The PMU is already counting cycles by calculating time elapsed in nanoseconds. Counting instructions is a different matter and requires another approach.
This patch adds the capability of counting completed instructions (Perf event PM_INST_CMPL) by counting the amount of instructions translated in each translation block right before exiting it. A new pmu_count_insns() helper in translation.c was added to do that. After verifying that the PMU is running (MMCR0_FC bit not set), we call helper_insns_inc(). This is new helper from power8_pmu.c that will add the instructions to the relevant counters. At this moment helper_insns_inc() is just summing instructions to counters, but it will also trigger counter negative overflow in a later patch. Signed-off-by: Daniel Henrique Barboza <danielhb...@gmail.com> --- target/ppc/helper.h | 1 + target/ppc/power8_pmu.c | 61 ++++++++++++++++++++++++++++++++++++++--- target/ppc/translate.c | 46 +++++++++++++++++++++++++++++++ 3 files changed, 104 insertions(+), 4 deletions(-) diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 5122632784..47dbbe6da1 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -21,6 +21,7 @@ DEF_HELPER_1(hrfid, void, env) DEF_HELPER_2(store_lpcr, void, env, tl) DEF_HELPER_2(store_pcr, void, env, tl) DEF_HELPER_2(store_mmcr0, void, env, tl) +DEF_HELPER_2(insns_inc, void, env, i32) #endif DEF_HELPER_1(check_tlb_flush_local, void, env) DEF_HELPER_1(check_tlb_flush_global, void, env) diff --git a/target/ppc/power8_pmu.c b/target/ppc/power8_pmu.c index 007007824d..311eaa358f 100644 --- a/target/ppc/power8_pmu.c +++ b/target/ppc/power8_pmu.c @@ -31,10 +31,9 @@ static void update_PMC_PM_CYC(CPUPPCState *env, int sprn, env->spr[sprn] += time_delta; } -static void update_programmable_PMC_reg(CPUPPCState *env, int sprn, - uint64_t time_delta) +static uint8_t get_PMC_event(CPUPPCState *env, int sprn) { - uint8_t event; + int event = 0x0; switch (sprn) { case SPR_POWER_PMC1: @@ -53,9 +52,17 @@ static void update_programmable_PMC_reg(CPUPPCState *env, int sprn, event = MMCR1_PMC4SEL & env->spr[SPR_POWER_MMCR1]; break; default: - return; + break; } + return event; +} + +static void update_programmable_PMC_reg(CPUPPCState *env, int sprn, + uint64_t time_delta) +{ + uint8_t event = get_PMC_event(env, sprn); + /* * MMCR0_PMC1SEL = 0xF0 is the architected PowerISA v3.1 event * that counts cycles using PMC1. @@ -124,4 +131,50 @@ void helper_store_mmcr0(CPUPPCState *env, target_ulong value) } } +static bool pmc_counting_insns(CPUPPCState *env, int sprn) +{ + bool ret = false; + uint8_t event; + + if (sprn == SPR_POWER_PMC5) { + return true; + } + + event = get_PMC_event(env, sprn); + + /* + * Event 0x2 is an implementation-dependent event that IBM + * POWER chips implement (at least since POWER8) that is + * equivalent to PM_INST_CMPL. Let's support this event on + * all programmable PMCs. + * + * Event 0xFE is the PowerISA v3.1 architected event to + * sample PM_INST_CMPL using PMC1. + */ + switch (sprn) { + case SPR_POWER_PMC1: + return event == 0x2 || event == 0xFE; + case SPR_POWER_PMC2: + case SPR_POWER_PMC3: + case SPR_POWER_PMC4: + return event == 0x2; + default: + break; + } + + return ret; +} + +/* This helper assumes that the PMC is running. */ +void helper_insns_inc(CPUPPCState *env, uint32_t num_insns) +{ + int sprn; + + for (sprn = SPR_POWER_PMC1; sprn <= SPR_POWER_PMC5; sprn++) { + if (pmc_counting_insns(env, sprn)) { + env->spr[sprn] += num_insns; + } + } +} + #endif /* defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY) */ diff --git a/target/ppc/translate.c b/target/ppc/translate.c index e4f75ba380..d45ce79a3e 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -4425,6 +4425,30 @@ static inline void gen_update_cfar(DisasContext *ctx, target_ulong nip) #endif } +#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY) +static void pmu_count_insns(DisasContext *ctx) +{ + TCGv t_mmcr0FC = tcg_constant_i64(MMCR0_FC); + TCGv t0 = tcg_temp_new(); + TCGLabel *l_exit = gen_new_label(); + + /* Do not bother calling the helper if the PMU is frozen */ + gen_load_spr(t0, SPR_POWER_MMCR0); + tcg_gen_andi_tl(t0, t0, MMCR0_FC); + tcg_gen_brcond_tl(TCG_COND_EQ, t0, t_mmcr0FC, l_exit); + + gen_helper_insns_inc(cpu_env, tcg_constant_i32(ctx->base.num_insns)); + + gen_set_label(l_exit); + tcg_temp_free(t_mmcr0FC); + tcg_temp_free(t0); +} +#else +static void pmu_count_insns(DisasContext *ctx) +{ + return; +} +#endif static inline bool use_goto_tb(DisasContext *ctx, target_ulong dest) { return translator_use_goto_tb(&ctx->base, dest); @@ -4439,9 +4463,17 @@ static void gen_lookup_and_goto_ptr(DisasContext *ctx) } else if (sse & (CPU_SINGLE_STEP | CPU_BRANCH_STEP)) { gen_helper_raise_exception(cpu_env, tcg_constant_i32(gen_prep_dbgex(ctx))); } else { + pmu_count_insns(ctx); tcg_gen_exit_tb(NULL, 0); } } else { + /* + * tcg_gen_lookup_and_goto_ptr will exit the TB if + * CF_NO_GOTO_PTR is set. Count insns now. + */ + if (ctx->base.tb->flags & CF_NO_GOTO_PTR) { + pmu_count_insns(ctx); + } tcg_gen_lookup_and_goto_ptr(); } } @@ -4453,6 +4485,8 @@ static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest) dest = (uint32_t) dest; } if (use_goto_tb(ctx, dest)) { + pmu_count_insns(ctx); + tcg_gen_goto_tb(n); tcg_gen_movi_tl(cpu_nip, dest & ~3); tcg_gen_exit_tb(ctx->base.tb, n); @@ -8785,6 +8819,8 @@ static void ppc_tr_tb_stop(DisasContextBase *dcbase, CPUState *cs) switch (is_jmp) { case DISAS_TOO_MANY: if (use_goto_tb(ctx, nip)) { + pmu_count_insns(ctx); + tcg_gen_goto_tb(0); gen_update_nip(ctx, nip); tcg_gen_exit_tb(ctx->base.tb, 0); @@ -8795,6 +8831,14 @@ static void ppc_tr_tb_stop(DisasContextBase *dcbase, CPUState *cs) gen_update_nip(ctx, nip); /* fall through */ case DISAS_CHAIN: + /* + * tcg_gen_lookup_and_goto_ptr will exit the TB if + * CF_NO_GOTO_PTR is set. Count insns now. + */ + if (ctx->base.tb->flags & CF_NO_GOTO_PTR) { + pmu_count_insns(ctx); + } + tcg_gen_lookup_and_goto_ptr(); break; @@ -8802,6 +8846,8 @@ static void ppc_tr_tb_stop(DisasContextBase *dcbase, CPUState *cs) gen_update_nip(ctx, nip); /* fall through */ case DISAS_EXIT: + pmu_count_insns(ctx); + tcg_gen_exit_tb(NULL, 0); break; -- 2.31.1