OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

target/ppc: Increment PMC5 with inline insns 

Profiling QEMU during Fedora 35 for PPC64 boot revealed that
6.39% of total time was being spent in helper_insns_inc(), on a
POWER9 machine. To avoid calling this helper every time PMCs had
to be incremented, an inline implementation of PMC5 increment and
check for overflow was developed. This led to a reduction of
about 12% in Fedora's boot time.

Signed-off-by: Leandro Lupori <leandro.lupori@eldorado.org.br>
Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Message-Id: <20221025202424.195984-4-leandro.lupori@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
This commit is contained in:
Leandro Lupori 2022-10-25 17:24:24 -03:00 committed by Daniel Henrique Barboza
parent 8b3d1c49a9
commit eeaaefe9fa
4 changed files with 69 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
target/ppc/helper.h
View File

@ -30,6 +30,7 @@ DEF_HELPER_2(store_mmcr1, void, env, tl)
DEF_HELPER_3(store_pmc, void, env, i32, i64)
DEF_HELPER_2(read_pmc, tl, env, i32)
DEF_HELPER_2(insns_inc, void, env, i32)
DEF_HELPER_1(handle_pmc5_overflow, void, env)
#endif
DEF_HELPER_1(check_tlb_flush_local, void, env)
DEF_HELPER_1(check_tlb_flush_global, void, env)

78
target/ppc/power8-pmu.c
View File

@ -22,8 +22,6 @@
#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY)
#define PMC_COUNTER_NEGATIVE_VAL 0x80000000UL
static bool pmc_has_overflow_enabled(CPUPPCState *env, int sprn)
{
if (sprn == SPR_POWER_PMC1) {
@ -88,49 +86,47 @@ static bool pmu_increment_insns(CPUPPCState *env, uint32_t num_insns)
bool overflow_triggered = false;
target_ulong tmp;
if (unlikely(ins_cnt & 0x1e)) {
if (ins_cnt & (1 << 1)) {
tmp = env->spr[SPR_POWER_PMC1];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMC1CE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC1] = tmp;
if (ins_cnt & (1 << 1)) {
tmp = env->spr[SPR_POWER_PMC1];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMC1CE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC1] = tmp;
}
if (ins_cnt & (1 << 2)) {
tmp = env->spr[SPR_POWER_PMC2];
if (ins_cnt & (1 << 2)) {
tmp = env->spr[SPR_POWER_PMC2];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMCjCE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC2] = tmp;
}
if (ins_cnt & (1 << 3)) {
tmp = env->spr[SPR_POWER_PMC3];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMCjCE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC3] = tmp;
}
if (ins_cnt & (1 << 4)) {
target_ulong mmcr1 = env->spr[SPR_POWER_MMCR1];
int sel = extract64(mmcr1, MMCR1_PMC4EVT_EXTR, MMCR1_EVT_SIZE);
if (sel == 0x02 || (env->spr[SPR_CTRL] & CTRL_RUN)) {
tmp = env->spr[SPR_POWER_PMC4];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMCjCE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC2] = tmp;
}
if (ins_cnt & (1 << 3)) {
tmp = env->spr[SPR_POWER_PMC3];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMCjCE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC3] = tmp;
}
if (ins_cnt & (1 << 4)) {
target_ulong mmcr1 = env->spr[SPR_POWER_MMCR1];
int sel = extract64(mmcr1, MMCR1_PMC4EVT_EXTR, MMCR1_EVT_SIZE);
if (sel == 0x02 || (env->spr[SPR_CTRL] & CTRL_RUN)) {
tmp = env->spr[SPR_POWER_PMC4];
tmp += num_insns;
if (tmp >= PMC_COUNTER_NEGATIVE_VAL && (mmcr0 & MMCR0_PMCjCE)) {
tmp = PMC_COUNTER_NEGATIVE_VAL;
overflow_triggered = true;
}
env->spr[SPR_POWER_PMC4] = tmp;
}
env->spr[SPR_POWER_PMC4] = tmp;
}
}
@ -310,6 +306,12 @@ static void fire_PMC_interrupt(PowerPCCPU *cpu)
raise_ebb_perfm_exception(env);
}
void helper_handle_pmc5_overflow(CPUPPCState *env)
{
env->spr[SPR_POWER_PMC5] = PMC_COUNTER_NEGATIVE_VAL;
fire_PMC_interrupt(env_archcpu(env));
}
/* This helper assumes that the PMC is running. */
void helper_insns_inc(CPUPPCState *env, uint32_t num_insns)
{

3
target/ppc/power8-pmu.h
View File

@ -14,6 +14,9 @@
#define POWER8_PMU_H
#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY)
#define PMC_COUNTER_NEGATIVE_VAL 0x80000000UL
void cpu_ppc_pmu_init(CPUPPCState *env);
void pmu_update_summaries(CPUPPCState *env);
#else

28
target/ppc/translate.c
View File

@ -36,6 +36,7 @@
#include "exec/log.h"
#include "qemu/atomic128.h"
#include "spr_common.h"
#include "power8-pmu.h"
#include "qemu/qemu-print.h"
#include "qapi/error.h"
@ -4271,6 +4272,9 @@ static void pmu_count_insns(DisasContext *ctx)
}
#if !defined(CONFIG_USER_ONLY)
TCGLabel *l;
TCGv t0;
/*
* The PMU insns_inc() helper stops the internal PMU timer if a
* counter overflows happens. In that case, if the guest is
@ -4279,8 +4283,26 @@ static void pmu_count_insns(DisasContext *ctx)
*/
gen_icount_io_start(ctx);
gen_helper_insns_inc(cpu_env, tcg_constant_i32(ctx->base.num_insns));
#else
/* Avoid helper calls when only PMC5-6 are enabled. */
if (!ctx->pmc_other) {
l = gen_new_label();
t0 = tcg_temp_new();
gen_load_spr(t0, SPR_POWER_PMC5);
tcg_gen_addi_tl(t0, t0, ctx->base.num_insns);
gen_store_spr(SPR_POWER_PMC5, t0);
/* Check for overflow, if it's enabled */
if (ctx->mmcr0_pmcjce) {
tcg_gen_brcondi_tl(TCG_COND_LT, t0, PMC_COUNTER_NEGATIVE_VAL, l);
gen_helper_handle_pmc5_overflow(cpu_env);
}
gen_set_label(l);
tcg_temp_free(t0);
} else {
gen_helper_insns_inc(cpu_env, tcg_constant_i32(ctx->base.num_insns));
}
#else
/*
* User mode can read (but not write) PMC5 and start/stop
* the PMU via MMCR0_FC. In this case just increment
@ -4293,7 +4315,7 @@ static void pmu_count_insns(DisasContext *ctx)
gen_store_spr(SPR_POWER_PMC5, t0);
tcg_temp_free(t0);
#endif /* #if !defined(CONFIG_USER_ONLY) */
#endif /* #if !defined(CONFIG_USER_ONLY) */
}
#else
static void pmu_count_insns(DisasContext *ctx)