From patchwork Thu Nov 24 04:23:42 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wei Huang X-Patchwork-Id: 9444791 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 754A360778 for ; Thu, 24 Nov 2016 04:24:00 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 6BED5279E0 for ; Thu, 24 Nov 2016 04:24:00 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 6065327EE9; Thu, 24 Nov 2016 04:24:00 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id C6DE1279E0 for ; Thu, 24 Nov 2016 04:23:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756692AbcKXEX4 (ORCPT ); Wed, 23 Nov 2016 23:23:56 -0500 Received: from mx1.redhat.com ([209.132.183.28]:39908 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756702AbcKXEXz (ORCPT ); Wed, 23 Nov 2016 23:23:55 -0500 Received: from int-mx10.intmail.prod.int.phx2.redhat.com (int-mx10.intmail.prod.int.phx2.redhat.com [10.5.11.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id E5ECA4E4DE; Thu, 24 Nov 2016 04:23:54 +0000 (UTC) Received: from weilaptop.redhat.com (vpn-57-189.rdu2.redhat.com [10.10.57.189]) by int-mx10.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id uAO4NhnR026665; Wed, 23 Nov 2016 23:23:52 -0500 From: Wei Huang To: cov@codeaurora.org Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu, shannon.zhao@linaro.org, alistair.francis@xilinx.com, croberts@codeaurora.org, alindsay@codeaurora.org, drjones@redhat.com, andre.przywara@arm.com Subject: [kvm-unit-tests PATCH v12 3/3] arm: pmu: Add CPI checking Date: Wed, 23 Nov 2016 22:23:42 -0600 Message-Id: <1479961422-4545-4-git-send-email-wei@redhat.com> In-Reply-To: <1479961422-4545-1-git-send-email-wei@redhat.com> References: <1479961422-4545-1-git-send-email-wei@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.23 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.38]); Thu, 24 Nov 2016 04:23:55 +0000 (UTC) Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Christopher Covington 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 in the configuration file. Signed-off-by: Christopher Covington Signed-off-by: Wei Huang Reviewed-by: Andrew Jones --- arm/pmu.c | 123 +++++++++++++++++++++++++++++++++++++++++++++++++++++- arm/unittests.cfg | 14 +++++++ 2 files changed, 136 insertions(+), 1 deletion(-) diff --git a/arm/pmu.c b/arm/pmu.c index 3ae6545..f05d00d 100644 --- a/arm/pmu.c +++ b/arm/pmu.c @@ -104,6 +104,27 @@ static inline uint32_t id_dfr0_read(void) asm volatile("mrc p15, 0, %0, c0, c1, 2" : "=r" (val)); return val; } + +/* + * 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. isb instructions were inserted to make sure + * pmccntr read after this function returns the exact instructions executed in + * the controlled block. Total instrs = isb + mcr + 2*loop = 2 + 2*loop. + */ +static inline void precise_instrs_loop(int loop, uint32_t pmcr) +{ + asm volatile( + " mcr p15, 0, %[pmcr], c9, c12, 0\n" + " isb\n" + "1: subs %[loop], %[loop], #1\n" + " bgt 1b\n" + " mcr p15, 0, %[z], c9, c12, 0\n" + " isb\n" + : [loop] "+r" (loop) + : [pmcr] "r" (pmcr), [z] "r" (0) + : "cc"); +} #elif defined(__aarch64__) static inline uint32_t pmcr_read(void) { @@ -150,6 +171,27 @@ static inline uint32_t id_dfr0_read(void) asm volatile("mrs %0, id_dfr0_el1" : "=r" (id)); return id; } + +/* + * 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. isb instructions are inserted to make sure + * pmccntr read after this function returns the exact instructions executed + * in the controlled block. Total instrs = isb + msr + 2*loop = 2 + 2*loop. + */ +static inline void precise_instrs_loop(int loop, uint32_t pmcr) +{ + asm volatile( + " msr pmcr_el0, %[pmcr]\n" + " isb\n" + "1: subs %[loop], %[loop], #1\n" + " b.gt 1b\n" + " msr pmcr_el0, xzr\n" + " isb\n" + : [loop] "+r" (loop) + : [pmcr] "r" (pmcr) + : "cc"); +} #endif /* @@ -207,6 +249,79 @@ static bool check_cycles_increase(void) return success; } +/* + * Execute a known number of guest instructions. Only even instruction counts + * greater than or equal to 4 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 loop = (num - 2) / 2; + + assert(num >= 4 && ((num - 2) % 2 == 0)); + precise_instrs_loop(loop, 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) +{ + uint32_t pmcr = pmcr_read() | PMU_PMCR_LC | PMU_PMCR_C | PMU_PMCR_E; + + /* init before event access, this test only cares about cycle count */ + pmcntenset_write(1 << PMU_CYCLE_IDX); + pmccfiltr_write(0); /* count cycles in EL0, EL1, but not EL2 */ + + if (cpi > 0) + printf("Checking for CPI=%d.\n", cpi); + printf("instrs : cycles0 cycles1 ...\n"); + + for (unsigned int i = 4; i < 300; i += 32) { + uint64_t avg, sum = 0; + + printf("%d :", i); + for (int j = 0; j < NR_SAMPLES; j++) { + uint64_t cycles; + + pmccntr_write(0); + measure_instrs(i, pmcr); + cycles = pmccntr_read(); + printf(" %"PRId64"", cycles); + + if (!cycles) { + printf("\ncycles not incrementing!\n"); + return false; + } else if (cpi > 0 && cycles != i * cpi) { + printf("\nunexpected cycle count received!\n"); + return false; + } else if ((cycles >> 32) != 0) { + /* The cycles taken by the loop above should + * fit in 32 bits easily. We check the upper + * 32 bits of the cycle counter to make sure + * there is no supprise. */ + printf("\ncycle count bigger than 32bit!\n"); + return false; + } + + sum += cycles; + } + avg = sum / NR_SAMPLES; + printf(" sum=%"PRId64" avg=%"PRId64" avg_ipc=%"PRId64" " + "avg_cpi=%"PRId64"\n", sum, avg, i / avg, avg / i); + } + + return true; +} + void pmu_init(void) { uint32_t dfr0; @@ -217,13 +332,19 @@ void pmu_init(void) report_info("PMU version: %d", pmu_version); } -int main(void) +int main(int argc, char *argv[]) { + int cpi = 0; + + if (argc > 1) + cpi = atol(argv[1]); + report_prefix_push("pmu"); pmu_init(); report("Control register", check_pmcr()); report("Monotonically increasing cycle count", check_cycles_increase()); + report("Cycle/instruction ratio", check_cpi(cpi)); return report_summary(); } diff --git a/arm/unittests.cfg b/arm/unittests.cfg index 816f494..044d97c 100644 --- a/arm/unittests.cfg +++ b/arm/unittests.cfg @@ -63,3 +63,17 @@ groups = pci [pmu] file = pmu.flat groups = pmu + +# Test PMU support (TCG) with -icount IPC=1 +[pmu-tcg-icount-1] +file = pmu.flat +extra_params = -icount 0 -append '1' +groups = pmu +accel = tcg + +# Test PMU support (TCG) with -icount IPC=256 +[pmu-tcg-icount-256] +file = pmu.flat +extra_params = -icount 8 -append '256' +groups = pmu +accel = tcg