On Mon, Nov 02, 2015 at 09:58:14AM -0600, Andrew Jones wrote: > On Fri, Oct 30, 2015 at 03:32:43PM -0400, Christopher Covington wrote: > > Hi Drew, > > > > On 10/30/2015 09:00 AM, Andrew Jones wrote: > > > On Wed, Oct 28, 2015 at 03:12:55PM -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 <cov@xxxxxxxxxxxxxx> > > >> --- > > >> arm/pmu.c | 103 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++- > > >> 1 file changed, 102 insertions(+), 1 deletion(-) > > >> > > >> diff --git a/arm/pmu.c b/arm/pmu.c > > >> index 4334de4..788886a 100644 > > >> --- a/arm/pmu.c > > >> +++ b/arm/pmu.c > > >> @@ -43,6 +43,23 @@ static inline unsigned long get_pmccntr(void) > > >> asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=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( > > >> + " 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" > > >> + : [i] "+r" (i) > > >> + : [pmcr] "r" (pmcr), [z] "r" (0) > > >> + : "cc"); > > >> +} > > >> #elif defined(__aarch64__) > > >> static inline uint32_t get_pmcr(void) > > >> { > > >> @@ -64,6 +81,23 @@ 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" > > >> + : [i] "+r" (i) > > >> + : [pmcr] "r" (pmcr) > > >> + : "cc"); > > >> +} > > >> #endif > > >> > > >> struct pmu_data { > > >> @@ -131,12 +165,79 @@ 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) > > >> + cpi = atol(argv[0]); > > >> + > > >> 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(); > > >> } > > > > > > I applied and tested this (by adding -icount 1 -append 1 to the cmdline), > > > > Thanks for giving this a spin. For whatever reason the -icount argument is the > > exponent n in 2^n. I could match that logic if you prefer, but the pmu.c code > > Oh yeah, I forgot how you had that in your earlier posts. So in that > case > > Reviewed-by: Andrew Jones <drjones@xxxxxxxxxx> > > I've applied these three patches to > > https://github.com/rhdrjones/kvm-unit-tests/commits/staging > > I'll send a pull request to Paolo for that branch soon. Hi Christopher, I still have these queued on staging, but before we ask Paolo to commit, I think we should try them with Shannon's patches for KVM in order to make sure they work there, as well as with TCG (I have a feeling we'll need to initialize a couple more registers). Also, now that we've got the 'ACCEL' patch in master, we can take the unittests.cfg -icount patch as well. Can you please resubmit with any changes needed for KVM, and also with a unittests.cfg patch enabling both KVM and TCG tests? Thanks, drew > > Thanks, > drew > > > currently takes the fully calculated shift value rather than the exponent. > > I've been testing with the following option pairs (dependent on 'accel = tcg' > > support). > > > > -- >8 -- > > Subject: [PATCH] arm: pmu: Add -icount checking configurations > > > > Pass a couple -icount values in TCG mode and strictly check the > > resulting cycle counts. > > > > Signed-off-by: Christopher Covington <cov@xxxxxxxxxxxxxx> > > --- > > arm/unittests.cfg | 14 ++++++++++++++ > > 1 file changed, 14 insertions(+) > > > > diff --git a/arm/unittests.cfg b/arm/unittests.cfg > > index fd94adb..5ca1e6a 100644 > > --- a/arm/unittests.cfg > > +++ b/arm/unittests.cfg > > @@ -40,3 +40,17 @@ groups = selftest > > [pmu] > > file = pmu.flat > > groups = pmu > > + > > +# Test PMU support with -icount IPC=1 > > +[pmu-icount-1] > > +file = pmu.flat > > +extra_params = -icount 0 -append '1' > > +groups = pmu > > +accel = tcg > > + > > +# Test PMU support with -icount IPC=256 > > +[pmu-icount-256] > > +file = pmu.flat > > +extra_params = -icount 8 -append '256' > > +groups = pmu > > +accel = tcg > > -- > > Qualcomm Innovation Center, Inc. > > The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, > > a Linux Foundation Collaborative Project > > -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html