Re: [Qemu-devel] [kvm-unit-tests PATCHv5 3/3] arm: pmu: Add CPI checking

[Andrew Jones]

On Mon, Oct 26, 2015 at 11:38:50AM -0400, Christopher Covington wrote:
> Calculate the numbers of cycles per instruction (CPI) implied by ARM
> PMU cycle counter values. The code includes a strict checking facility
> intended for the -icount option in TCG mode but it is not yet enabled
> in the configuration file. Enabling it must wait on infrastructure
> improvements which allow for different tests to be run on TCG versus
> KVM.
> 
> Signed-off-by: Christopher Covington <address@hidden>
> ---
>  arm/pmu.c | 105 
> +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 104 insertions(+), 1 deletion(-)
> 
> diff --git a/arm/pmu.c b/arm/pmu.c
> index c44d708..59f26ab 100644
> --- a/arm/pmu.c
> +++ b/arm/pmu.c
> @@ -43,6 +43,25 @@ static inline unsigned long get_pmccntr(void)
>       asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (cycles));
>       return cycles;
>  }
> +
> +/*
> + * Extra instructions such as `mov rd, #0` inserted by the compiler would be

Probably don't need the 'such as `mov..`. Removing it also allows this
comment to directly match the 64-bit one.

> + * difficult to compensate for, so hand assemble everything between, and
> + * including, the PMCR accesses to start and stop counting.
> + */
> +static inline void loop(int i, uint32_t pmcr)
> +{
> +     uint32_t z = 0;
> +
> +     asm volatile(
> +     "       mcr p15, 0, %[pmcr], c9, c12, 0\n"
> +     "1:     subs %[i], %[i], #1\n"
> +     "       bgt 1b\n"
> +     "       mcr p15, 0, %[z], c9, c12, 0\n"

Thanks for making some formatting improvements. We're still
missing the tabs after the instructions though. The format
used by the kernel is

[label]<tab>insn<tab>operands

> +     : [i] "+r" (i)
> +     : [pmcr] "r" (pmcr), [z] "r" (z)

I don't think you should need the z variable. Just doing

[z] "r" (0)

should work.

> +     : "cc");
> +}
>  #elif defined(__aarch64__)
>  static inline uint32_t get_pmcr(void)
>  {
> @@ -64,6 +83,23 @@ static inline unsigned long get_pmccntr(void)
>       asm volatile("mrs %0, pmccntr_el0" : "=r" (cycles));
>       return cycles;
>  }
> +
> +/*
> + * Extra instructions inserted by the compiler would be difficult to 
> compensate
> + * for, so hand assemble everything between, and including, the PMCR accesses
> + * to start and stop counting.
> + */
> +static inline void loop(int i, uint32_t pmcr)
> +{
> +     asm volatile(
> +     "       msr pmcr_el0, %[pmcr]\n"
> +     "1:     subs %[i], %[i], #1\n"
> +     "       b.gt 1b\n"
> +     "       msr pmcr_el0, xzr\n"

same tab after insn comment

> +     : [i] "+r" (i)
> +     : [pmcr] "r" (pmcr)
> +     : "cc");
> +}
>  #endif
>  
>  struct pmu_data {
> @@ -131,12 +167,79 @@ static bool check_cycles_increase(void)
>       return true;
>  }
>  
> -int main(void)
> +/*
> + * Execute a known number of guest instructions. Only odd instruction counts
> + * greater than or equal to 3 are supported by the in-line assembly code. The
> + * control register (PMCR_EL0) is initialized with the provided value 
> (allowing
> + * for example for the cycle counter or event counters to be reset). At the 
> end
> + * of the exact instruction loop, zero is written to PMCR_EL0 to disable
> + * counting, allowing the cycle counter or event counters to be read at the
> + * leisure of the calling code.
> + */
> +static void measure_instrs(int num, uint32_t pmcr)
> +{
> +     int i = (num - 1) / 2;
> +
> +     assert(num >= 3 && ((num - 1) % 2 == 0));
> +     loop(i, pmcr);
> +}
> +
> +/*
> + * Measure cycle counts for various known instruction counts. Ensure that the
> + * cycle counter progresses (similar to check_cycles_increase() but with more
> + * instructions and using reset and stop controls). If supplied a positive,
> + * nonzero CPI parameter, also strictly check that every measurement matches
> + * it. Strict CPI checking is used to test -icount mode.
> + */
> +static bool check_cpi(int cpi)
> +{
> +     struct pmu_data pmu = { {0} };
> +
> +     pmu.cycle_counter_reset = 1;
> +     pmu.enable = 1;
> +
> +     if (cpi > 0)
> +             printf("Checking for CPI=%d.\n", cpi);
> +     printf("instrs : cycles0 cycles1 ...\n");
> +
> +     for (int i = 3; i < 300; i += 32) {
> +             int avg, sum = 0;
> +
> +             printf("%d :", i);
> +             for (int j = 0; j < NR_SAMPLES; j++) {
> +                     int cycles;
> +
> +                     measure_instrs(i, pmu.pmcr_el0);
> +                     cycles = get_pmccntr();
> +                     printf(" %d", cycles);
> +
> +                     if (!cycles || (cpi > 0 && cycles != i * cpi)) {
> +                             printf("\n");
> +                             return false;
> +                     }
> +
> +                     sum += cycles;
> +             }
> +             avg = sum / NR_SAMPLES;
> +             printf(" sum=%d avg=%d avg_ipc=%d avg_cpi=%d\n",
> +                     sum, avg, i / avg, avg / i);
> +     }
> +
> +     return true;
> +}
> +
> +int main(int argc, char *argv[])
>  {
> +     int cpi = 0;
> +
> +     if (argc > 1)

if (argc > 0)

Unlike a real main() we don't have the program name automatically put
in argv[0]. This inconsistency is a bit annoying, but to change it now
probably isn't worth it.

> +             cpi = atol(argv[0]);

Ah, looks like the right index is being used here though, so the above
check was probably supposed to be >=

> +
>       report_prefix_push("pmu");
>  
>       report("Control register", check_pmcr());
>       report("Monotonically increasing cycle count", check_cycles_increase());
> +     report("Cycle/instruction ratio", check_cpi(cpi));
>  
>       return report_summary();
>  }
> -- 
> Qualcomm Innovation Center, Inc.
> The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
> a Linux Foundation Collaborative Project
> 
> 

Thanks,
drew