_lock_iothread(); if (ret < 0) { - cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_CODE); + cpu_dump_state(cpu, stderr, CPU_DUMP_CODE); vm_stop(RUN_STATE_INTERNAL_ERROR); } diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events index 8841025d68..33c5b1b3af 100644 --- a/accel/kvm/trace-events +++ b/accel/kvm/trace-events @@ -1,4 +1,4 @@ -# Trace events for debugging and performance instrumentation +# See docs/devel/tracing.txt for syntax documentation. # kvm-all.c kvm_ioctl(int type, void *arg) "type 0x%x, arg %p" diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 88cc8389e9..f2f618217d 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -878,10 +878,11 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, CPUTLBEntry *entry; target_ulong tlb_addr; - tlb_fill(cpu, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr); + tlb_fill(cpu, addr, size, access_type, mmu_idx, retaddr); entry = tlb_entry(env, mmu_idx, addr); - tlb_addr = entry->addr_read; + tlb_addr = (access_type == MMU_DATA_LOAD ? + entry->addr_read : entry->addr_code); if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) { /* RAM access */ uintptr_t haddr = addr + entry->addend; diff --git a/accel/tcg/trace-events b/accel/tcg/trace-events index c22ad60af7..01852217a6 100644 --- a/accel/tcg/trace-events +++ b/accel/tcg/trace-events @@ -1,4 +1,4 @@ -# Trace events for debugging and performance instrumentation +# See docs/devel/tracing.txt for syntax documentation. # TCG related tracing (mostly disabled by default) # cpu-exec.c diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 8f593b926f..20b59f93f4 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -50,6 +50,7 @@ #include "translate-all.h" #include "qemu/bitmap.h" #include "qemu/error-report.h" +#include "qemu/qemu-print.h" #include "qemu/timer.h" #include "qemu/main-loop.h" #include "exec/log.h" @@ -1673,7 +1674,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, tb_page_addr_t phys_pc, phys_page2; target_ulong virt_page2; tcg_insn_unit *gen_code_buf; - int gen_code_size, search_size; + int gen_code_size, search_size, max_insns; #ifdef CONFIG_PROFILER TCGProfile *prof = &tcg_ctx->prof; int64_t ti; @@ -1691,6 +1692,17 @@ TranslationBlock *tb_gen_code(CPUState *cpu, cflags &= ~CF_CLUSTER_MASK; cflags |= cpu->cluster_index << CF_CLUSTER_SHIFT; + max_insns = cflags & CF_COUNT_MASK; + if (max_insns == 0) { + max_insns = CF_COUNT_MASK; + } + if (max_insns > TCG_MAX_INSNS) { + max_insns = TCG_MAX_INSNS; + } + if (cpu->singlestep_enabled || singlestep) { + max_insns = 1; + } + buffer_overflow: tb = tb_alloc(pc); if (unlikely(!tb)) { @@ -1710,6 +1722,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, tb->cflags = cflags; tb->trace_vcpu_dstate = *cpu->trace_dstate; tcg_ctx->tb_cflags = cflags; + tb_overflow: #ifdef CONFIG_PROFILER /* includes aborted translations because of exceptions */ @@ -1720,7 +1733,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, tcg_func_start(tcg_ctx); tcg_ctx->cpu = ENV_GET_CPU(env); - gen_intermediate_code(cpu, tb); + gen_intermediate_code(cpu, tb, max_insns); tcg_ctx->cpu = NULL; trace_translate_block(tb, tb->pc, tb->tc.ptr); @@ -1743,14 +1756,39 @@ TranslationBlock *tb_gen_code(CPUState *cpu, ti = profile_getclock(); #endif - /* ??? Overflow could be handled better here. In particular, we - don't need to re-do gen_intermediate_code, nor should we re-do - the tcg optimization currently hidden inside tcg_gen_code. All - that should be required is to flush the TBs, allocate a new TB, - re-initialize it per above, and re-do the actual code generation. */ gen_code_size = tcg_gen_code(tcg_ctx, tb); if (unlikely(gen_code_size < 0)) { - goto buffer_overflow; + switch (gen_code_size) { + case -1: + /* + * Overflow of code_gen_buffer, or the current slice of it. + * + * TODO: We don't need to re-do gen_intermediate_code, nor + * should we re-do the tcg optimization currently hidden + * inside tcg_gen_code. All that should be required is to + * flush the TBs, allocate a new TB, re-initialize it per + * above, and re-do the actual code generation. + */ + goto buffer_overflow; + + case -2: + /* + * The code generated for the TranslationBlock is too large. + * The maximum size allowed by the unwind info is 64k. + * There may be stricter constraints from relocations + * in the tcg backend. + * + * Try again with half as many insns as we attempted this time. + * If a single insn overflows, there's a bug somewhere... + */ + max_insns = tb->icount; + assert(max_insns > 1); + max_insns /= 2; + goto tb_overflow; + + default: + g_assert_not_reached(); + } } search_size = encode_search(tb, (void *)gen_code_buf + gen_code_size); if (unlikely(search_size < 0)) { @@ -2214,8 +2252,7 @@ void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr) tb_jmp_cache_clear_page(cpu, addr); } -static void print_qht_statistics(FILE *f, fprintf_function cpu_fprintf, - struct qht_stats hst) +static void print_qht_statistics(struct qht_stats hst) { uint32_t hgram_opts; size_t hgram_bins; @@ -2224,7 +2261,7 @@ static void print_qht_statistics(FILE *f, fprintf_function cpu_fprintf, if (!hst.head_buckets) { return; } - cpu_fprintf(f, "TB hash buckets %zu/%zu (%0.2f%% head buckets used)\n", + qemu_printf("TB hash buckets %zu/%zu (%0.2f%% head buckets used)\n", hst.used_head_buckets, hst.head_buckets, (double)hst.used_head_buckets / hst.head_buckets * 100); @@ -2234,7 +2271,7 @@ static void print_qht_statistics(FILE *f, fprintf_function cpu_fprintf, hgram_opts |= QDIST_PR_NODECIMAL; } hgram = qdist_pr(&hst.occupancy, 10, hgram_opts); - cpu_fprintf(f, "TB hash occupancy %0.2f%% avg chain occ. Histogram: %s\n", + qemu_printf("TB hash occupancy %0.2f%% avg chain occ. Histogram: %s\n", qdist_avg(&hst.occupancy) * 100, hgram); g_free(hgram); @@ -2247,7 +2284,7 @@ static void print_qht_statistics(FILE *f, fprintf_function cpu_fprintf, hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE; } hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts); - cpu_fprintf(f, "TB hash avg chain %0.3f buckets. Histogram: %s\n", + qemu_printf("TB hash avg chain %0.3f buckets. Histogram: %s\n", qdist_avg(&hst.chain), hgram); g_free(hgram); } @@ -2285,7 +2322,7 @@ static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data) return false; } -void dump_exec_info(FILE *f, fprintf_function cpu_fprintf) +void dump_exec_info(void) { struct tb_tree_stats tst = {}; struct qht_stats hst; @@ -2294,48 +2331,49 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf) tcg_tb_foreach(tb_tree_stats_iter, &tst); nb_tbs = tst.nb_tbs; /* XXX: avoid using doubles ? */ - cpu_fprintf(f, "Translation buffer state:\n"); + qemu_printf("Translation buffer state:\n"); /* * Report total code size including the padding and TB structs; * otherwise users might think "-tb-size" is not honoured. * For avg host size we use the precise numbers from tb_tree_stats though. */ - cpu_fprintf(f, "gen code size %zu/%zu\n", + qemu_printf("gen code size %zu/%zu\n", tcg_code_size(), tcg_code_capacity()); - cpu_fprintf(f, "TB count %zu\n", nb_tbs); - cpu_fprintf(f, "TB avg target size %zu max=%zu bytes\n", + qemu_printf("TB count %zu\n", nb_tbs); + qemu_printf("TB avg target size %zu max=%zu bytes\n", nb_tbs ? tst.target_size / nb_tbs : 0, tst.max_target_size); - cpu_fprintf(f, "TB avg host size %zu bytes (expansion ratio: %0.1f)\n", + qemu_printf("TB avg host size %zu bytes (expansion ratio: %0.1f)\n", nb_tbs ? tst.host_size / nb_tbs : 0, tst.target_size ? (double)tst.host_size / tst.target_size : 0); - cpu_fprintf(f, "cross page TB count %zu (%zu%%)\n", tst.cross_page, - nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0); - cpu_fprintf(f, "direct jump count %zu (%zu%%) (2 jumps=%zu %zu%%)\n", + qemu_printf("cross page TB count %zu (%zu%%)\n", tst.cross_page, + nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0); + qemu_printf("direct jump count %zu (%zu%%) (2 jumps=%zu %zu%%)\n", tst.direct_jmp_count, nb_tbs ? (tst.direct_jmp_count * 100) / nb_tbs : 0, tst.direct_jmp2_count, nb_tbs ? (tst.direct_jmp2_count * 100) / nb_tbs : 0); qht_statistics_init(&tb_ctx.htable, &hst); - print_qht_statistics(f, cpu_fprintf, hst); + print_qht_statistics(hst); qht_statistics_destroy(&hst); - cpu_fprintf(f, "\nStatistics:\n"); - cpu_fprintf(f, "TB flush count %u\n", + qemu_printf("\nStatistics:\n"); + qemu_printf("TB flush count %u\n", atomic_read(&tb_ctx.tb_flush_count)); - cpu_fprintf(f, "TB invalidate count %zu\n", tcg_tb_phys_invalidate_count()); + qemu_printf("TB invalidate count %zu\n", + tcg_tb_phys_invalidate_count()); tlb_flush_counts(&flush_full, &flush_part, &flush_elide); - cpu_fprintf(f, "TLB full flushes %zu\n", flush_full); - cpu_fprintf(f, "TLB partial flushes %zu\n", flush_part); - cpu_fprintf(f, "TLB elided flushes %zu\n", flush_elide); - tcg_dump_info(f, cpu_fprintf); + qemu_printf("TLB full flushes %zu\n", flush_full); + qemu_printf("TLB partial flushes %zu\n", flush_part); + qemu_printf("TLB elided flushes %zu\n", flush_elide); + tcg_dump_info(); } -void dump_opcount_info(FILE *f, fprintf_function cpu_fprintf) +void dump_opcount_info(void) { - tcg_dump_op_count(f, cpu_fprintf); + tcg_dump_op_count(); } #else /* CONFIG_USER_ONLY */ diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index afd0a49ea6..8d65ead708 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -32,7 +32,7 @@ void translator_loop_temp_check(DisasContextBase *db) } void translator_loop(const TranslatorOps *ops, DisasContextBase *db, - CPUState *cpu, TranslationBlock *tb) + CPUState *cpu, TranslationBlock *tb, int max_insns) { int bp_insn = 0; @@ -42,20 +42,9 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, db->pc_next = db->pc_first; db->is_jmp = DISAS_NEXT; db->num_insns = 0; + db->max_insns = max_insns; db->singlestep_enabled = cpu->singlestep_enabled; - /* Instruction counting */ - db->max_insns = tb_cflags(db->tb) & CF_COUNT_MASK; - if (db->max_insns == 0) { - db->max_insns = CF_COUNT_MASK; - } - if (db->max_insns > TCG_MAX_INSNS) { - db->max_insns = TCG_MAX_INSNS; - } - if (db->singlestep_enabled || singlestep) { - db->max_insns = 1; - } - ops->init_disas_context(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ |