aboutsummaryrefslogtreecommitdiff
path: root/accel/tcg
diff options
context:
space:
mode:
Diffstat (limited to 'accel/tcg')
-rw-r--r--accel/tcg/cpu-exec.c1
-rw-r--r--accel/tcg/cputlb.c37
-rw-r--r--accel/tcg/internal-common.h2
-rw-r--r--accel/tcg/meson.build11
-rw-r--r--accel/tcg/monitor.c209
-rw-r--r--accel/tcg/plugin-gen.c30
-rw-r--r--accel/tcg/tcg-accel-ops-mttcg.c1
-rw-r--r--accel/tcg/tcg-accel-ops.c12
-rw-r--r--accel/tcg/tcg-all.c9
-rw-r--r--accel/tcg/tcg-stats.c219
-rw-r--r--accel/tcg/translate-all.c6
11 files changed, 303 insertions, 234 deletions
diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index cc5f362..713bdb2 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -1039,6 +1039,7 @@ bool tcg_exec_realizefn(CPUState *cpu, Error **errp)
assert(tcg_ops->cpu_exec_halt);
assert(tcg_ops->cpu_exec_interrupt);
assert(tcg_ops->cpu_exec_reset);
+ assert(tcg_ops->pointer_wrap);
#endif /* !CONFIG_USER_ONLY */
assert(tcg_ops->translate_code);
assert(tcg_ops->get_tb_cpu_state);
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index 5f6d7c6..87e14bd 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -1773,6 +1773,9 @@ static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
l->page[1].size = l->page[0].size - size0;
l->page[0].size = size0;
+ l->page[1].addr = cpu->cc->tcg_ops->pointer_wrap(cpu, l->mmu_idx,
+ l->page[1].addr, addr);
+
/*
* Lookup both pages, recognizing exceptions from either. If the
* second lookup potentially resized, refresh first CPUTLBEntryFull.
@@ -1871,8 +1874,12 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
goto stop_the_world;
}
- /* Collect tlb flags for read. */
+ /* Finish collecting tlb flags for both read and write. */
+ full = &cpu->neg.tlb.d[mmu_idx].fulltlb[index];
tlb_addr |= tlbe->addr_read;
+ tlb_addr &= TLB_FLAGS_MASK & ~TLB_FORCE_SLOW;
+ tlb_addr |= full->slow_flags[MMU_DATA_STORE];
+ tlb_addr |= full->slow_flags[MMU_DATA_LOAD];
/* Notice an IO access or a needs-MMU-lookup access */
if (unlikely(tlb_addr & (TLB_MMIO | TLB_DISCARD_WRITE))) {
@@ -1882,13 +1889,12 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
}
hostaddr = (void *)((uintptr_t)addr + tlbe->addend);
- full = &cpu->neg.tlb.d[mmu_idx].fulltlb[index];
if (unlikely(tlb_addr & TLB_NOTDIRTY)) {
notdirty_write(cpu, addr, size, full, retaddr);
}
- if (unlikely(tlb_addr & TLB_FORCE_SLOW)) {
+ if (unlikely(tlb_addr & TLB_WATCHPOINT)) {
int wp_flags = 0;
if (full->slow_flags[MMU_DATA_STORE] & TLB_WATCHPOINT) {
@@ -1897,10 +1903,8 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
if (full->slow_flags[MMU_DATA_LOAD] & TLB_WATCHPOINT) {
wp_flags |= BP_MEM_READ;
}
- if (wp_flags) {
- cpu_check_watchpoint(cpu, addr, size,
- full->attrs, wp_flags, retaddr);
- }
+ cpu_check_watchpoint(cpu, addr, size,
+ full->attrs, wp_flags, retaddr);
}
return hostaddr;
@@ -2926,3 +2930,22 @@ uint64_t cpu_ldq_code_mmu(CPUArchState *env, vaddr addr,
{
return do_ld8_mmu(env_cpu(env), addr, oi, retaddr, MMU_INST_FETCH);
}
+
+/*
+ * Common pointer_wrap implementations.
+ */
+
+/*
+ * To be used for strict alignment targets.
+ * Because no accesses are unaligned, no accesses wrap either.
+ */
+vaddr cpu_pointer_wrap_notreached(CPUState *cs, int idx, vaddr res, vaddr base)
+{
+ g_assert_not_reached();
+}
+
+/* To be used for strict 32-bit targets. */
+vaddr cpu_pointer_wrap_uint32(CPUState *cs, int idx, vaddr res, vaddr base)
+{
+ return (uint32_t)res;
+}
diff --git a/accel/tcg/internal-common.h b/accel/tcg/internal-common.h
index 1dbc45d..6adfeef 100644
--- a/accel/tcg/internal-common.h
+++ b/accel/tcg/internal-common.h
@@ -139,4 +139,6 @@ G_NORETURN void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr);
void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr);
void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr);
+void tcg_get_stats(AccelState *accel, GString *buf);
+
#endif
diff --git a/accel/tcg/meson.build b/accel/tcg/meson.build
index d6f533f..002aa8f 100644
--- a/accel/tcg/meson.build
+++ b/accel/tcg/meson.build
@@ -1,4 +1,4 @@
-if not get_option('tcg').allowed()
+if not have_tcg
subdir_done()
endif
@@ -11,6 +11,7 @@ tcg_ss.add(files(
'tcg-runtime-gvec.c',
'tb-maint.c',
'tcg-all.c',
+ 'tcg-stats.c',
'translate-all.c',
'translator.c',
))
@@ -18,15 +19,15 @@ if get_option('plugins')
tcg_ss.add(files('plugin-gen.c'))
endif
-libuser_ss.add_all(tcg_ss)
-libsystem_ss.add_all(tcg_ss)
+user_ss.add_all(tcg_ss)
+system_ss.add_all(tcg_ss)
-libuser_ss.add(files(
+user_ss.add(files(
'user-exec.c',
'user-exec-stub.c',
))
-libsystem_ss.add(files(
+system_ss.add(files(
'cputlb.c',
'icount-common.c',
'monitor.c',
diff --git a/accel/tcg/monitor.c b/accel/tcg/monitor.c
index 1c182b6..be5c195 100644
--- a/accel/tcg/monitor.c
+++ b/accel/tcg/monitor.c
@@ -7,197 +7,13 @@
*/
#include "qemu/osdep.h"
-#include "qemu/accel.h"
-#include "qemu/qht.h"
#include "qapi/error.h"
#include "qapi/type-helpers.h"
#include "qapi/qapi-commands-machine.h"
#include "monitor/monitor.h"
-#include "system/cpu-timers.h"
-#include "exec/icount.h"
#include "system/tcg.h"
#include "tcg/tcg.h"
#include "internal-common.h"
-#include "tb-context.h"
-
-
-static void dump_drift_info(GString *buf)
-{
- if (!icount_enabled()) {
- return;
- }
-
- g_string_append_printf(buf, "Host - Guest clock %"PRIi64" ms\n",
- (cpu_get_clock() - icount_get()) / SCALE_MS);
- if (icount_align_option) {
- g_string_append_printf(buf, "Max guest delay %"PRIi64" ms\n",
- -max_delay / SCALE_MS);
- g_string_append_printf(buf, "Max guest advance %"PRIi64" ms\n",
- max_advance / SCALE_MS);
- } else {
- g_string_append_printf(buf, "Max guest delay NA\n");
- g_string_append_printf(buf, "Max guest advance NA\n");
- }
-}
-
-static void dump_accel_info(GString *buf)
-{
- AccelState *accel = current_accel();
- bool one_insn_per_tb = object_property_get_bool(OBJECT(accel),
- "one-insn-per-tb",
- &error_fatal);
-
- g_string_append_printf(buf, "Accelerator settings:\n");
- g_string_append_printf(buf, "one-insn-per-tb: %s\n\n",
- one_insn_per_tb ? "on" : "off");
-}
-
-static void print_qht_statistics(struct qht_stats hst, GString *buf)
-{
- uint32_t hgram_opts;
- size_t hgram_bins;
- char *hgram;
-
- if (!hst.head_buckets) {
- return;
- }
- g_string_append_printf(buf, "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);
-
- hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
- hgram_opts |= QDIST_PR_100X | QDIST_PR_PERCENT;
- if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
- hgram_opts |= QDIST_PR_NODECIMAL;
- }
- hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
- g_string_append_printf(buf, "TB hash occupancy %0.2f%% avg chain occ. "
- "Histogram: %s\n",
- qdist_avg(&hst.occupancy) * 100, hgram);
- g_free(hgram);
-
- hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
- hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
- if (hgram_bins > 10) {
- hgram_bins = 10;
- } else {
- hgram_bins = 0;
- hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
- }
- hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
- g_string_append_printf(buf, "TB hash avg chain %0.3f buckets. "
- "Histogram: %s\n",
- qdist_avg(&hst.chain), hgram);
- g_free(hgram);
-}
-
-struct tb_tree_stats {
- size_t nb_tbs;
- size_t host_size;
- size_t target_size;
- size_t max_target_size;
- size_t direct_jmp_count;
- size_t direct_jmp2_count;
- size_t cross_page;
-};
-
-static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data)
-{
- const TranslationBlock *tb = value;
- struct tb_tree_stats *tst = data;
-
- tst->nb_tbs++;
- tst->host_size += tb->tc.size;
- tst->target_size += tb->size;
- if (tb->size > tst->max_target_size) {
- tst->max_target_size = tb->size;
- }
- if (tb->page_addr[1] != -1) {
- tst->cross_page++;
- }
- if (tb->jmp_reset_offset[0] != TB_JMP_OFFSET_INVALID) {
- tst->direct_jmp_count++;
- if (tb->jmp_reset_offset[1] != TB_JMP_OFFSET_INVALID) {
- tst->direct_jmp2_count++;
- }
- }
- return false;
-}
-
-static void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)
-{
- CPUState *cpu;
- size_t full = 0, part = 0, elide = 0;
-
- CPU_FOREACH(cpu) {
- full += qatomic_read(&cpu->neg.tlb.c.full_flush_count);
- part += qatomic_read(&cpu->neg.tlb.c.part_flush_count);
- elide += qatomic_read(&cpu->neg.tlb.c.elide_flush_count);
- }
- *pfull = full;
- *ppart = part;
- *pelide = elide;
-}
-
-static void tcg_dump_info(GString *buf)
-{
- g_string_append_printf(buf, "[TCG profiler not compiled]\n");
-}
-
-static void dump_exec_info(GString *buf)
-{
- struct tb_tree_stats tst = {};
- struct qht_stats hst;
- size_t nb_tbs, flush_full, flush_part, flush_elide;
-
- tcg_tb_foreach(tb_tree_stats_iter, &tst);
- nb_tbs = tst.nb_tbs;
- /* XXX: avoid using doubles ? */
- g_string_append_printf(buf, "Translation buffer state:\n");
- /*
- * Report total code size including the padding and TB structs;
- * otherwise users might think "-accel tcg,tb-size" is not honoured.
- * For avg host size we use the precise numbers from tb_tree_stats though.
- */
- g_string_append_printf(buf, "gen code size %zu/%zu\n",
- tcg_code_size(), tcg_code_capacity());
- g_string_append_printf(buf, "TB count %zu\n", nb_tbs);
- g_string_append_printf(buf, "TB avg target size %zu max=%zu bytes\n",
- nb_tbs ? tst.target_size / nb_tbs : 0,
- tst.max_target_size);
- g_string_append_printf(buf, "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);
- g_string_append_printf(buf, "cross page TB count %zu (%zu%%)\n",
- tst.cross_page,
- nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
- g_string_append_printf(buf, "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(hst, buf);
- qht_statistics_destroy(&hst);
-
- g_string_append_printf(buf, "\nStatistics:\n");
- g_string_append_printf(buf, "TB flush count %u\n",
- qatomic_read(&tb_ctx.tb_flush_count));
- g_string_append_printf(buf, "TB invalidate count %u\n",
- qatomic_read(&tb_ctx.tb_phys_invalidate_count));
-
- tlb_flush_counts(&flush_full, &flush_part, &flush_elide);
- g_string_append_printf(buf, "TLB full flushes %zu\n", flush_full);
- g_string_append_printf(buf, "TLB partial flushes %zu\n", flush_part);
- g_string_append_printf(buf, "TLB elided flushes %zu\n", flush_elide);
- tcg_dump_info(buf);
-}
HumanReadableText *qmp_x_query_jit(Error **errp)
{
@@ -208,29 +24,7 @@ HumanReadableText *qmp_x_query_jit(Error **errp)
return NULL;
}
- dump_accel_info(buf);
- dump_exec_info(buf);
- dump_drift_info(buf);
-
- return human_readable_text_from_str(buf);
-}
-
-static void tcg_dump_op_count(GString *buf)
-{
- g_string_append_printf(buf, "[TCG profiler not compiled]\n");
-}
-
-HumanReadableText *qmp_x_query_opcount(Error **errp)
-{
- g_autoptr(GString) buf = g_string_new("");
-
- if (!tcg_enabled()) {
- error_setg(errp,
- "Opcode count information is only available with accel=tcg");
- return NULL;
- }
-
- tcg_dump_op_count(buf);
+ tcg_dump_stats(buf);
return human_readable_text_from_str(buf);
}
@@ -238,7 +32,6 @@ HumanReadableText *qmp_x_query_opcount(Error **errp)
static void hmp_tcg_register(void)
{
monitor_register_hmp_info_hrt("jit", qmp_x_query_jit);
- monitor_register_hmp_info_hrt("opcount", qmp_x_query_opcount);
}
type_init(hmp_tcg_register);
diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c
index c1da753..9920381 100644
--- a/accel/tcg/plugin-gen.c
+++ b/accel/tcg/plugin-gen.c
@@ -117,10 +117,20 @@ static TCGv_i32 gen_cpu_index(void)
static void gen_udata_cb(struct qemu_plugin_regular_cb *cb)
{
TCGv_i32 cpu_index = gen_cpu_index();
+ enum qemu_plugin_cb_flags cb_flags =
+ tcg_call_to_qemu_plugin_cb_flags(cb->info->flags);
+ TCGv_i32 flags = tcg_constant_i32(cb_flags);
+ TCGv_i32 clear_flags = tcg_constant_i32(QEMU_PLUGIN_CB_NO_REGS);
+ tcg_gen_st_i32(flags, tcg_env,
+ offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
tcg_gen_call2(cb->f.vcpu_udata, cb->info, NULL,
tcgv_i32_temp(cpu_index),
tcgv_ptr_temp(tcg_constant_ptr(cb->userp)));
+ tcg_gen_st_i32(clear_flags, tcg_env,
+ offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
tcg_temp_free_i32(cpu_index);
+ tcg_temp_free_i32(flags);
+ tcg_temp_free_i32(clear_flags);
}
static TCGv_ptr gen_plugin_u64_ptr(qemu_plugin_u64 entry)
@@ -173,10 +183,20 @@ static void gen_udata_cond_cb(struct qemu_plugin_conditional_cb *cb)
tcg_gen_ld_i64(val, ptr, 0);
tcg_gen_brcondi_i64(cond, val, cb->imm, after_cb);
TCGv_i32 cpu_index = gen_cpu_index();
+ enum qemu_plugin_cb_flags cb_flags =
+ tcg_call_to_qemu_plugin_cb_flags(cb->info->flags);
+ TCGv_i32 flags = tcg_constant_i32(cb_flags);
+ TCGv_i32 clear_flags = tcg_constant_i32(QEMU_PLUGIN_CB_NO_REGS);
+ tcg_gen_st_i32(flags, tcg_env,
+ offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
tcg_gen_call2(cb->f.vcpu_udata, cb->info, NULL,
tcgv_i32_temp(cpu_index),
tcgv_ptr_temp(tcg_constant_ptr(cb->userp)));
+ tcg_gen_st_i32(clear_flags, tcg_env,
+ offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
tcg_temp_free_i32(cpu_index);
+ tcg_temp_free_i32(flags);
+ tcg_temp_free_i32(clear_flags);
gen_set_label(after_cb);
tcg_temp_free_i64(val);
@@ -210,12 +230,22 @@ static void gen_mem_cb(struct qemu_plugin_regular_cb *cb,
qemu_plugin_meminfo_t meminfo, TCGv_i64 addr)
{
TCGv_i32 cpu_index = gen_cpu_index();
+ enum qemu_plugin_cb_flags cb_flags =
+ tcg_call_to_qemu_plugin_cb_flags(cb->info->flags);
+ TCGv_i32 flags = tcg_constant_i32(cb_flags);
+ TCGv_i32 clear_flags = tcg_constant_i32(QEMU_PLUGIN_CB_NO_REGS);
+ tcg_gen_st_i32(flags, tcg_env,
+ offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
tcg_gen_call4(cb->f.vcpu_mem, cb->info, NULL,
tcgv_i32_temp(cpu_index),
tcgv_i32_temp(tcg_constant_i32(meminfo)),
tcgv_i64_temp(addr),
tcgv_ptr_temp(tcg_constant_ptr(cb->userp)));
+ tcg_gen_st_i32(clear_flags, tcg_env,
+ offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
tcg_temp_free_i32(cpu_index);
+ tcg_temp_free_i32(flags);
+ tcg_temp_free_i32(clear_flags);
}
static void inject_cb(struct qemu_plugin_dyn_cb *cb)
diff --git a/accel/tcg/tcg-accel-ops-mttcg.c b/accel/tcg/tcg-accel-ops-mttcg.c
index dfcee30..337b993 100644
--- a/accel/tcg/tcg-accel-ops-mttcg.c
+++ b/accel/tcg/tcg-accel-ops-mttcg.c
@@ -113,7 +113,6 @@ static void *mttcg_cpu_thread_fn(void *arg)
}
}
- qatomic_set_mb(&cpu->exit_request, 0);
qemu_wait_io_event(cpu);
} while (!cpu->unplug || cpu_can_run(cpu));
diff --git a/accel/tcg/tcg-accel-ops.c b/accel/tcg/tcg-accel-ops.c
index b24d6a7..3b0d7d2 100644
--- a/accel/tcg/tcg-accel-ops.c
+++ b/accel/tcg/tcg-accel-ops.c
@@ -26,7 +26,8 @@
*/
#include "qemu/osdep.h"
-#include "system/accel-ops.h"
+#include "accel/accel-ops.h"
+#include "accel/accel-cpu-ops.h"
#include "system/tcg.h"
#include "system/replay.h"
#include "exec/icount.h"
@@ -80,6 +81,9 @@ int tcg_cpu_exec(CPUState *cpu)
cpu_exec_start(cpu);
ret = cpu_exec(cpu);
cpu_exec_end(cpu);
+
+ qatomic_set_mb(&cpu->exit_request, 0);
+
return ret;
}
@@ -93,8 +97,6 @@ static void tcg_cpu_reset_hold(CPUState *cpu)
/* mask must never be zero, except for A20 change call */
void tcg_handle_interrupt(CPUState *cpu, int mask)
{
- g_assert(bql_locked());
-
cpu->interrupt_request |= mask;
/*
@@ -198,8 +200,10 @@ static inline void tcg_remove_all_breakpoints(CPUState *cpu)
cpu_watchpoint_remove_all(cpu, BP_GDB);
}
-static void tcg_accel_ops_init(AccelOpsClass *ops)
+static void tcg_accel_ops_init(AccelClass *ac)
{
+ AccelOpsClass *ops = ac->ops;
+
if (qemu_tcg_mttcg_enabled()) {
ops->create_vcpu_thread = mttcg_start_vcpu_thread;
ops->kick_vcpu_thread = mttcg_kick_vcpu_thread;
diff --git a/accel/tcg/tcg-all.c b/accel/tcg/tcg-all.c
index 6e5dc33..5125e1a 100644
--- a/accel/tcg/tcg-all.c
+++ b/accel/tcg/tcg-all.c
@@ -39,6 +39,8 @@
#ifndef CONFIG_USER_ONLY
#include "hw/boards.h"
#endif
+#include "accel/accel-ops.h"
+#include "accel/accel-cpu-ops.h"
#include "accel/tcg/cpu-ops.h"
#include "internal-common.h"
@@ -80,9 +82,9 @@ static void tcg_accel_instance_init(Object *obj)
bool one_insn_per_tb;
-static int tcg_init_machine(MachineState *ms)
+static int tcg_init_machine(AccelState *as, MachineState *ms)
{
- TCGState *s = TCG_STATE(current_accel());
+ TCGState *s = TCG_STATE(as);
unsigned max_threads = 1;
#ifndef CONFIG_USER_ONLY
@@ -219,7 +221,7 @@ static void tcg_set_one_insn_per_tb(Object *obj, bool value, Error **errp)
qatomic_set(&one_insn_per_tb, value);
}
-static int tcg_gdbstub_supported_sstep_flags(void)
+static int tcg_gdbstub_supported_sstep_flags(AccelState *as)
{
/*
* In replay mode all events will come from the log and can't be
@@ -241,6 +243,7 @@ static void tcg_accel_class_init(ObjectClass *oc, const void *data)
ac->init_machine = tcg_init_machine;
ac->cpu_common_realize = tcg_exec_realizefn;
ac->cpu_common_unrealize = tcg_exec_unrealizefn;
+ ac->get_stats = tcg_get_stats;
ac->allowed = &tcg_allowed;
ac->gdbstub_supported_sstep_flags = tcg_gdbstub_supported_sstep_flags;
diff --git a/accel/tcg/tcg-stats.c b/accel/tcg/tcg-stats.c
new file mode 100644
index 0000000..ced5dec
--- /dev/null
+++ b/accel/tcg/tcg-stats.c
@@ -0,0 +1,219 @@
+/*
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ *
+ * QEMU TCG statistics
+ *
+ * Copyright (c) 2003-2005 Fabrice Bellard
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/accel.h"
+#include "qemu/qht.h"
+#include "qapi/error.h"
+#include "system/cpu-timers.h"
+#include "exec/icount.h"
+#include "hw/core/cpu.h"
+#include "tcg/tcg.h"
+#include "internal-common.h"
+#include "tb-context.h"
+#include <math.h>
+
+static void dump_drift_info(GString *buf)
+{
+ if (!icount_enabled()) {
+ return;
+ }
+
+ g_string_append_printf(buf, "Host - Guest clock %"PRIi64" ms\n",
+ (cpu_get_clock() - icount_get()) / SCALE_MS);
+ if (icount_align_option) {
+ g_string_append_printf(buf, "Max guest delay %"PRIi64" ms\n",
+ -max_delay / SCALE_MS);
+ g_string_append_printf(buf, "Max guest advance %"PRIi64" ms\n",
+ max_advance / SCALE_MS);
+ } else {
+ g_string_append_printf(buf, "Max guest delay NA\n");
+ g_string_append_printf(buf, "Max guest advance NA\n");
+ }
+}
+
+static void dump_accel_info(AccelState *accel, GString *buf)
+{
+ bool one_insn_per_tb = object_property_get_bool(OBJECT(accel),
+ "one-insn-per-tb",
+ &error_fatal);
+
+ g_string_append_printf(buf, "Accelerator settings:\n");
+ g_string_append_printf(buf, "one-insn-per-tb: %s\n\n",
+ one_insn_per_tb ? "on" : "off");
+}
+
+static void print_qht_statistics(struct qht_stats hst, GString *buf)
+{
+ uint32_t hgram_opts;
+ size_t hgram_bins;
+ char *hgram;
+ double avg;
+
+ if (!hst.head_buckets) {
+ return;
+ }
+ g_string_append_printf(buf, "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);
+
+ hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
+ hgram_opts |= QDIST_PR_100X | QDIST_PR_PERCENT;
+ if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
+ hgram_opts |= QDIST_PR_NODECIMAL;
+ }
+ hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
+ avg = qdist_avg(&hst.occupancy);
+ if (!isnan(avg)) {
+ g_string_append_printf(buf, "TB hash occupancy "
+ "%0.2f%% avg chain occ. "
+ "Histogram: %s\n",
+ avg * 100, hgram);
+ }
+ g_free(hgram);
+
+ hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
+ hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
+ if (hgram_bins > 10) {
+ hgram_bins = 10;
+ } else {
+ hgram_bins = 0;
+ hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
+ }
+ hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
+ avg = qdist_avg(&hst.chain);
+ if (!isnan(avg)) {
+ g_string_append_printf(buf, "TB hash avg chain %0.3f buckets. "
+ "Histogram: %s\n",
+ avg, hgram);
+ }
+ g_free(hgram);
+}
+
+struct tb_tree_stats {
+ size_t nb_tbs;
+ size_t host_size;
+ size_t target_size;
+ size_t max_target_size;
+ size_t direct_jmp_count;
+ size_t direct_jmp2_count;
+ size_t cross_page;
+};
+
+static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data)
+{
+ const TranslationBlock *tb = value;
+ struct tb_tree_stats *tst = data;
+
+ tst->nb_tbs++;
+ tst->host_size += tb->tc.size;
+ tst->target_size += tb->size;
+ if (tb->size > tst->max_target_size) {
+ tst->max_target_size = tb->size;
+ }
+#ifndef CONFIG_USER_ONLY
+ if (tb->page_addr[1] != -1) {
+ tst->cross_page++;
+ }
+#endif
+ if (tb->jmp_reset_offset[0] != TB_JMP_OFFSET_INVALID) {
+ tst->direct_jmp_count++;
+ if (tb->jmp_reset_offset[1] != TB_JMP_OFFSET_INVALID) {
+ tst->direct_jmp2_count++;
+ }
+ }
+ return false;
+}
+
+static void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)
+{
+ CPUState *cpu;
+ size_t full = 0, part = 0, elide = 0;
+
+ CPU_FOREACH(cpu) {
+ full += qatomic_read(&cpu->neg.tlb.c.full_flush_count);
+ part += qatomic_read(&cpu->neg.tlb.c.part_flush_count);
+ elide += qatomic_read(&cpu->neg.tlb.c.elide_flush_count);
+ }
+ *pfull = full;
+ *ppart = part;
+ *pelide = elide;
+}
+
+static void tcg_dump_flush_info(GString *buf)
+{
+ size_t flush_full, flush_part, flush_elide;
+
+ g_string_append_printf(buf, "TB flush count %u\n",
+ qatomic_read(&tb_ctx.tb_flush_count));
+ g_string_append_printf(buf, "TB invalidate count %u\n",
+ qatomic_read(&tb_ctx.tb_phys_invalidate_count));
+
+ tlb_flush_counts(&flush_full, &flush_part, &flush_elide);
+ g_string_append_printf(buf, "TLB full flushes %zu\n", flush_full);
+ g_string_append_printf(buf, "TLB partial flushes %zu\n", flush_part);
+ g_string_append_printf(buf, "TLB elided flushes %zu\n", flush_elide);
+}
+
+static void dump_exec_info(GString *buf)
+{
+ struct tb_tree_stats tst = {};
+ struct qht_stats hst;
+ size_t nb_tbs;
+
+ tcg_tb_foreach(tb_tree_stats_iter, &tst);
+ nb_tbs = tst.nb_tbs;
+ /* XXX: avoid using doubles ? */
+ g_string_append_printf(buf, "Translation buffer state:\n");
+ /*
+ * Report total code size including the padding and TB structs;
+ * otherwise users might think "-accel tcg,tb-size" is not honoured.
+ * For avg host size we use the precise numbers from tb_tree_stats though.
+ */
+ g_string_append_printf(buf, "gen code size %zu/%zu\n",
+ tcg_code_size(), tcg_code_capacity());
+ g_string_append_printf(buf, "TB count %zu\n", nb_tbs);
+ g_string_append_printf(buf, "TB avg target size %zu max=%zu bytes\n",
+ nb_tbs ? tst.target_size / nb_tbs : 0,
+ tst.max_target_size);
+ g_string_append_printf(buf, "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);
+ g_string_append_printf(buf, "cross page TB count %zu (%zu%%)\n",
+ tst.cross_page,
+ nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
+ g_string_append_printf(buf, "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(hst, buf);
+ qht_statistics_destroy(&hst);
+
+ g_string_append_printf(buf, "\nStatistics:\n");
+ tcg_dump_flush_info(buf);
+}
+
+void tcg_get_stats(AccelState *accel, GString *buf)
+{
+ dump_accel_info(accel, buf);
+ dump_exec_info(buf);
+ dump_drift_info(buf);
+}
+
+void tcg_dump_stats(GString *buf)
+{
+ tcg_get_stats(current_accel(), buf);
+}
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 451b383..d468667 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -24,7 +24,6 @@
#include "tcg/tcg.h"
#include "exec/mmap-lock.h"
#include "tb-internal.h"
-#include "tlb-bounds.h"
#include "exec/tb-flush.h"
#include "qemu/cacheinfo.h"
#include "qemu/target-info.h"
@@ -313,11 +312,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu, TCGTBCPUState s)
tcg_ctx->gen_tb = tb;
tcg_ctx->addr_type = target_long_bits() == 32 ? TCG_TYPE_I32 : TCG_TYPE_I64;
-#ifdef CONFIG_SOFTMMU
- tcg_ctx->page_bits = TARGET_PAGE_BITS;
- tcg_ctx->page_mask = TARGET_PAGE_MASK;
- tcg_ctx->tlb_dyn_max_bits = CPU_TLB_DYN_MAX_BITS;
-#endif
tcg_ctx->guest_mo = cpu->cc->tcg_ops->guest_default_memory_order;
restart_translate:
generated by cgit v1.1 at 2025-08-03 11:01:22 +0000