[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v8 06/10] target/ppc: enable PMU instruction count
From: |
David Gibson |
Subject: |
Re: [PATCH v8 06/10] target/ppc: enable PMU instruction count |
Date: |
Mon, 29 Nov 2021 15:36:18 +1100 |
On Thu, Nov 25, 2021 at 12:08:13PM -0300, Daniel Henrique Barboza wrote:
> 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), call
> helper_insns_inc(). This new helper from power8-pmu.c will add the
> instructions to the relevant counters. It'll also be responsible for
> triggering counter negative overflows as it is already being done with
> cycles.
>
> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
> ---
> target/ppc/cpu.h | 1 +
> target/ppc/helper.h | 1 +
> target/ppc/helper_regs.c | 4 +++
> target/ppc/power8-pmu-regs.c.inc | 6 +++++
> target/ppc/power8-pmu.c | 38 ++++++++++++++++++++++++++
> target/ppc/translate.c | 46 ++++++++++++++++++++++++++++++++
> 6 files changed, 96 insertions(+)
>
> diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
> index 9b41b022e2..38cd2b5c43 100644
> --- a/target/ppc/cpu.h
> +++ b/target/ppc/cpu.h
> @@ -656,6 +656,7 @@ enum {
> HFLAGS_PR = 14, /* MSR_PR */
> HFLAGS_PMCC0 = 15, /* MMCR0 PMCC bit 0 */
> HFLAGS_PMCC1 = 16, /* MMCR0 PMCC bit 1 */
> + HFLAGS_MMCR0FC = 17, /* MMCR0 FC bit */
Now that the event stuff is a bit more refined, you could narrow this
down to specifically marking if any counters are actively counting
instructions (not frozen by MMCR0[FC] and not frozen by
MMCR0[FC14|FC56] *and* have the right event selected).
Since I suspect the instruction counting instrumentation could be
quite expensive (helper call on every tb), that might be worthwhile.
> HFLAGS_VSX = 23, /* MSR_VSX if cpu has VSX */
> HFLAGS_VR = 25, /* MSR_VR if cpu has VRE */
>
> diff --git a/target/ppc/helper.h b/target/ppc/helper.h
> index 94b4690375..d8a23e054a 100644
> --- a/target/ppc/helper.h
> +++ b/target/ppc/helper.h
> @@ -24,6 +24,7 @@ DEF_HELPER_2(store_mmcr0, void, env, tl)
> 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)
> #endif
> DEF_HELPER_1(check_tlb_flush_local, void, env)
> DEF_HELPER_1(check_tlb_flush_global, void, env)
> diff --git a/target/ppc/helper_regs.c b/target/ppc/helper_regs.c
> index 99562edd57..875c2fdfc6 100644
> --- a/target/ppc/helper_regs.c
> +++ b/target/ppc/helper_regs.c
> @@ -115,6 +115,10 @@ static uint32_t hreg_compute_hflags_value(CPUPPCState
> *env)
> if (env->spr[SPR_POWER_MMCR0] & MMCR0_PMCC1) {
> hflags |= 1 << HFLAGS_PMCC1;
> }
> + if (env->spr[SPR_POWER_MMCR0] & MMCR0_FC) {
> + hflags |= 1 << HFLAGS_MMCR0FC;
> + }
> +
>
> #ifndef CONFIG_USER_ONLY
> if (!env->has_hv_mode || (msr & (1ull << MSR_HV))) {
> diff --git a/target/ppc/power8-pmu-regs.c.inc
> b/target/ppc/power8-pmu-regs.c.inc
> index 25b13ad564..580e4e41b2 100644
> --- a/target/ppc/power8-pmu-regs.c.inc
> +++ b/target/ppc/power8-pmu-regs.c.inc
> @@ -113,6 +113,12 @@ static void write_MMCR0_common(DisasContext *ctx, TCGv
> val)
> */
> gen_icount_io_start(ctx);
> gen_helper_store_mmcr0(cpu_env, val);
> +
> + /*
> + * End the translation block because MMCR0 writes can change
> + * ctx->pmu_frozen.
> + */
> + ctx->base.is_jmp = DISAS_EXIT_UPDATE;
> }
>
> void spr_write_MMCR0_ureg(DisasContext *ctx, int sprn, int gprn)
> diff --git a/target/ppc/power8-pmu.c b/target/ppc/power8-pmu.c
> index 01e0b9b8fc..59d0def79d 100644
> --- a/target/ppc/power8-pmu.c
> +++ b/target/ppc/power8-pmu.c
> @@ -112,6 +112,30 @@ static PMUEventType pmc_get_event(CPUPPCState *env, int
> sprn)
> return evt_type;
> }
>
> +static bool pmu_increment_insns(CPUPPCState *env, uint32_t num_insns)
> +{
> + bool overflow_triggered = false;
> + int sprn;
> +
> + /* PMC6 never counts instructions */
> + for (sprn = SPR_POWER_PMC1; sprn <= SPR_POWER_PMC5; sprn++) {
> + if (pmc_get_event(env, sprn) != PMU_EVENT_INSTRUCTIONS) {
> + continue;
> + }
> +
> + env->spr[sprn] += num_insns;
> +
> + if (env->spr[sprn] >= PMC_COUNTER_NEGATIVE_VAL &&
> + pmc_has_overflow_enabled(env, sprn)) {
> +
> + overflow_triggered = true;
> + env->spr[sprn] = PMC_COUNTER_NEGATIVE_VAL;
Does the hardware PMU actually guarantee that the event will happen
exactly on the overflow? Or could you count a few into the negative
zone before the event is delivered?
> + }
> + }
> +
> + return overflow_triggered;
> +}
> +
> static void pmu_update_cycles(CPUPPCState *env)
> {
> uint64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
> @@ -258,6 +282,20 @@ static void fire_PMC_interrupt(PowerPCCPU *cpu)
> return;
> }
>
> +/* This helper assumes that the PMC is running. */
> +void helper_insns_inc(CPUPPCState *env, uint32_t num_insns)
> +{
> + bool overflow_triggered;
> + PowerPCCPU *cpu;
> +
> + overflow_triggered = pmu_increment_insns(env, num_insns);
> +
> + if (overflow_triggered) {
> + cpu = env_archcpu(env);
> + fire_PMC_interrupt(cpu);
> + }
> +}
> +
> static void cpu_ppc_pmu_timer_cb(void *opaque)
> {
> PowerPCCPU *cpu = opaque;
> diff --git a/target/ppc/translate.c b/target/ppc/translate.c
> index 9960df6e18..ccc83d0603 100644
> --- a/target/ppc/translate.c
> +++ b/target/ppc/translate.c
> @@ -177,6 +177,7 @@ struct DisasContext {
> bool hr;
> bool mmcr0_pmcc0;
> bool mmcr0_pmcc1;
> + bool pmu_frozen;
> ppc_spr_t *spr_cb; /* Needed to check rights for mfspr/mtspr */
> int singlestep_enabled;
> uint32_t flags;
> @@ -4170,6 +4171,31 @@ static inline void gen_update_cfar(DisasContext *ctx,
> target_ulong nip)
> #endif
> }
>
> +#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY)
Should this actually be !CONFIG_USER_ONLY? IIUC there are
circumstances where userspace could access the PMU, including
instruction counting.
> +static void pmu_count_insns(DisasContext *ctx)
> +{
> + /* Do not bother calling the helper if the PMU is frozen */
> + if (ctx->pmu_frozen) {
> + return;
> + }
> +
> + /*
> + * The PMU insns_inc() helper stops the internal PMU timer if a
> + * counter overflows happens. In that case, if the guest is
> + * running with icount and we do not handle it beforehand,
> + * the helper can trigger a 'bad icount read'.
> + */
> + gen_icount_io_start(ctx);
> +
> + gen_helper_insns_inc(cpu_env, tcg_constant_i32(ctx->base.num_insns));
> +}
> +#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);
> @@ -4180,6 +4206,14 @@ static void gen_lookup_and_goto_ptr(DisasContext *ctx)
> if (unlikely(ctx->singlestep_enabled)) {
> gen_debug_exception(ctx);
> } 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();
> }
> }
> @@ -4191,6 +4225,7 @@ 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);
> @@ -8458,6 +8493,7 @@ static void ppc_tr_init_disas_context(DisasContextBase
> *dcbase, CPUState *cs)
> ctx->hr = (hflags >> HFLAGS_HR) & 1;
> ctx->mmcr0_pmcc0 = (hflags >> HFLAGS_PMCC0) & 1;
> ctx->mmcr0_pmcc1 = (hflags >> HFLAGS_PMCC1) & 1;
> + ctx->pmu_frozen = (hflags >> HFLAGS_MMCR0FC) & 1;
>
> ctx->singlestep_enabled = 0;
> if ((hflags >> HFLAGS_SE) & 1) {
> @@ -8564,6 +8600,7 @@ 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);
> @@ -8574,6 +8611,14 @@ 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;
>
> @@ -8581,6 +8626,7 @@ 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;
>
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
signature.asc
Description: PGP signature
- [PATCH v8 01/10] target/ppc: introduce PMUEventType and PMU overflow timers, (continued)
- [PATCH v8 01/10] target/ppc: introduce PMUEventType and PMU overflow timers, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 02/10] target/ppc: PMU basic cycle count for pseries TCG, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 03/10] target/ppc: PMU: update counters on PMCs r/w, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 04/10] target/ppc: PMU: update counters on MMCR1 write, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 05/10] target/ppc: enable PMU counter overflow with cycle events, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 06/10] target/ppc: enable PMU instruction count, Daniel Henrique Barboza, 2021/11/25
- Re: [PATCH v8 06/10] target/ppc: enable PMU instruction count,
David Gibson <=
- [PATCH v8 07/10] target/ppc/power8-pmu.c: add PM_RUN_INST_CMPL (0xFA) event, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 08/10] PPC64/TCG: Implement 'rfebb' instruction, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 09/10] target/ppc: PMU Event-Based exception support, Daniel Henrique Barboza, 2021/11/25
- [PATCH v8 10/10] target/ppc/excp_helper.c: EBB handling adjustments, Daniel Henrique Barboza, 2021/11/25