mirror of
https://github.com/izzy2lost/xemu.git
synced 2026-07-06 00:20:22 -07:00
Merge tag 'accel-20250715' of https://github.com/philmd/qemu into staging
Accelerators patches
- Unify x86/arm hw/xen/arch_hvm.h header
- Move non-system-specific 'accel/accel-ops.h' and 'accel-cpu-ops.h' to accel/
- Move KVM definitions qapi/accelerator.json
- Add @qom-type field to CpuInfoFast QAPI structure
- Display CPU model name in 'info cpus' HMP command
- Introduce @x-accel-stats QMP command
- Add 'info accel' on HMP
- Improve qemu_add_vm_change_state_handler*() docstring
- Extract TCG statistic related code to tcg-stats.c
- Implement AccelClass::get_[vcpu]_stats() handlers for TCG and HVF
- Do not dump NaN in TCG statistics
- Revert incomplete "accel/tcg: Unregister the RCU before exiting RR thread"
# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEE+qvnXhKRciHc/Wuy4+MsLN6twN4FAmh2r4UACgkQ4+MsLN6t
# wN5i6xAAkOvwFh1GmsPUdz5RxzsWoIUDvyENg6E8Axwe5tSEMRFiPjabbTQJomQg
# GZt75XIS24LZFZ+hvqrLSA+dFgXTgWv08ZE81EjwjmAMBlLCOPhCgeN6C1p8100Y
# scSvRJbP9k9lpA5K7et/1X4AkK2cZyh+LGJgCjr2Al2mbERpPueDF8fxqeohFvXQ
# nTSks4XlA0yQ06+9r49aQAiuXvgg9lDT1wIglD2HEV7vOVs/ud+yyL8+z5YMeFzx
# pSIc6wDu4PqdA46w4MZs90uTy7S/PMvBiYDEiV3tKzg0MLttvFGlT58/YjVtguTP
# mNkfwIEwQtDQzoxsFIJO7yBTlTRBs95V4aIVk3pB+Gb/bideRPIkeVQvgMSEBKj7
# N0pEXWOxfB9iIWO6b1utYpQ4uxeDOU/8DPUCit1IBbNgKTaJkJb77fboYk7NaB0K
# KEtObAk6jMatB/xr+vUFWc4sMk9wlm72w8wcQzgKZ0xV2U3d1/Y/9nS4GvI510ev
# TRQ3mKj7N319uCeId1czF6W8rillCJ2u8ZK53u+Nfp7R3PbsRSMc6IDJ1UdDUlyR
# HFcWHxbcbEGhe8SnFGab4Qd6fWChcn2EaEoAJJz+Rqv0k3zcwqccNM5waCABAjTE
# 0S22JIHePJKcpkMLGq3EOUAQuu+8Zsol7gPCLxSAMclVqPTl9ck=
# =rAav
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 15 Jul 2025 15:44:05 EDT
# gpg: using RSA key FAABE75E12917221DCFD6BB2E3E32C2CDEADC0DE
# gpg: Good signature from "Philippe Mathieu-Daudé (F4BUG) <f4bug@amsat.org>" [full]
# Primary key fingerprint: FAAB E75E 1291 7221 DCFD 6BB2 E3E3 2C2C DEAD C0DE
* tag 'accel-20250715' of https://github.com/philmd/qemu:
system/runstate: Document qemu_add_vm_change_state_handler_prio* in hdr
system/runstate: Document qemu_add_vm_change_state_handler()
accel/hvf: Implement AccelClass::get_vcpu_stats() handler
accel/tcg: Implement AccelClass::get_stats() handler
accel/tcg: Propagate AccelState to dump_accel_info()
accel/system: Add 'info accel' on human monitor
accel/system: Introduce @x-accel-stats QMP command
accel/tcg: Extract statistic related code to tcg-stats.c
Revert "accel/tcg: Unregister the RCU before exiting RR thread"
accel: Extract AccelClass definition to 'accel/accel-ops.h'
accel: Rename 'system/accel-ops.h' -> 'accel/accel-cpu-ops.h'
accel/tcg: Do not dump NaN statistics
hw/core/machine: Display CPU model name in 'info cpus' command
qapi/machine: Add @qom-type field to CpuInfoFast structure
qapi/accel: Move definitions related to accelerators in their own file
hw/arm/xen-pvh: Remove unnecessary 'hw/xen/arch_hvm.h' header
hw/xen/arch_hvm: Unify x86 and ARM variants
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Conflicts:
qapi/machine.json
Commit 0462da9d6b ("qapi: remove trivial "Returns:" sections")
removed trivial "Returns:". This caused a conflict with the move from
machine.json to accelerator.json.
This commit is contained in:
@@ -10,7 +10,9 @@
|
||||
#include "qemu/osdep.h"
|
||||
#include "qemu/accel.h"
|
||||
#include "qemu/target-info.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "accel/accel-cpu.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "accel-internal.h"
|
||||
|
||||
/* Lookup AccelClass from opt_name. Returns NULL if not found */
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
/*
|
||||
* QMP commands related to accelerators
|
||||
*
|
||||
* Copyright (c) Linaro
|
||||
*
|
||||
* SPDX-License-Identifier: GPL-2.0-or-later
|
||||
*/
|
||||
|
||||
#include "qemu/osdep.h"
|
||||
#include "qemu/accel.h"
|
||||
#include "qapi/type-helpers.h"
|
||||
#include "qapi/qapi-commands-accelerator.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "hw/core/cpu.h"
|
||||
|
||||
HumanReadableText *qmp_x_accel_stats(Error **errp)
|
||||
{
|
||||
AccelState *accel = current_accel();
|
||||
AccelClass *acc = ACCEL_GET_CLASS(accel);
|
||||
g_autoptr(GString) buf = g_string_new("");
|
||||
|
||||
if (acc->get_stats) {
|
||||
acc->get_stats(accel, buf);
|
||||
}
|
||||
if (acc->ops->get_vcpu_stats) {
|
||||
CPUState *cpu;
|
||||
|
||||
CPU_FOREACH(cpu) {
|
||||
acc->ops->get_vcpu_stats(cpu, buf);
|
||||
}
|
||||
}
|
||||
|
||||
return human_readable_text_from_str(buf);
|
||||
}
|
||||
+11
-1
@@ -25,8 +25,12 @@
|
||||
|
||||
#include "qemu/osdep.h"
|
||||
#include "qemu/accel.h"
|
||||
#include "qapi/qapi-commands-accelerator.h"
|
||||
#include "monitor/monitor.h"
|
||||
#include "hw/boards.h"
|
||||
#include "system/accel-ops.h"
|
||||
#include "hw/core/cpu.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "system/cpus.h"
|
||||
#include "qemu/error-report.h"
|
||||
#include "accel-internal.h"
|
||||
@@ -101,11 +105,17 @@ void accel_init_ops_interfaces(AccelClass *ac)
|
||||
cpus_register_accel(ops);
|
||||
}
|
||||
|
||||
static void accel_ops_class_init(ObjectClass *oc, const void *data)
|
||||
{
|
||||
monitor_register_hmp_info_hrt("accel", qmp_x_accel_stats);
|
||||
}
|
||||
|
||||
static const TypeInfo accel_ops_type_info = {
|
||||
.name = TYPE_ACCEL_OPS,
|
||||
.parent = TYPE_OBJECT,
|
||||
.abstract = true,
|
||||
.class_size = sizeof(AccelOpsClass),
|
||||
.class_init = accel_ops_class_init,
|
||||
};
|
||||
|
||||
static void accel_system_register_types(void)
|
||||
|
||||
@@ -54,10 +54,11 @@
|
||||
#include "gdbstub/enums.h"
|
||||
#include "exec/cpu-common.h"
|
||||
#include "hw/core/cpu.h"
|
||||
#include "system/accel-ops.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "system/cpus.h"
|
||||
#include "system/hvf.h"
|
||||
#include "system/hvf_int.h"
|
||||
#include <mach/mach_time.h>
|
||||
|
||||
HVFState *hvf_state;
|
||||
|
||||
@@ -118,6 +119,12 @@ static void dummy_signal(int sig)
|
||||
{
|
||||
}
|
||||
|
||||
static void do_hvf_get_vcpu_exec_time(CPUState *cpu, run_on_cpu_data arg)
|
||||
{
|
||||
int r = hv_vcpu_get_exec_time(cpu->accel->fd, arg.host_ptr);
|
||||
assert_hvf_ok(r);
|
||||
}
|
||||
|
||||
static void hvf_vcpu_destroy(CPUState *cpu)
|
||||
{
|
||||
hv_return_t ret = hv_vcpu_destroy(cpu->accel->fd);
|
||||
@@ -347,6 +354,21 @@ static void hvf_remove_all_breakpoints(CPUState *cpu)
|
||||
}
|
||||
}
|
||||
|
||||
static void hvf_get_vcpu_stats(CPUState *cpu, GString *buf)
|
||||
{
|
||||
uint64_t time_mach; /* units of mach_absolute_time() */
|
||||
|
||||
run_on_cpu(cpu, do_hvf_get_vcpu_exec_time, RUN_ON_CPU_HOST_PTR(&time_mach));
|
||||
|
||||
mach_timebase_info_data_t timebase;
|
||||
mach_timebase_info(&timebase);
|
||||
uint64_t time_ns = time_mach * timebase.numer / timebase.denom;
|
||||
|
||||
g_string_append_printf(buf, "HVF cumulative execution time: %llu.%.3llus\n",
|
||||
time_ns / 1000000000,
|
||||
(time_ns % 1000000000) / 1000000);
|
||||
}
|
||||
|
||||
static void hvf_accel_ops_class_init(ObjectClass *oc, const void *data)
|
||||
{
|
||||
AccelOpsClass *ops = ACCEL_OPS_CLASS(oc);
|
||||
@@ -365,7 +387,10 @@ static void hvf_accel_ops_class_init(ObjectClass *oc, const void *data)
|
||||
ops->remove_all_breakpoints = hvf_remove_all_breakpoints;
|
||||
ops->update_guest_debug = hvf_update_guest_debug;
|
||||
ops->supports_guest_debug = hvf_arch_supports_guest_debug;
|
||||
|
||||
ops->get_vcpu_stats = hvf_get_vcpu_stats;
|
||||
};
|
||||
|
||||
static const TypeInfo hvf_accel_ops_type = {
|
||||
.name = ACCEL_OPS_NAME("hvf"),
|
||||
|
||||
|
||||
@@ -10,6 +10,7 @@
|
||||
|
||||
#include "qemu/osdep.h"
|
||||
#include "qemu/error-report.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "system/address-spaces.h"
|
||||
#include "system/memory.h"
|
||||
#include "system/hvf.h"
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
#include "qemu/osdep.h"
|
||||
#include "qemu/error-report.h"
|
||||
#include "qemu/main-loop.h"
|
||||
#include "system/accel-ops.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "system/kvm.h"
|
||||
#include "system/kvm_int.h"
|
||||
#include "system/runstate.h"
|
||||
|
||||
@@ -32,6 +32,7 @@
|
||||
#include "system/runstate.h"
|
||||
#include "system/cpus.h"
|
||||
#include "system/accel-blocker.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "qemu/bswap.h"
|
||||
#include "exec/tswap.h"
|
||||
#include "system/memory.h"
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
common_ss.add(files('accel-common.c'))
|
||||
specific_ss.add(files('accel-target.c'))
|
||||
system_ss.add(files('accel-system.c', 'accel-blocker.c'))
|
||||
system_ss.add(files('accel-system.c', 'accel-blocker.c', 'accel-qmp.c'))
|
||||
user_ss.add(files('accel-user.c'))
|
||||
|
||||
subdir('tcg')
|
||||
|
||||
+2
-1
@@ -18,7 +18,8 @@
|
||||
#include "qemu/option.h"
|
||||
#include "qemu/config-file.h"
|
||||
#include "qemu/accel.h"
|
||||
#include "system/accel-ops.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "system/qtest.h"
|
||||
#include "system/cpus.h"
|
||||
#include "qemu/guest-random.h"
|
||||
|
||||
@@ -139,6 +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_dump_stats(GString *buf);
|
||||
void tcg_get_stats(AccelState *accel, GString *buf);
|
||||
|
||||
#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',
|
||||
))
|
||||
|
||||
@@ -7,205 +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_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_dump_stats(GString *buf)
|
||||
{
|
||||
dump_accel_info(buf);
|
||||
dump_exec_info(buf);
|
||||
dump_drift_info(buf);
|
||||
}
|
||||
|
||||
HumanReadableText *qmp_x_query_jit(Error **errp)
|
||||
{
|
||||
|
||||
@@ -302,8 +302,6 @@ static void *rr_cpu_thread_fn(void *arg)
|
||||
rr_deal_with_unplugged_cpus();
|
||||
}
|
||||
|
||||
rcu_unregister_thread();
|
||||
|
||||
g_assert_not_reached();
|
||||
}
|
||||
|
||||
|
||||
@@ -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"
|
||||
|
||||
@@ -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"
|
||||
|
||||
@@ -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;
|
||||
|
||||
|
||||
@@ -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);
|
||||
}
|
||||
+2
-1
@@ -19,7 +19,8 @@
|
||||
#include "chardev/char.h"
|
||||
#include "qemu/accel.h"
|
||||
#include "accel/dummy-cpus.h"
|
||||
#include "system/accel-ops.h"
|
||||
#include "accel/accel-ops.h"
|
||||
#include "accel/accel-cpu-ops.h"
|
||||
#include "system/cpus.h"
|
||||
#include "system/xen.h"
|
||||
#include "system/runstate.h"
|
||||
|
||||
Reference in New Issue
Block a user