From patchwork Sun Sep 1 14:21:09 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125281 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 49FFF112C for ; Sun, 1 Sep 2019 14:24:07 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 1F6D222CE9 for ; Sun, 1 Sep 2019 14:24:07 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 1F6D222CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57746 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qlx-00065e-MJ for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:24:05 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39443) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QjS-0004SO-AO for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4QjQ-0004Z5-AW for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:29 -0400 Received: from mga12.intel.com ([192.55.52.136]:16710) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4QjQ-0004WR-3E for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:28 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:25 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453071" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:24 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:09 +0800 Message-Id: <20190901142119.20482-2-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 01/11] util/cutils: Add qemu_strtotime_ps() X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" To convert strings with time suffixes to numbers, support time unit are "ps" for picosecond, "ns" for nanosecond, "us" for microsecond, "ms" for millisecond or "s" for second. Signed-off-by: Tao Xu --- New patch in v10. --- include/qemu/cutils.h | 1 + util/cutils.c | 82 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) diff --git a/include/qemu/cutils.h b/include/qemu/cutils.h index 12301340a4..0e70a807e1 100644 --- a/include/qemu/cutils.h +++ b/include/qemu/cutils.h @@ -180,5 +180,6 @@ int uleb128_decode_small(const uint8_t *in, uint32_t *n); * *str1 is <, == or > than *str2. */ int qemu_pstrcmp0(const char **str1, const char **str2); +int qemu_strtotime_ps(const char *nptr, const char **end, uint64_t *result); #endif diff --git a/util/cutils.c b/util/cutils.c index fd591cadf0..a50c15f46a 100644 --- a/util/cutils.c +++ b/util/cutils.c @@ -847,3 +847,85 @@ int qemu_pstrcmp0(const char **str1, const char **str2) { return g_strcmp0(*str1, *str2); } + +static int64_t timeunit_mul(const char *unitstr) +{ + if (g_strcmp0(unitstr, "ps") == 0) { + return 1; + } else if (g_strcmp0(unitstr, "ns") == 0) { + return 1000; + } else if (g_strcmp0(unitstr, "us") == 0) { + return 1000000; + } else if (g_strcmp0(unitstr, "ms") == 0) { + return 1000000000LL; + } else if (g_strcmp0(unitstr, "s") == 0) { + return 1000000000000LL; + } else { + return -1; + } +} + + +/* + * Convert string to time, support time unit are ps for picosecond, + * ns for nanosecond, us for microsecond, ms for millisecond or s for second. + * End pointer will be returned in *end, if not NULL. Return -ERANGE on + * overflow, and -EINVAL on other error. + */ +static int do_strtotime(const char *nptr, const char **end, + const char *default_unit, uint64_t *result) +{ + int retval; + const char *endptr; + int mul_required = 0; + int64_t mul; + double val, integral, fraction; + + retval = qemu_strtod_finite(nptr, &endptr, &val); + if (retval) { + goto out; + } + fraction = modf(val, &integral); + if (fraction != 0) { + mul_required = 1; + } + + mul = timeunit_mul(endptr); + + if (mul == 1000000000000LL) { + endptr++; + } else if (mul != -1) { + endptr += 2; + } else { + mul = timeunit_mul(default_unit); + assert(mul >= 0); + } + if (mul == 1 && mul_required) { + retval = -EINVAL; + goto out; + } + /* + * Values >= 0xfffffffffffffc00 overflow uint64_t after their trip + * through double (53 bits of precision). + */ + if ((val * (double)mul >= 0xfffffffffffffc00) || val < 0) { + retval = -ERANGE; + goto out; + } + *result = val * (double)mul; + retval = 0; + +out: + if (end) { + *end = endptr; + } else if (*endptr) { + retval = -EINVAL; + } + + return retval; +} + +int qemu_strtotime_ps(const char *nptr, const char **end, uint64_t *result) +{ + return do_strtotime(nptr, end, "ps", result); +} From patchwork Sun Sep 1 14:21:10 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125283 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 1CF0B14F7 for ; Sun, 1 Sep 2019 14:24:13 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id F16D622CE9 for ; Sun, 1 Sep 2019 14:24:12 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org F16D622CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57748 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qm3-0006CO-F6 for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:24:11 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39448) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QjS-0004SP-AP for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4QjQ-0004Ze-Qt for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:30 -0400 Received: from mga12.intel.com ([192.55.52.136]:16710) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4QjQ-0004WR-Hk for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:28 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:27 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453077" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:26 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:10 +0800 Message-Id: <20190901142119.20482-3-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 02/11] tests/cutils: Add test for qemu_strtotime_ps() X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" Test the input of basic, time suffixes, float, invaild, trailing and overflow. Signed-off-by: Tao Xu --- New patch in v10. --- tests/test-cutils.c | 199 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 199 insertions(+) diff --git a/tests/test-cutils.c b/tests/test-cutils.c index 1aa8351520..19c967d3d5 100644 --- a/tests/test-cutils.c +++ b/tests/test-cutils.c @@ -2179,6 +2179,193 @@ static void test_qemu_strtosz_metric(void) g_assert(endptr == str + 6); } +static void test_qemu_strtotime_ps_simple(void) +{ + const char *str; + const char *endptr; + int err; + uint64_t res = 0xbaadf00d; + + str = "0"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 0); + g_assert(endptr == str + 1); + + str = "56789"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 56789); + g_assert(endptr == str + 5); + + err = qemu_strtotime_ps(str, NULL, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 56789); + + /* Note: precision is 53 bits since we're parsing with strtod() */ + + str = "9007199254740991"; /* 2^53-1 */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 0x1fffffffffffff); + g_assert(endptr == str + 16); + + str = "9007199254740992"; /* 2^53 */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 0x20000000000000); + g_assert(endptr == str + 16); + + str = "9007199254740993"; /* 2^53+1 */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 0x20000000000000); /* rounded to 53 bits */ + g_assert(endptr == str + 16); + + str = "18446744073709549568"; /* 0xfffffffffffff800 (53 msbs set) */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 0xfffffffffffff800); + g_assert(endptr == str + 20); + + str = "18446744073709550591"; /* 0xfffffffffffffbff */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 0xfffffffffffff800); /* rounded to 53 bits */ + g_assert(endptr == str + 20); + + /* 0x7ffffffffffffe00..0x7fffffffffffffff get rounded to + * 0x8000000000000000, thus -ERANGE; see test_qemu_strtosz_erange() */ +} + +static void test_qemu_strtotime_ps_units(void) +{ + const char *ps = "1ps"; + const char *ns = "1ns"; + const char *us = "1us"; + const char *ms = "1ms"; + const char *s = "1s"; + int err; + const char *endptr; + uint64_t res = 0xbaadf00d; + + err = qemu_strtotime_ps(ps, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 1); + g_assert(endptr == ps + 3); + + err = qemu_strtotime_ps(ns, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 1000); + g_assert(endptr == ns + 3); + + err = qemu_strtotime_ps(us, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 1000000); + g_assert(endptr == us + 3); + + err = qemu_strtotime_ps(ms, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 1000000000LL); + g_assert(endptr == ms + 3); + + err = qemu_strtotime_ps(s, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 1000000000000ULL); + g_assert(endptr == s + 2); +} + +static void test_qemu_strtotime_ps_float(void) +{ + const char *str = "56.789ns"; + int err; + const char *endptr; + uint64_t res = 0xbaadf00d; + + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, 0); + g_assert_cmpint(res, ==, 56.789 * 1000); + g_assert(endptr == str + 8); +} + +static void test_qemu_strtotime_ps_invalid(void) +{ + const char *str; + const char *endptr; + int err; + uint64_t res = 0xbaadf00d; + + str = ""; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -EINVAL); + g_assert(endptr == str); + + str = " \t "; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -EINVAL); + g_assert(endptr == str); + + str = "crap"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -EINVAL); + g_assert(endptr == str); + + str = "inf"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -EINVAL); + g_assert(endptr == str); + + str = "NaN"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -EINVAL); + g_assert(endptr == str); +} + +static void test_qemu_strtotime_ps_trailing(void) +{ + const char *str; + int err; + uint64_t res = 0xbaadf00d; + + str = "123xxx"; + + err = qemu_strtotime_ps(str, NULL, &res); + g_assert_cmpint(err, ==, -EINVAL); +} + +static void test_qemu_strtotime_ps_erange(void) +{ + const char *str; + const char *endptr; + int err; + uint64_t res = 0xbaadf00d; + + str = "-1"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -ERANGE); + g_assert(endptr == str + 2); + + str = "18446744073709550592"; /* 0xfffffffffffffc00 */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -ERANGE); + g_assert(endptr == str + 20); + + str = "18446744073709551615"; /* 2^64-1 */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -ERANGE); + g_assert(endptr == str + 20); + + str = "18446744073709551616"; /* 2^64 */ + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -ERANGE); + g_assert(endptr == str + 20); + + str = "200000000000000s"; + err = qemu_strtotime_ps(str, &endptr, &res); + g_assert_cmpint(err, ==, -ERANGE); + g_assert(endptr == str + 16); +} + int main(int argc, char **argv) { g_test_init(&argc, &argv, NULL); @@ -2456,5 +2643,17 @@ int main(int argc, char **argv) g_test_add_func("/cutils/strtosz/metric", test_qemu_strtosz_metric); + g_test_add_func("/cutils/strtotime/simple", + test_qemu_strtotime_ps_simple); + g_test_add_func("/cutils/strtotime/units", + test_qemu_strtotime_ps_units); + g_test_add_func("/cutils/strtotime/float", + test_qemu_strtotime_ps_float); + g_test_add_func("/cutils/strtotime/invalid", + test_qemu_strtotime_ps_invalid); + g_test_add_func("/cutils/strtotime/trailing", + test_qemu_strtotime_ps_trailing); + g_test_add_func("/cutils/strtotime/erange", + test_qemu_strtotime_ps_erange); return g_test_run(); } From patchwork Sun Sep 1 14:21:11 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125285 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 48CC914F7 for ; Sun, 1 Sep 2019 14:24:16 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 296FD22CE9 for ; Sun, 1 Sep 2019 14:24:16 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 296FD22CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57750 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qm6-0006Gg-Iu for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:24:14 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39468) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QjU-0004Sm-Jz for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:33 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4QjT-0004d5-7k for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:32 -0400 Received: from mga12.intel.com ([192.55.52.136]:16712) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4QjS-0004b6-V2 for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:31 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:30 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453083" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:28 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:11 +0800 Message-Id: <20190901142119.20482-4-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 03/11] qapi: Add builtin type time X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" Add optional builtin type time, fallback is uint64. This type use qemu_strtotime_ps() for pre-converting time suffix to numbers. Signed-off-by: Tao Xu --- New patch in v10. --- include/qapi/visitor-impl.h | 4 ++++ include/qapi/visitor.h | 9 +++++++++ qapi/opts-visitor.c | 22 ++++++++++++++++++++++ qapi/qapi-visit-core.c | 12 ++++++++++++ qapi/qobject-input-visitor.c | 18 ++++++++++++++++++ qapi/trace-events | 1 + scripts/qapi/common.py | 2 ++ 7 files changed, 68 insertions(+) diff --git a/include/qapi/visitor-impl.h b/include/qapi/visitor-impl.h index 8ccb3b6c20..e0979563c7 100644 --- a/include/qapi/visitor-impl.h +++ b/include/qapi/visitor-impl.h @@ -88,6 +88,10 @@ struct Visitor void (*type_size)(Visitor *v, const char *name, uint64_t *obj, Error **errp); + /* Optional; fallback is type_uint64() */ + void (*type_time)(Visitor *v, const char *name, uint64_t *obj, + Error **errp); + /* Must be set */ void (*type_bool)(Visitor *v, const char *name, bool *obj, Error **errp); diff --git a/include/qapi/visitor.h b/include/qapi/visitor.h index 5b2ed3f202..4c3198b1c5 100644 --- a/include/qapi/visitor.h +++ b/include/qapi/visitor.h @@ -554,6 +554,15 @@ void visit_type_int64(Visitor *v, const char *name, int64_t *obj, void visit_type_size(Visitor *v, const char *name, uint64_t *obj, Error **errp); +/* + * Visit a uint64_t value. + * Like visit_type_uint64(), except that some visitors may choose to + * recognize numbers with timeunit suffix, such as "ps", "ns", "us" + * "ms" and "s". + */ +void visit_type_time(Visitor *v, const char *name, uint64_t *obj, + Error **errp); + /* * Visit a boolean value. * diff --git a/qapi/opts-visitor.c b/qapi/opts-visitor.c index 324b197495..d73b2e51a0 100644 --- a/qapi/opts-visitor.c +++ b/qapi/opts-visitor.c @@ -508,6 +508,27 @@ opts_type_size(Visitor *v, const char *name, uint64_t *obj, Error **errp) processed(ov, name); } +static void +opts_type_time(Visitor *v, const char *name, uint64_t *obj, Error **errp) +{ + OptsVisitor *ov = to_ov(v); + const QemuOpt *opt; + int err; + + opt = lookup_scalar(ov, name, errp); + if (!opt) { + return; + } + + err = qemu_strtotime_ps(opt->str ? opt->str : "", NULL, obj); + if (err < 0) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, opt->name, + "a time value"); + return; + } + + processed(ov, name); +} static void opts_optional(Visitor *v, const char *name, bool *present) @@ -555,6 +576,7 @@ opts_visitor_new(const QemuOpts *opts) ov->visitor.type_int64 = &opts_type_int64; ov->visitor.type_uint64 = &opts_type_uint64; ov->visitor.type_size = &opts_type_size; + ov->visitor.type_time = &opts_type_time; ov->visitor.type_bool = &opts_type_bool; ov->visitor.type_str = &opts_type_str; diff --git a/qapi/qapi-visit-core.c b/qapi/qapi-visit-core.c index 5365561b07..ac8896455c 100644 --- a/qapi/qapi-visit-core.c +++ b/qapi/qapi-visit-core.c @@ -277,6 +277,18 @@ void visit_type_size(Visitor *v, const char *name, uint64_t *obj, } } +void visit_type_time(Visitor *v, const char *name, uint64_t *obj, + Error **errp) +{ + assert(obj); + trace_visit_type_time(v, name, obj); + if (v->type_time) { + v->type_time(v, name, obj, errp); + } else { + v->type_uint64(v, name, obj, errp); + } +} + void visit_type_bool(Visitor *v, const char *name, bool *obj, Error **errp) { assert(obj); diff --git a/qapi/qobject-input-visitor.c b/qapi/qobject-input-visitor.c index 32236cbcb1..9b66941d8a 100644 --- a/qapi/qobject-input-visitor.c +++ b/qapi/qobject-input-visitor.c @@ -627,6 +627,23 @@ static void qobject_input_type_size_keyval(Visitor *v, const char *name, } } +static void qobject_input_type_time_keyval(Visitor *v, const char *name, + uint64_t *obj, Error **errp) +{ + QObjectInputVisitor *qiv = to_qiv(v); + const char *str = qobject_input_get_keyval(qiv, name, errp); + + if (!str) { + return; + } + + if (qemu_strtotime_ps(str, NULL, obj) < 0) { + /* TODO report -ERANGE more nicely */ + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + full_name(qiv, name), "time"); + } +} + static void qobject_input_optional(Visitor *v, const char *name, bool *present) { QObjectInputVisitor *qiv = to_qiv(v); @@ -708,6 +725,7 @@ Visitor *qobject_input_visitor_new_keyval(QObject *obj) v->visitor.type_any = qobject_input_type_any; v->visitor.type_null = qobject_input_type_null; v->visitor.type_size = qobject_input_type_size_keyval; + v->visitor.type_time = qobject_input_type_time_keyval; v->keyval = true; return &v->visitor; diff --git a/qapi/trace-events b/qapi/trace-events index 5eb4afa110..c4605a7ccc 100644 --- a/qapi/trace-events +++ b/qapi/trace-events @@ -29,6 +29,7 @@ visit_type_int16(void *v, const char *name, int16_t *obj) "v=%p name=%s obj=%p" visit_type_int32(void *v, const char *name, int32_t *obj) "v=%p name=%s obj=%p" visit_type_int64(void *v, const char *name, int64_t *obj) "v=%p name=%s obj=%p" visit_type_size(void *v, const char *name, uint64_t *obj) "v=%p name=%s obj=%p" +visit_type_time(void *v, const char *name, uint64_t *obj) "v=%p name=%s obj=%p" visit_type_bool(void *v, const char *name, bool *obj) "v=%p name=%s obj=%p" visit_type_str(void *v, const char *name, char **obj) "v=%p name=%s obj=%p" visit_type_number(void *v, const char *name, void *obj) "v=%p name=%s obj=%p" diff --git a/scripts/qapi/common.py b/scripts/qapi/common.py index d61bfdc526..3a6f108794 100644 --- a/scripts/qapi/common.py +++ b/scripts/qapi/common.py @@ -35,6 +35,7 @@ builtin_types = { 'uint32': 'QTYPE_QNUM', 'uint64': 'QTYPE_QNUM', 'size': 'QTYPE_QNUM', + 'time': 'QTYPE_QNUM', 'any': None, # any QType possible, actually 'QType': 'QTYPE_QSTRING', } @@ -1834,6 +1835,7 @@ class QAPISchema(object): ('uint32', 'int', 'uint32_t'), ('uint64', 'int', 'uint64_t'), ('size', 'int', 'uint64_t'), + ('time', 'int', 'uint64_t'), ('bool', 'boolean', 'bool'), ('any', 'value', 'QObject' + pointer_suffix), ('null', 'null', 'QNull' + pointer_suffix)]: From patchwork Sun Sep 1 14:21:12 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125291 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 36D98112C for ; Sun, 1 Sep 2019 14:27:15 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 17F0F22CE9 for ; Sun, 1 Sep 2019 14:27:15 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 17F0F22CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57778 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qoz-0001UO-GU for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:27:13 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39491) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QjW-0004YG-Px for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:36 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4QjV-0004hq-CE for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:34 -0400 Received: from mga12.intel.com ([192.55.52.136]:16717) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4QjV-0004f3-35 for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:33 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:32 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453090" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:30 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:12 +0800 Message-Id: <20190901142119.20482-5-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 04/11] tests: Add test for QAPI builtin type time X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" Add tests for time input such as zero, around limit of precision, signed upper limit, actual upper limit, beyond limits, time suffixes, and etc. Signed-off-by: Tao Xu --- New patch in v10. --- tests/test-keyval.c | 125 +++++++++++++++++++++++++++++ tests/test-qobject-input-visitor.c | 29 +++++++ 2 files changed, 154 insertions(+) diff --git a/tests/test-keyval.c b/tests/test-keyval.c index 09b0ae3c68..b36914f0fc 100644 --- a/tests/test-keyval.c +++ b/tests/test-keyval.c @@ -490,6 +490,130 @@ static void test_keyval_visit_size(void) visit_free(v); } +static void test_keyval_visit_time(void) +{ + Error *err = NULL; + Visitor *v; + QDict *qdict; + uint64_t time; + + /* Lower limit zero */ + qdict = keyval_parse("time1=0", NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &error_abort); + g_assert_cmpuint(time, ==, 0); + visit_check_struct(v, &error_abort); + visit_end_struct(v, NULL); + visit_free(v); + + /* Around limit of precision: 2^53-1, 2^53, 2^53+1 */ + qdict = keyval_parse("time1=9007199254740991," + "time2=9007199254740992," + "time3=9007199254740993", + NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &error_abort); + g_assert_cmphex(time, ==, 0x1fffffffffffff); + visit_type_time(v, "time2", &time, &error_abort); + g_assert_cmphex(time, ==, 0x20000000000000); + visit_type_time(v, "time3", &time, &error_abort); + g_assert_cmphex(time, ==, 0x20000000000000); + visit_check_struct(v, &error_abort); + visit_end_struct(v, NULL); + visit_free(v); + + /* Close to signed upper limit 0x7ffffffffffffc00 (53 msbs set) */ + qdict = keyval_parse("time1=9223372036854774784," /* 7ffffffffffffc00 */ + "time2=9223372036854775295", /* 7ffffffffffffdff */ + NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &error_abort); + g_assert_cmphex(time, ==, 0x7ffffffffffffc00); + visit_type_time(v, "time2", &time, &error_abort); + g_assert_cmphex(time, ==, 0x7ffffffffffffc00); + visit_check_struct(v, &error_abort); + visit_end_struct(v, NULL); + visit_free(v); + + /* Close to actual upper limit 0xfffffffffffff800 (53 msbs set) */ + qdict = keyval_parse("time1=18446744073709549568," /* fffffffffffff800 */ + "time2=18446744073709550591", /* fffffffffffffbff */ + NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &error_abort); + g_assert_cmphex(time, ==, 0xfffffffffffff800); + visit_type_time(v, "time2", &time, &error_abort); + g_assert_cmphex(time, ==, 0xfffffffffffff800); + visit_check_struct(v, &error_abort); + visit_end_struct(v, NULL); + visit_free(v); + + /* Beyond limits */ + qdict = keyval_parse("time1=-1," + "time2=18446744073709550592", /* fffffffffffffc00 */ + NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &err); + error_free_or_abort(&err); + visit_type_time(v, "time2", &time, &err); + error_free_or_abort(&err); + visit_end_struct(v, NULL); + visit_free(v); + + /* Suffixes */ + qdict = keyval_parse("time1=2ps,time2=3.4ns,time3=5us," + "time4=0.6ms,time5=700s", + NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &error_abort); + g_assert_cmpuint(time, ==, 2); + visit_type_time(v, "time2", &time, &error_abort); + g_assert_cmpuint(time, ==, 3400); + visit_type_time(v, "time3", &time, &error_abort); + g_assert_cmphex(time, ==, 5 * 1000 * 1000); + visit_type_time(v, "time4", &time, &error_abort); + g_assert_cmphex(time, ==, 600 * 1000 * 1000); + visit_type_time(v, "time5", &time, &error_abort); + g_assert_cmphex(time, ==, 700 * 1000000000000ULL); + visit_check_struct(v, &error_abort); + visit_end_struct(v, NULL); + visit_free(v); + + /* Beyond limit with suffix */ + qdict = keyval_parse("time1=18446745s", NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &err); + error_free_or_abort(&err); + visit_end_struct(v, NULL); + visit_free(v); + + /* Trailing crap */ + qdict = keyval_parse("time1=89ks,time2=ns", NULL, &error_abort); + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + qobject_unref(qdict); + visit_start_struct(v, NULL, NULL, 0, &error_abort); + visit_type_time(v, "time1", &time, &err); + error_free_or_abort(&err); + visit_type_time(v, "time2", &time, &err);; + error_free_or_abort(&err); + visit_end_struct(v, NULL); + visit_free(v); +} + static void test_keyval_visit_dict(void) { Error *err = NULL; @@ -678,6 +802,7 @@ int main(int argc, char *argv[]) g_test_add_func("/keyval/visit/bool", test_keyval_visit_bool); g_test_add_func("/keyval/visit/number", test_keyval_visit_number); g_test_add_func("/keyval/visit/size", test_keyval_visit_size); + g_test_add_func("/keyval/visit/time", test_keyval_visit_time); g_test_add_func("/keyval/visit/dict", test_keyval_visit_dict); g_test_add_func("/keyval/visit/list", test_keyval_visit_list); g_test_add_func("/keyval/visit/optional", test_keyval_visit_optional); diff --git a/tests/test-qobject-input-visitor.c b/tests/test-qobject-input-visitor.c index 6bacabf063..4b5820b744 100644 --- a/tests/test-qobject-input-visitor.c +++ b/tests/test-qobject-input-visitor.c @@ -366,6 +366,31 @@ static void test_visitor_in_size_str_fail(TestInputVisitorData *data, error_free_or_abort(&err); } +static void test_visitor_in_time_str_keyval(TestInputVisitorData *data, + const void *unused) +{ + uint64_t res, value = 265 * 1000 * 1000; + Visitor *v; + + v = visitor_input_test_init_full(data, true, "\"265us\""); + + visit_type_time(v, NULL, &res, &error_abort); + g_assert_cmpfloat(res, ==, value); +} + +static void test_visitor_in_time_str_fail(TestInputVisitorData *data, + const void *unused) +{ + uint64_t res = 0; + Visitor *v; + Error *err = NULL; + + v = visitor_input_test_init(data, "\"265us\""); + + visit_type_time(v, NULL, &res, &err); + error_free_or_abort(&err); +} + static void test_visitor_in_string(TestInputVisitorData *data, const void *unused) { @@ -1311,6 +1336,10 @@ int main(int argc, char **argv) NULL, test_visitor_in_size_str_keyval); input_visitor_test_add("/visitor/input/size_str_fail", NULL, test_visitor_in_size_str_fail); + input_visitor_test_add("/visitor/input/time_str_keyval", + NULL, test_visitor_in_time_str_keyval); + input_visitor_test_add("/visitor/input/time_str_fail", + NULL, test_visitor_in_time_str_fail); input_visitor_test_add("/visitor/input/string", NULL, test_visitor_in_string); input_visitor_test_add("/visitor/input/enum", From patchwork Sun Sep 1 14:21:13 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125293 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 14914112C for ; Sun, 1 Sep 2019 14:27:18 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id D96F022CE9 for ; Sun, 1 Sep 2019 14:27:17 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org D96F022CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57780 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qp2-0001Xg-4x for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:27:16 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39507) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QjZ-0004bD-7M for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:40 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4QjX-0004jv-FX for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:37 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4QjX-0004jJ-6g for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:35 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:34 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453097" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:32 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:13 +0800 Message-Id: <20190901142119.20482-6-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 05/11] numa: Extend CLI to provide initiator information for numa nodes X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" In ACPI 6.3 chapter 5.2.27 Heterogeneous Memory Attribute Table (HMAT), The initiator represents processor which access to memory. And in 5.2.27.3 Memory Proximity Domain Attributes Structure, the attached initiator is defined as where the memory controller responsible for a memory proximity domain. With attached initiator information, the topology of heterogeneous memory can be described. Extend CLI of "-numa node" option to indicate the initiator numa node-id. In the linux kernel, the codes in drivers/acpi/hmat/hmat.c parse and report the platform's HMAT tables. Suggested-by: Dan Williams Signed-off-by: Tao Xu --- Changes in v10: - Add machine oprion properties "-machine hmat=on|off" for enabling or disabling HMAT in QEMU. - Add more description for initiator option. - Report error then HMAT is enalbe and initiator option is missing. Not allow invaild initiator now. (Igor) --- hw/core/machine.c | 72 +++++++++++++++++++++++++++++++++++++++++++ hw/core/numa.c | 11 +++++++ include/sysemu/numa.h | 6 ++++ qapi/machine.json | 10 +++++- qemu-options.hx | 35 ++++++++++++++++++--- 5 files changed, 128 insertions(+), 6 deletions(-) diff --git a/hw/core/machine.c b/hw/core/machine.c index c5e0d52fbc..852f05c8c5 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -516,6 +516,20 @@ static void machine_set_nvdimm(Object *obj, bool value, Error **errp) ms->nvdimms_state->is_enabled = value; } +static bool machine_get_hmat(Object *obj, Error **errp) +{ + MachineState *ms = MACHINE(obj); + + return ms->numa_state->hmat_enabled; +} + +static void machine_set_hmat(Object *obj, bool value, Error **errp) +{ + MachineState *ms = MACHINE(obj); + + ms->numa_state->hmat_enabled = value; +} + static char *machine_get_nvdimm_persistence(Object *obj, Error **errp) { MachineState *ms = MACHINE(obj); @@ -643,6 +657,7 @@ void machine_set_cpu_numa_node(MachineState *machine, const CpuInstanceProperties *props, Error **errp) { MachineClass *mc = MACHINE_GET_CLASS(machine); + NodeInfo *numa_info = machine->numa_state->nodes; bool match = false; int i; @@ -712,6 +727,16 @@ void machine_set_cpu_numa_node(MachineState *machine, match = true; slot->props.node_id = props->node_id; slot->props.has_node_id = props->has_node_id; + + if (numa_info[props->node_id].initiator_valid && + (props->node_id != numa_info[props->node_id].initiator)) { + error_setg(errp, "The initiator of CPU NUMA node %" PRId64 + " should be itself.", props->node_id); + return; + } + numa_info[props->node_id].initiator_valid = true; + numa_info[props->node_id].has_cpu = true; + numa_info[props->node_id].initiator = props->node_id; } if (!match) { @@ -958,6 +983,13 @@ static void machine_initfn(Object *obj) if (mc->numa_mem_supported) { ms->numa_state = g_new0(NumaState, 1); + object_property_add_bool(obj, "hmat", + machine_get_hmat, machine_set_hmat, + &error_abort); + object_property_set_description(obj, "hmat", + "Set on/off to enable/disable " + "ACPI Heterogeneous Memory Attribute " + "Table (HMAT)", NULL); } /* Register notifier when init is done for sysbus sanity checks */ @@ -1046,6 +1078,41 @@ static char *cpu_slot_to_string(const CPUArchId *cpu) return g_string_free(s, false); } +static void numa_validate_initiator(NumaState *nstat) +{ + int i; + NodeInfo *numa_info = nstat->nodes; + + for (i = 0; i < nstat->num_nodes; i++) { + if (numa_info[i].initiator >= MAX_NODES) { + error_report("The initiator id %" PRIu16 " expects an integer " + "between 0 and %d", numa_info[i].initiator, + MAX_NODES - 1); + goto err; + } + + if (!numa_info[numa_info[i].initiator].present) { + error_report("NUMA node %" PRIu16 " is missing, use " + "'-numa node' option to declare it first.", + numa_info[i].initiator); + goto err; + } + + if (numa_info[numa_info[i].initiator].has_cpu) { + numa_info[i].initiator_valid = true; + } else { + error_report("The initiator of NUMA node %d is invalid.", i); + goto err; + } + } + + return; + +err: + error_printf("\n"); + exit(1); +} + static void machine_numa_finish_cpu_init(MachineState *machine) { int i; @@ -1086,6 +1153,11 @@ static void machine_numa_finish_cpu_init(MachineState *machine) machine_set_cpu_numa_node(machine, &props, &error_fatal); } } + + if (machine->numa_state->hmat_enabled) { + numa_validate_initiator(machine->numa_state); + } + if (s->len && !qtest_enabled()) { warn_report("CPU(s) not present in any NUMA nodes: %s", s->str); diff --git a/hw/core/numa.c b/hw/core/numa.c index 1cbaf590af..1e75c26e49 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -133,6 +133,17 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node, numa_info[nodenr].node_mem = object_property_get_uint(o, "size", NULL); numa_info[nodenr].node_memdev = MEMORY_BACKEND(o); } + + if (node->has_initiator) { + if (!ms->numa_state->hmat_enabled) { + error_setg(errp, "ACPI Heterogeneous Memory Attribute Table " + "(HMAT) is disabled, use -machine,hmat=yes before " + "set initiator of NUMA"); + return; + } + + numa_info[nodenr].initiator = node->initiator; + } numa_info[nodenr].present = true; max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1); ms->numa_state->num_nodes++; diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index ae9c41d02b..a788c3b126 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -18,6 +18,9 @@ struct NodeInfo { uint64_t node_mem; struct HostMemoryBackend *node_memdev; bool present; + bool has_cpu; + bool initiator_valid; + uint16_t initiator; uint8_t distance[MAX_NODES]; }; @@ -33,6 +36,9 @@ struct NumaState { /* Allow setting NUMA distance for different NUMA nodes */ bool have_numa_distance; + /* Detect if HMAT support is enabled. */ + bool hmat_enabled; + /* NUMA nodes information */ NodeInfo nodes[MAX_NODES]; }; diff --git a/qapi/machine.json b/qapi/machine.json index ca26779f1a..3c2914cd1c 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -463,6 +463,13 @@ # @memdev: memory backend object. If specified for one node, # it must be specified for all nodes. # +# @initiator: defined in ACPI 6.3 Chapter 5.2.27.3 Table 5-145, +# indicate the nodeid which has the memory controller +# responsible for this NUMA node. This field provides +# additional information as to the initiator node that +# is closest (as in directly attached) to this node, and +# therefore has the best performance (since 4.2) +# # Since: 2.1 ## { 'struct': 'NumaNodeOptions', @@ -470,7 +477,8 @@ '*nodeid': 'uint16', '*cpus': ['uint16'], '*mem': 'size', - '*memdev': 'str' }} + '*memdev': 'str', + '*initiator': 'uint16' }} ## # @NumaDistOptions: diff --git a/qemu-options.hx b/qemu-options.hx index ea0638e92d..9f568c58d1 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -43,7 +43,8 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \ " suppress-vmdesc=on|off disables self-describing migration (default=off)\n" " nvdimm=on|off controls NVDIMM support (default=off)\n" " enforce-config-section=on|off enforce configuration section migration (default=off)\n" - " memory-encryption=@var{} memory encryption object to use (default=none)\n", + " memory-encryption=@var{} memory encryption object to use (default=none)\n" + " hmat=on|off controls ACPI HMAT support (default=off)\n", QEMU_ARCH_ALL) STEXI @item -machine [type=]@var{name}[,prop=@var{value}[,...]] @@ -103,6 +104,9 @@ NOTE: this parameter is deprecated. Please use @option{-global} @option{migration.send-configuration}=@var{on|off} instead. @item memory-encryption=@var{} Memory encryption object to use. The default is none. +@item hmat=on|off +Enables or disables ACPI Heterogeneous Memory Attribute Table (HMAT) support. +The default is off. @end table ETEXI @@ -161,14 +165,14 @@ If any on the three values is given, the total number of CPUs @var{n} can be omi ETEXI DEF("numa", HAS_ARG, QEMU_OPTION_numa, - "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node]\n" - "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node]\n" + "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" + "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" "-numa dist,src=source,dst=destination,val=distance\n" "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n", QEMU_ARCH_ALL) STEXI -@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}] -@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}] +@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] +@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] @itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance} @itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}] @findex -numa @@ -215,6 +219,27 @@ split equally between them. @samp{mem} and @samp{memdev} are mutually exclusive. Furthermore, if one node uses @samp{memdev}, all of them have to use it. +@samp{initiator} is an additional option indicate the @var{initiator} +NUMA that has best performance (the lowest latency or largest bandwidth) +to this NUMA @var{node}. Note that this option can be set only when +the machine oprion properties "-machine hmat=on". + +Following example creates a machine with 2 NUMA nodes, node 0 has CPU. +node 1 has only memory, and its' initiator is node 0. Note that because +node 0 has CPU, by default the initiator of node 0 is itself and must be +itself. +@example +-machine hmat=on \ +-m 2G,slots=2,maxmem=4G \ +-object memory-backend-ram,size=1G,id=m0 \ +-object memory-backend-ram,size=1G,id=m1 \ +-numa node,nodeid=0,memdev=m0 \ +-numa node,nodeid=1,memdev=m1,initiator=0 \ +-smp 2,sockets=2,maxcpus=2 \ +-numa cpu,node-id=0,socket-id=0 \ +-numa cpu,node-id=0,socket-id=1 +@end example + @var{source} and @var{destination} are NUMA node IDs. @var{distance} is the NUMA distance from @var{source} to @var{destination}. The distance from a node to itself is always 10. If any pair of nodes is From patchwork Sun Sep 1 14:21:14 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125301 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id EC17E16B1 for ; Sun, 1 Sep 2019 14:30:38 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id CCC2822CE9 for ; Sun, 1 Sep 2019 14:30:38 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org CCC2822CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57812 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QsH-0005P7-1l for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:30:37 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39530) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qjb-0004eF-PU for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:41 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4QjZ-0004l3-64 for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:39 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4QjY-0004jJ-RZ for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:37 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:36 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453104" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:34 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:14 +0800 Message-Id: <20190901142119.20482-7-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 06/11] hmat acpi: Build Memory Proximity Domain Attributes Structure(s) X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, Jonathan Cameron , dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" From: Liu Jingqi HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table (HMAT). The specification references below link: http://www.uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf It describes the memory attributes, such as memory side cache attributes and bandwidth and latency details, related to the Memory Proximity Domain. The software is expected to use this information as hint for optimization. This structure describes Memory Proximity Domain Attributes by memory subsystem and its associativity with processor proximity domain as well as hint for memory usage. In the linux kernel, the codes in drivers/acpi/hmat/hmat.c parse and report the platform's HMAT tables. Reviewed-by: Daniel Black Reviewed-by: Jonathan Cameron Signed-off-by: Liu Jingqi Signed-off-by: Tao Xu --- No changes in v10 --- hw/acpi/Kconfig | 5 +++ hw/acpi/Makefile.objs | 1 + hw/acpi/hmat.c | 101 ++++++++++++++++++++++++++++++++++++++++++ hw/acpi/hmat.h | 45 +++++++++++++++++++ hw/i386/acpi-build.c | 3 ++ 5 files changed, 155 insertions(+) create mode 100644 hw/acpi/hmat.c create mode 100644 hw/acpi/hmat.h diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index 7c59cf900b..039bb99efa 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -7,6 +7,7 @@ config ACPI_X86 select ACPI_NVDIMM select ACPI_CPU_HOTPLUG select ACPI_MEMORY_HOTPLUG + select ACPI_HMAT config ACPI_X86_ICH bool @@ -31,3 +32,7 @@ config ACPI_VMGENID bool default y depends on PC + +config ACPI_HMAT + bool + depends on ACPI diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index 9bb2101e3b..c05019b059 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -6,6 +6,7 @@ common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o common-obj-$(CONFIG_ACPI_VMGENID) += vmgenid.o +common-obj-$(CONFIG_ACPI_HMAT) += hmat.o common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.o diff --git a/hw/acpi/hmat.c b/hw/acpi/hmat.c new file mode 100644 index 0000000000..1368fce7ee --- /dev/null +++ b/hw/acpi/hmat.c @@ -0,0 +1,101 @@ +/* + * HMAT ACPI Implementation + * + * Copyright(C) 2019 Intel Corporation. + * + * Author: + * Liu jingqi + * Tao Xu + * + * HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table + * (HMAT) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + */ + +#include "qemu/osdep.h" +#include "sysemu/numa.h" +#include "hw/acpi/hmat.h" + +/* + * ACPI 6.3: + * 5.2.27.3 Memory Proximity Domain Attributes Structure: Table 5-145 + */ +static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, + int mem_node) +{ + + /* Memory Proximity Domain Attributes Structure */ + /* Type */ + build_append_int_noprefix(table_data, 0, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); + /* Length */ + build_append_int_noprefix(table_data, 40, 4); + /* Flags */ + build_append_int_noprefix(table_data, flags, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); + /* Proximity Domain for the Attached Initiator */ + build_append_int_noprefix(table_data, initiator, 4); + /* Proximity Domain for the Memory */ + build_append_int_noprefix(table_data, mem_node, 4); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 4); + /* + * Reserved: + * Previously defined as the Start Address of the System Physical + * Address Range. Deprecated since ACPI Spec 6.3. + */ + build_append_int_noprefix(table_data, 0, 8); + /* + * Reserved: + * Previously defined as the Range Length of the region in bytes. + * Deprecated since ACPI Spec 6.3. + */ + build_append_int_noprefix(table_data, 0, 8); +} + +/* Build HMAT sub table structures */ +static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) +{ + uint16_t flags; + int i; + + for (i = 0; i < nstat->num_nodes; i++) { + flags = 0; + + if (nstat->nodes[i].initiator_valid) { + flags |= HMAT_PROX_INIT_VALID; + } + + build_hmat_mpda(table_data, flags, nstat->nodes[i].initiator, i); + } +} + +void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat) +{ + uint64_t hmat_start; + + hmat_start = table_data->len; + + /* reserve space for HMAT header */ + acpi_data_push(table_data, 40); + + hmat_build_table_structs(table_data, nstat); + + build_header(linker, table_data, + (void *)(table_data->data + hmat_start), + "HMAT", table_data->len - hmat_start, 2, NULL, NULL); +} diff --git a/hw/acpi/hmat.h b/hw/acpi/hmat.h new file mode 100644 index 0000000000..0c1839cf6f --- /dev/null +++ b/hw/acpi/hmat.h @@ -0,0 +1,45 @@ +/* + * HMAT ACPI Implementation Header + * + * Copyright(C) 2019 Intel Corporation. + * + * Author: + * Liu jingqi + * Tao Xu + * + * HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table + * (HMAT) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + */ + +#ifndef HMAT_H +#define HMAT_H + +#include "hw/acpi/acpi-defs.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/bios-linker-loader.h" +#include "hw/acpi/aml-build.h" + +/* + * ACPI 6.3: 5.2.27.3 Memory Proximity Domain Attributes Structure, + * Table 5-145, Field "flag", Bit [0]: set to 1 to indicate that data in + * the Proximity Domain for the Attached Initiator field is valid. + * Other bits reserved. + */ +#define HMAT_PROX_INIT_VALID 0x1 + +void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat); + +#endif diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index e54e571a75..ff9a5983eb 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -68,6 +68,7 @@ #include "hw/i386/intel_iommu.h" #include "hw/acpi/ipmi.h" +#include "hw/acpi/hmat.h" /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and * -M pc-i440fx-2.0. Even if the actual amount of AML generated grows @@ -2698,6 +2699,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) acpi_add_table(table_offsets, tables_blob); build_slit(tables_blob, tables->linker, machine); } + acpi_add_table(table_offsets, tables_blob); + build_hmat(tables_blob, tables->linker, machine->numa_state); } if (acpi_get_mcfg(&mcfg)) { acpi_add_table(table_offsets, tables_blob); From patchwork Sun Sep 1 14:21:15 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125303 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 4859B1510 for ; Sun, 1 Sep 2019 14:33:45 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 2481522CE9 for ; Sun, 1 Sep 2019 14:33:45 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 2481522CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57838 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4QvI-00089l-As for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:33:44 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39538) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qjc-0004fG-NV for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:42 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4Qjb-0004mr-8O for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:40 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4Qja-0004jJ-UW for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:39 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:38 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453111" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:36 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:15 +0800 Message-Id: <20190901142119.20482-8-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 07/11] hmat acpi: Build System Locality Latency and Bandwidth Information Structure(s) X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, Jonathan Cameron , dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" From: Liu Jingqi This structure describes the memory access latency and bandwidth information from various memory access initiator proximity domains. The latency and bandwidth numbers represented in this structure correspond to rated latency and bandwidth for the platform. The software could use this information as hint for optimization. Reviewed-by: Daniel Black Reviewed-by: Jonathan Cameron Signed-off-by: Liu Jingqi Signed-off-by: Tao Xu --- No changes in v10. --- hw/acpi/hmat.c | 95 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 41 ++++++++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 24 +++++++++++ 4 files changed, 160 insertions(+), 1 deletion(-) diff --git a/hw/acpi/hmat.c b/hw/acpi/hmat.c index 1368fce7ee..27e7ff63f8 100644 --- a/hw/acpi/hmat.c +++ b/hw/acpi/hmat.c @@ -67,11 +67,81 @@ static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, build_append_int_noprefix(table_data, 0, 8); } +/* + * ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information + * Structure: Table 5-146 + */ +static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *hmat_lb, + uint32_t num_initiator, uint32_t num_target, + uint32_t *initiator_pxm, int type) +{ + uint32_t s = num_initiator; + uint32_t t = num_target; + uint8_t m, n; + uint8_t mask = 0x0f; + int i; + + /* Type */ + build_append_int_noprefix(table_data, 1, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); + /* Length */ + build_append_int_noprefix(table_data, 32 + 4 * s + 4 * t + 2 * s * t, 4); + /* Flags: Bits [3:0] Memory Hierarchy, Bits[7:4] Reserved */ + build_append_int_noprefix(table_data, hmat_lb->hierarchy & mask, 1); + /* Data Type */ + build_append_int_noprefix(table_data, hmat_lb->data_type, 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); + /* Number of Initiator Proximity Domains (s) */ + build_append_int_noprefix(table_data, s, 4); + /* Number of Target Proximity Domains (t) */ + build_append_int_noprefix(table_data, t, 4); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 4); + + /* Entry Base Unit */ + if (HMAT_IS_LATENCY(type)) { + build_append_int_noprefix(table_data, hmat_lb->base_lat, 8); + } else { + build_append_int_noprefix(table_data, hmat_lb->base_bw, 8); + } + + /* Initiator Proximity Domain List */ + for (i = 0; i < s; i++) { + build_append_int_noprefix(table_data, initiator_pxm[i], 4); + } + + /* Target Proximity Domain List */ + for (i = 0; i < t; i++) { + build_append_int_noprefix(table_data, i, 4); + } + + /* Latency or Bandwidth Entries */ + for (i = 0; i < s; i++) { + m = initiator_pxm[i]; + for (n = 0; n < t; n++) { + uint16_t entry; + + if (HMAT_IS_LATENCY(type)) { + entry = hmat_lb->latency[m][n]; + } else { + entry = hmat_lb->bandwidth[m][n]; + } + + build_append_int_noprefix(table_data, entry, 2); + } + } +} + /* Build HMAT sub table structures */ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) { uint16_t flags; - int i; + uint32_t num_initiator = 0; + uint32_t initiator_pxm[MAX_NODES]; + int i, hrchy, type; + HMAT_LB_Info *numa_hmat_lb; for (i = 0; i < nstat->num_nodes; i++) { flags = 0; @@ -82,6 +152,29 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) build_hmat_mpda(table_data, flags, nstat->nodes[i].initiator, i); } + + for (i = 0; i < nstat->num_nodes; i++) { + if (nstat->nodes[i].has_cpu) { + initiator_pxm[num_initiator++] = i; + } + } + + /* + * ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information + * Structure: Table 5-146 + */ + for (hrchy = HMAT_LB_MEM_MEMORY; + hrchy <= HMAT_LB_MEM_CACHE_3RD_LEVEL; hrchy++) { + for (type = HMAT_LB_DATA_ACCESS_LATENCY; + type <= HMAT_LB_DATA_WRITE_BANDWIDTH; type++) { + numa_hmat_lb = nstat->hmat_lb[hrchy][type]; + + if (numa_hmat_lb) { + build_hmat_lb(table_data, numa_hmat_lb, num_initiator, + nstat->num_nodes, initiator_pxm, type); + } + } + } } void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat) diff --git a/hw/acpi/hmat.h b/hw/acpi/hmat.h index 0c1839cf6f..79ddb873c1 100644 --- a/hw/acpi/hmat.h +++ b/hw/acpi/hmat.h @@ -40,6 +40,47 @@ */ #define HMAT_PROX_INIT_VALID 0x1 +#define HMAT_IS_LATENCY(type) (type <= HMAT_LB_DATA_WRITE_LATENCY) + +struct HMAT_LB_Info { + /* + * Indicates total number of Proximity Domains + * that can initiate memory access requests. + */ + uint32_t num_initiator; + /* + * Indicates total number of Proximity Domains + * that can act as target. + */ + uint32_t num_target; + /* + * Indicates it's memory or + * the specified level memory side cache. + */ + uint8_t hierarchy; + /* + * Present the type of data, + * access/read/write latency or bandwidth. + */ + uint8_t data_type; + /* The base unit for latency in nanoseconds. */ + uint64_t base_lat; + /* The base unit for bandwidth in megabytes per second(MB/s). */ + uint64_t base_bw; + /* + * latency[i][j]: + * Indicates the latency based on base_lat + * from Initiator Proximity Domain i to Target Proximity Domain j. + */ + uint16_t latency[MAX_NODES][MAX_NODES]; + /* + * bandwidth[i][j]: + * Indicates the bandwidth based on base_bw + * from Initiator Proximity Domain i to Target Proximity Domain j. + */ + uint16_t bandwidth[MAX_NODES][MAX_NODES]; +}; + void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat); #endif diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index 375770a80f..ad8955ecd8 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -49,6 +49,7 @@ typedef struct FWCfgEntry FWCfgEntry; typedef struct FWCfgIoState FWCfgIoState; typedef struct FWCfgMemState FWCfgMemState; typedef struct FWCfgState FWCfgState; +typedef struct HMAT_LB_Info HMAT_LB_Info; typedef struct HostMemoryBackend HostMemoryBackend; typedef struct HVFX86EmulatorState HVFX86EmulatorState; typedef struct I2CBus I2CBus; diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index a788c3b126..8dbf76c5b4 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -14,6 +14,27 @@ struct CPUArchId; #define NUMA_DISTANCE_MAX 254 #define NUMA_DISTANCE_UNREACHABLE 255 +/* the value of AcpiHmatLBInfo flags */ +enum { + HMAT_LB_MEM_MEMORY = 0, + HMAT_LB_MEM_CACHE_1ST_LEVEL = 1, + HMAT_LB_MEM_CACHE_2ND_LEVEL = 2, + HMAT_LB_MEM_CACHE_3RD_LEVEL = 3, +}; + +/* the value of AcpiHmatLBInfo data type */ +enum { + HMAT_LB_DATA_ACCESS_LATENCY = 0, + HMAT_LB_DATA_READ_LATENCY = 1, + HMAT_LB_DATA_WRITE_LATENCY = 2, + HMAT_LB_DATA_ACCESS_BANDWIDTH = 3, + HMAT_LB_DATA_READ_BANDWIDTH = 4, + HMAT_LB_DATA_WRITE_BANDWIDTH = 5, +}; + +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1) +#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1) + struct NodeInfo { uint64_t node_mem; struct HostMemoryBackend *node_memdev; @@ -41,6 +62,9 @@ struct NumaState { /* NUMA nodes information */ NodeInfo nodes[MAX_NODES]; + + /* NUMA modes HMAT Locality Latency and Bandwidth Information */ + HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS][HMAT_LB_TYPES]; }; typedef struct NumaState NumaState; From patchwork Sun Sep 1 14:21:16 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125299 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 819D5112C for ; Sun, 1 Sep 2019 14:30:31 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 62BFB22CE9 for ; Sun, 1 Sep 2019 14:30:31 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 62BFB22CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57810 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qs9-0005Dm-Js for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:30:29 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39553) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qje-0004h0-MI for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:44 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4Qjd-0004oh-CA for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:42 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4Qjd-0004jJ-1Y for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:41 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:40 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453123" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:38 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:16 +0800 Message-Id: <20190901142119.20482-9-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 08/11] hmat acpi: Build Memory Side Cache Information Structure(s) X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, Jonathan Cameron , dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" From: Liu Jingqi This structure describes memory side cache information for memory proximity domains if the memory side cache is present and the physical device forms the memory side cache. The software could use this information to effectively place the data in memory to maximize the performance of the system memory that use the memory side cache. Reviewed-by: Daniel Black Reviewed-by: Jonathan Cameron Signed-off-by: Liu Jingqi Signed-off-by: Tao Xu --- No changes in v10 --- hw/acpi/hmat.c | 64 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 17 +++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 5 ++++ 4 files changed, 86 insertions(+), 1 deletion(-) diff --git a/hw/acpi/hmat.c b/hw/acpi/hmat.c index 27e7ff63f8..71d8950241 100644 --- a/hw/acpi/hmat.c +++ b/hw/acpi/hmat.c @@ -134,14 +134,63 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *hmat_lb, } } +/* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: Table 5-147 */ +static void build_hmat_cache(GArray *table_data, HMAT_Cache_Info *hmat_cache) +{ + /* + * Cache Attributes: Bits [3:0] – Total Cache Levels + * for this Memory Proximity Domain + */ + uint32_t cache_attr = hmat_cache->total_levels & 0xF; + + /* Bits [7:4] : Cache Level described in this structure */ + cache_attr |= (hmat_cache->level & 0xF) << 4; + + /* Bits [11:8] - Cache Associativity */ + cache_attr |= (hmat_cache->associativity & 0xF) << 8; + + /* Bits [15:12] - Write Policy */ + cache_attr |= (hmat_cache->write_policy & 0xF) << 12; + + /* Bits [31:16] - Cache Line size in bytes */ + cache_attr |= (hmat_cache->line_size & 0xFFFF) << 16; + + cache_attr = cpu_to_le32(cache_attr); + + /* Type */ + build_append_int_noprefix(table_data, 2, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); + /* Length */ + build_append_int_noprefix(table_data, 32, 4); + /* Proximity Domain for the Memory */ + build_append_int_noprefix(table_data, hmat_cache->mem_proximity, 4); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 4); + /* Memory Side Cache Size */ + build_append_int_noprefix(table_data, hmat_cache->size, 8); + /* Cache Attributes */ + build_append_int_noprefix(table_data, cache_attr, 4); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); + /* + * Number of SMBIOS handles (n) + * Linux kernel uses Memory Side Cache Information Structure + * without SMBIOS entries for now, so set Number of SMBIOS handles + * as 0. + */ + build_append_int_noprefix(table_data, 0, 2); +} + /* Build HMAT sub table structures */ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) { uint16_t flags; uint32_t num_initiator = 0; uint32_t initiator_pxm[MAX_NODES]; - int i, hrchy, type; + int i, hrchy, type, level; HMAT_LB_Info *numa_hmat_lb; + HMAT_Cache_Info *numa_hmat_cache; for (i = 0; i < nstat->num_nodes; i++) { flags = 0; @@ -175,6 +224,19 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) } } } + + /* + * ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: + * Table 5-147 + */ + for (i = 0; i < nstat->num_nodes; i++) { + for (level = 0; level <= MAX_HMAT_CACHE_LEVEL; level++) { + numa_hmat_cache = nstat->hmat_cache[i][level]; + if (numa_hmat_cache) { + build_hmat_cache(table_data, numa_hmat_cache); + } + } + } } void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat) diff --git a/hw/acpi/hmat.h b/hw/acpi/hmat.h index 79ddb873c1..1373f22b27 100644 --- a/hw/acpi/hmat.h +++ b/hw/acpi/hmat.h @@ -81,6 +81,23 @@ struct HMAT_LB_Info { uint16_t bandwidth[MAX_NODES][MAX_NODES]; }; +struct HMAT_Cache_Info { + /* The memory proximity domain to which the memory belongs. */ + uint32_t mem_proximity; + /* Size of memory side cache in bytes. */ + uint64_t size; + /* Total cache levels for this memory proximity domain. */ + uint8_t total_levels; + /* Cache level described in this structure. */ + uint8_t level; + /* Cache Associativity: None/Direct Mapped/Comple Cache Indexing */ + uint8_t associativity; + /* Write Policy: None/Write Back(WB)/Write Through(WT) */ + uint8_t write_policy; + /* Cache Line size in bytes. */ + uint16_t line_size; +}; + void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat); #endif diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index ad8955ecd8..426fd503f0 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -49,6 +49,7 @@ typedef struct FWCfgEntry FWCfgEntry; typedef struct FWCfgIoState FWCfgIoState; typedef struct FWCfgMemState FWCfgMemState; typedef struct FWCfgState FWCfgState; +typedef struct HMAT_Cache_Info HMAT_Cache_Info; typedef struct HMAT_LB_Info HMAT_LB_Info; typedef struct HostMemoryBackend HostMemoryBackend; typedef struct HVFX86EmulatorState HVFX86EmulatorState; diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index 8dbf76c5b4..dc48d39439 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -35,6 +35,8 @@ enum { #define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1) #define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1) +#define MAX_HMAT_CACHE_LEVEL 3 + struct NodeInfo { uint64_t node_mem; struct HostMemoryBackend *node_memdev; @@ -65,6 +67,9 @@ struct NumaState { /* NUMA modes HMAT Locality Latency and Bandwidth Information */ HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS][HMAT_LB_TYPES]; + + /* Memory Side Cache Information Structure */ + HMAT_Cache_Info *hmat_cache[MAX_NODES][MAX_HMAT_CACHE_LEVEL + 1]; }; typedef struct NumaState NumaState; From patchwork Sun Sep 1 14:21:17 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125289 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 048AC13B1 for ; Sun, 1 Sep 2019 14:27:14 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 7DEB622CE9 for ; Sun, 1 Sep 2019 14:27:13 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 7DEB622CE9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57776 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qoy-0001SR-0n for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:27:12 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39568) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qji-0004ka-9Y for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:49 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4Qjg-0004rA-8J for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:46 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4Qjf-0004jJ-5S for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:43 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:42 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453134" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:40 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:17 +0800 Message-Id: <20190901142119.20482-10-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 09/11] numa: Extend CLI to provide memory latency and bandwidth information X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" From: Liu Jingqi Add -numa hmat-lb option to provide System Locality Latency and Bandwidth Information. These memory attributes help to build System Locality Latency and Bandwidth Information Structure(s) in ACPI Heterogeneous Memory Attribute Table (HMAT). Signed-off-by: Liu Jingqi Signed-off-by: Tao Xu --- Changes in v10: - use new builtin type 'time' as qapi input. --- hw/core/numa.c | 164 ++++++++++++++++++++++++++++++++++++++++++ include/sysemu/numa.h | 2 + qapi/machine.json | 95 +++++++++++++++++++++++- qemu-options.hx | 49 ++++++++++++- 4 files changed, 307 insertions(+), 3 deletions(-) diff --git a/hw/core/numa.c b/hw/core/numa.c index 1e75c26e49..7387547793 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -42,6 +42,7 @@ #include "qemu/option.h" #include "qemu/config-file.h" #include "qemu/cutils.h" +#include "hw/acpi/hmat.h" QemuOptsList qemu_numa_opts = { .name = "numa", @@ -186,6 +187,152 @@ void parse_numa_distance(MachineState *ms, NumaDistOptions *dist, Error **errp) ms->numa_state->have_numa_distance = true; } +static uint64_t hmat_get_base(uint64_t lb_data, int unit) +{ + uint64_t base = 1; + + while (lb_data >= UINT16_MAX && QEMU_IS_ALIGNED(lb_data, unit)) { + lb_data /= unit; + base *= unit; + } + + if (lb_data < UINT16_MAX) { + return base; + } else { + return 0; + } +} + +void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node, + Error **errp) +{ + int nb_numa_nodes = ms->numa_state->num_nodes; + NodeInfo *numa_info = ms->numa_state->nodes; + HMAT_LB_Info *hmat_lb = NULL; + uint64_t base_lat = 0, base_bw = 0, bw_mb; + + if (node->data_type <= HMATLB_DATA_TYPE_WRITE_LATENCY) { + if (!node->has_latency) { + error_setg(errp, "Missing 'latency' option."); + return; + } + if (node->has_bandwidth) { + error_setg(errp, "Invalid option 'bandwidth' since " + "the data type is latency."); + return; + } + } + + if (node->data_type >= HMATLB_DATA_TYPE_ACCESS_BANDWIDTH) { + if (!node->has_bandwidth) { + error_setg(errp, "Missing 'bandwidth' option."); + return; + } + if (node->has_latency) { + error_setg(errp, "Invalid option 'latency' since " + "the data type is bandwidth."); + return; + } + } + + if (node->initiator >= nb_numa_nodes) { + error_setg(errp, "Invalid initiator=%" + PRIu16 ", it should be less than %d.", + node->initiator, nb_numa_nodes); + return; + } + if (!numa_info[node->initiator].has_cpu) { + error_setg(errp, "Invalid initiator=%" + PRIu16 ", it isn't an initiator proximity domain.", + node->initiator); + return; + } + + if (node->target >= nb_numa_nodes) { + error_setg(errp, "Invalid target=%" + PRIu16 ", it should be less than %d.", + node->target, nb_numa_nodes); + return; + } + if (!numa_info[node->target].present) { + error_setg(errp, "Invalid target=%" + PRIu16 ", it hasn't a valid NUMA node.", + node->target); + return; + } + + if (node->has_latency) { + hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type]; + + if (!hmat_lb) { + hmat_lb = g_malloc0(sizeof(*hmat_lb)); + ms->numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb; + } else if (hmat_lb->latency[node->initiator][node->target]) { + error_setg(errp, "Duplicate configuration of the latency for " + "initiator=%" PRIu16 " and target=%" PRIu16 ".", + node->initiator, node->target); + return; + } + + base_lat = hmat_get_base(node->latency, 1000); + if (base_lat == 0) { + error_setg(errp, "Latency value %" PRIu64 " overflow, max value" + " is %" PRIu16, node->latency, UINT16_MAX - 1); + return; + } + + /* Only the first time of setting the base unit is valid. */ + if (hmat_lb->base_lat == 0) { + hmat_lb->base_lat = base_lat; + } else if (hmat_lb->base_lat != base_lat) { + error_setg(errp, "Invalid base latency unit %" PRIu64 ", all " + "latencies must be specified in the same units.", base_lat); + return; + } + + hmat_lb->latency[node->initiator][node->target] = + node->latency / base_lat; + } + + if (node->has_bandwidth) { + hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type]; + bw_mb = node->bandwidth / 1024 / 1024; + + if (!hmat_lb) { + hmat_lb = g_malloc0(sizeof(*hmat_lb)); + ms->numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb; + } else if (hmat_lb->bandwidth[node->initiator][node->target]) { + error_setg(errp, "Duplicate configuration of the bandwidth for " + "initiator=%" PRIu16 " and target=%" PRIu16 ".", + node->initiator, node->target); + return; + } + + base_bw = hmat_get_base(bw_mb, 1024); + if (base_bw == 0) { + error_setg(errp, "Bandwidth value %" PRIu64 " overflow, max value" + " is %" PRIu16, bw_mb, UINT16_MAX - 1); + return; + } + + /* Only the first time of setting the base unit is valid. */ + if (hmat_lb->base_bw == 0) { + hmat_lb->base_bw = base_bw; + } else if (hmat_lb->base_bw != base_bw) { + error_setg(errp, "Invalid base bandwidth unit %" PRIu64 ", all " + "bandwidths must be specified in the same units.", base_bw); + return; + } + + hmat_lb->bandwidth[node->initiator][node->target] = bw_mb; + } + + if (hmat_lb) { + hmat_lb->hierarchy = node->hierarchy; + hmat_lb->data_type = node->data_type; + } +} + void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp) { Error *err = NULL; @@ -224,6 +371,12 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp) machine_set_cpu_numa_node(ms, qapi_NumaCpuOptions_base(&object->u.cpu), &err); break; + case NUMA_OPTIONS_TYPE_HMAT_LB: + parse_numa_hmat_lb(ms, &object->u.hmat_lb, &err); + if (err) { + goto end; + } + break; default: abort(); } @@ -251,6 +404,17 @@ static int parse_numa(void *opaque, QemuOpts *opts, Error **errp) qemu_strtosz_MiB(mem_str, NULL, &object->u.node.mem); } + if (object->type == NUMA_OPTIONS_TYPE_HMAT_LB) { + if (object->u.hmat_lb.has_latency) { + const char *lat_str = qemu_opt_get(opts, "latency"); + qemu_strtotime_ps(lat_str, NULL, &object->u.hmat_lb.latency); + } + if (object->u.hmat_lb.has_bandwidth) { + const char *bw_str = qemu_opt_get(opts, "bandwidth"); + qemu_strtosz_MiB(bw_str, NULL, &object->u.hmat_lb.bandwidth); + } + } + set_numa_options(ms, object, &err); end: diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index dc48d39439..c18e939395 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -75,6 +75,8 @@ typedef struct NumaState NumaState; void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp); void parse_numa_opts(MachineState *ms); +void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node, + Error **errp); void numa_complete_configuration(MachineState *ms); void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms); extern QemuOptsList qemu_numa_opts; diff --git a/qapi/machine.json b/qapi/machine.json index 3c2914cd1c..b6019335e8 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -426,10 +426,12 @@ # # @cpu: property based CPU(s) to node mapping (Since: 2.10) # +# @hmat-lb: memory latency and bandwidth information (Since: 4.2) +# # Since: 2.1 ## { 'enum': 'NumaOptionsType', - 'data': [ 'node', 'dist', 'cpu' ] } + 'data': [ 'node', 'dist', 'cpu', 'hmat-lb' ] } ## # @NumaOptions: @@ -444,7 +446,8 @@ 'data': { 'node': 'NumaNodeOptions', 'dist': 'NumaDistOptions', - 'cpu': 'NumaCpuOptions' }} + 'cpu': 'NumaCpuOptions', + 'hmat-lb': 'NumaHmatLBOptions' }} ## # @NumaNodeOptions: @@ -557,6 +560,94 @@ 'base': 'CpuInstanceProperties', 'data' : {} } +## +# @HmatLBMemoryHierarchy: +# +# The memory hierarchy in the System Locality Latency +# and Bandwidth Information Structure of HMAT (Heterogeneous +# Memory Attribute Table) +# +# For more information of @HmatLBMemoryHierarchy see +# the chapter 5.2.27.4: Table 5-142: Field "Flags" of ACPI 6.3 spec. +# +# @memory: the structure represents the memory performance +# +# @first-level: first level memory of memory side cached memory +# +# @second-level: second level memory of memory side cached memory +# +# @third-level: third level memory of memory side cached memory +# +# Since: 4.2 +## +{ 'enum': 'HmatLBMemoryHierarchy', + 'data': [ 'memory', 'first-level', 'second-level', 'third-level' ] } + +## +# @HmatLBDataType: +# +# Data type in the System Locality Latency +# and Bandwidth Information Structure of HMAT (Heterogeneous +# Memory Attribute Table) +# +# For more information of @HmatLBDataType see +# the chapter 5.2.27.4: Table 5-142: Field "Data Type" of ACPI 6.3 spec. +# +# @access-latency: access latency (nanoseconds) +# +# @read-latency: read latency (nanoseconds) +# +# @write-latency: write latency (nanoseconds) +# +# @access-bandwidth: access bandwidth (MB/s) +# +# @read-bandwidth: read bandwidth (MB/s) +# +# @write-bandwidth: write bandwidth (MB/s) +# +# Since: 4.2 +## +{ 'enum': 'HmatLBDataType', + 'data': [ 'access-latency', 'read-latency', 'write-latency', + 'access-bandwidth', 'read-bandwidth', 'write-bandwidth' ] } + +## +# @NumaHmatLBOptions: +# +# Set the system locality latency and bandwidth information +# between Initiator and Target proximity Domains. +# +# For more information of @NumaHmatLBOptions see +# the chapter 5.2.27.4: Table 5-142 of ACPI 6.3 spec. +# +# @initiator: the Initiator Proximity Domain. +# +# @target: the Target Proximity Domain. +# +# @hierarchy: the Memory Hierarchy. Indicates the performance +# of memory or side cache. +# +# @data-type: presents the type of data, access/read/write +# latency or hit latency. +# +# @latency: the value of latency from @initiator to @target proximity domain, +# the latency units are "ps(picosecond)", "ns(nanosecond)" or +# "us(microsecond)". +# +# @bandwidth: the value of bandwidth between @initiator and @target proximity +# domain, the bandwidth units are "MB(/s)","GB(/s)" or "TB(/s)". +# +# Since: 4.2 +## +{ 'struct': 'NumaHmatLBOptions', + 'data': { + 'initiator': 'uint16', + 'target': 'uint16', + 'hierarchy': 'HmatLBMemoryHierarchy', + 'data-type': 'HmatLBDataType', + '*latency': 'time', + '*bandwidth': 'size' }} + ## # @HostMemPolicy: # diff --git a/qemu-options.hx b/qemu-options.hx index 9f568c58d1..252495c288 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -168,16 +168,19 @@ DEF("numa", HAS_ARG, QEMU_OPTION_numa, "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" "-numa dist,src=source,dst=destination,val=distance\n" - "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n", + "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n" + "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,latency=lat][,bandwidth=bw]\n", QEMU_ARCH_ALL) STEXI @item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] @itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] @itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance} @itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}] +@itemx -numa hmat-lb,initiator=@var{node},target=@var{node},hierarchy=@var{str},data-type=@var{str}[,latency=@var{lat}][,bandwidth=@var{bw}] @findex -numa Define a NUMA node and assign RAM and VCPUs to it. Set the NUMA distance from a source node to a destination node. +Set the ACPI Heterogeneous Memory Attributes for the given nodes. Legacy VCPU assignment uses @samp{cpus} option where @var{firstcpu} and @var{lastcpu} are CPU indexes. Each @@ -256,6 +259,50 @@ specified resources, it just assigns existing resources to NUMA nodes. This means that one still has to use the @option{-m}, @option{-smp} options to allocate RAM and VCPUs respectively. +Use @samp{hmat-lb} to set System Locality Latency and Bandwidth Information +between initiator and target NUMA nodes in ACPI Heterogeneous Attribute Memory Table (HMAT). +Initiator NUMA node can create memory requests, usually including one or more processors. +Target NUMA node contains addressable memory. + +In @samp{hmat-lb} option, @var{node} are NUMA node IDs. @var{str} of 'hierarchy' +is the memory hierarchy of the target NUMA node: if @var{str} is 'memory', the structure +represents the memory performance; if @var{str} is 'first-level|second-level|third-level', +this structure represents aggregated performance of memory side caches for each domain. +@var{str} of 'data-type' is type of data represented by this structure instance: +if 'hierarchy' is 'memory', 'data-type' is 'access|read|write' latency(nanoseconds) +or 'access|read|write' bandwidth(MB/s) of the target memory; if 'hierarchy' is +'first-level|second-level|third-level', 'data-type' is 'access|read|write' hit latency +or 'access|read|write' hit bandwidth of the target memory side cache. + +@var{lat} of 'latency' is latency value, the possible value and units are +NUM[ps|ns|us] (picosecond|nanosecond|microsecond), the recommended unit is 'ns'. @var{bw} +is bandwidth value, the possible value and units are NUM[M|G|T], mean that +the bandwidth value are NUM MB/s, GB/s or TB/s. Note that max NUM is 65534, +if NUM is 0, means the corresponding latency or bandwidth information is not provided. +And if input numbers without any unit, the latency unit will be 'ps' and the bandwidth +will be MB/s. + +For example, the following option assigns NUMA node 0 and 1. Node 0 has 2 cpus and +a ram, node 1 has only a ram. The processors in node 0 access memory in node +0 with access-latency 5 nanoseconds, access-bandwidth is 200 MB/s; +The processors in NUMA node 0 access memory in NUMA node 1 with access-latency 10 +nanoseconds, access-bandwidth is 100 MB/s. +@example +-machine hmat=on \ +-m 2G \ +-object memory-backend-ram,size=1G,id=m0 \ +-object memory-backend-ram,size=1G,id=m1 \ +-smp 2 \ +-numa node,nodeid=0,memdev=m0 \ +-numa node,nodeid=1,memdev=m1,initiator=0 \ +-numa cpu,node-id=0,socket-id=0 \ +-numa cpu,node-id=0,socket-id=1 \ +-numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-latency,latency=5ns \ +-numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-bandwidth,bandwidth=200M \ +-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-latency,latency=10ns \ +-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,bandwidth=100M +@end example + ETEXI DEF("add-fd", HAS_ARG, QEMU_OPTION_add_fd, From patchwork Sun Sep 1 14:21:18 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125295 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 4D8A3112C for ; Sun, 1 Sep 2019 14:28:06 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 1D63C20644 for ; Sun, 1 Sep 2019 14:28:06 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 1D63C20644 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57782 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qpo-0002iZ-Uh for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:28:04 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39580) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qjk-0004mg-9o for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:49 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4Qjh-0004uE-Rz for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:47 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4Qjh-0004jJ-Ax for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:45 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:45 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453142" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:43 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:18 +0800 Message-Id: <20190901142119.20482-11-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 10/11] numa: Extend CLI to provide memory side cache information X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" From: Liu Jingqi Add -numa hmat-cache option to provide Memory Side Cache Information. These memory attributes help to build Memory Side Cache Information Structure(s) in ACPI Heterogeneous Memory Attribute Table (HMAT). Reviewed-by: Daniel Black Signed-off-by: Liu Jingqi Signed-off-by: Tao Xu --- No changes in v10. --- hw/core/numa.c | 67 +++++++++++++++++++++++++++++++++++ include/sysemu/numa.h | 2 ++ qapi/machine.json | 81 +++++++++++++++++++++++++++++++++++++++++-- qemu-options.hx | 16 +++++++-- 4 files changed, 162 insertions(+), 4 deletions(-) diff --git a/hw/core/numa.c b/hw/core/numa.c index 7387547793..6e4f6169cb 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -333,6 +333,67 @@ void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node, } } +void parse_numa_hmat_cache(MachineState *ms, NumaHmatCacheOptions *node, + Error **errp) +{ + int nb_numa_nodes = ms->numa_state->num_nodes; + HMAT_Cache_Info *hmat_cache = NULL; + + if (node->node_id >= nb_numa_nodes) { + error_setg(errp, "Invalid node-id=%" PRIu32 + ", it should be less than %d.", + node->node_id, nb_numa_nodes); + return; + } + + if (node->total > MAX_HMAT_CACHE_LEVEL) { + error_setg(errp, "Invalid total=%" PRIu8 + ", it should be less than or equal to %d.", + node->total, MAX_HMAT_CACHE_LEVEL); + return; + } + if (node->level > node->total) { + error_setg(errp, "Invalid level=%" PRIu8 + ", it should be less than or equal to" + " total=%" PRIu8 ".", + node->level, node->total); + return; + } + if (ms->numa_state->hmat_cache[node->node_id][node->level]) { + error_setg(errp, "Duplicate configuration of the side cache for " + "node-id=%" PRIu32 " and level=%" PRIu8 ".", + node->node_id, node->level); + return; + } + + if ((node->level > 1) && + ms->numa_state->hmat_cache[node->node_id][node->level - 1] && + (node->size >= + ms->numa_state->hmat_cache[node->node_id][node->level - 1]->size)) { + error_setg(errp, "Invalid size=0x%" PRIx64 + ", the size of level=%" PRIu8 + " should be less than the size(0x%" PRIx64 + ") of level=%" PRIu8 ".", + node->size, node->level, + ms->numa_state->hmat_cache[node->node_id] + [node->level - 1]->size, + node->level - 1); + return; + } + + hmat_cache = g_malloc0(sizeof(*hmat_cache)); + + hmat_cache->mem_proximity = node->node_id; + hmat_cache->size = node->size; + hmat_cache->total_levels = node->total; + hmat_cache->level = node->level; + hmat_cache->associativity = node->assoc; + hmat_cache->write_policy = node->policy; + hmat_cache->line_size = node->line; + + ms->numa_state->hmat_cache[node->node_id][node->level] = hmat_cache; +} + void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp) { Error *err = NULL; @@ -377,6 +438,12 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp) goto end; } break; + case NUMA_OPTIONS_TYPE_HMAT_CACHE: + parse_numa_hmat_cache(ms, &object->u.hmat_cache, &err); + if (err) { + goto end; + } + break; default: abort(); } diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index c18e939395..700d7c0392 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -77,6 +77,8 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp); void parse_numa_opts(MachineState *ms); void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node, Error **errp); +void parse_numa_hmat_cache(MachineState *ms, NumaHmatCacheOptions *node, + Error **errp); void numa_complete_configuration(MachineState *ms); void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms); extern QemuOptsList qemu_numa_opts; diff --git a/qapi/machine.json b/qapi/machine.json index b6019335e8..088be81920 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -428,10 +428,12 @@ # # @hmat-lb: memory latency and bandwidth information (Since: 4.2) # +# @hmat-cache: memory side cache information (Since: 4.2) +# # Since: 2.1 ## { 'enum': 'NumaOptionsType', - 'data': [ 'node', 'dist', 'cpu', 'hmat-lb' ] } + 'data': [ 'node', 'dist', 'cpu', 'hmat-lb', 'hmat-cache' ] } ## # @NumaOptions: @@ -447,7 +449,8 @@ 'node': 'NumaNodeOptions', 'dist': 'NumaDistOptions', 'cpu': 'NumaCpuOptions', - 'hmat-lb': 'NumaHmatLBOptions' }} + 'hmat-lb': 'NumaHmatLBOptions', + 'hmat-cache': 'NumaHmatCacheOptions' }} ## # @NumaNodeOptions: @@ -648,6 +651,80 @@ '*latency': 'time', '*bandwidth': 'size' }} +## +# @HmatCacheAssociativity: +# +# Cache associativity in the Memory Side Cache +# Information Structure of HMAT +# +# For more information of @HmatCacheAssociativity see +# the chapter 5.2.27.5: Table 5-143 of ACPI 6.3 spec. +# +# @none: None +# +# @direct: Direct Mapped +# +# @complex: Complex Cache Indexing (implementation specific) +# +# Since: 4.2 +## +{ 'enum': 'HmatCacheAssociativity', + 'data': [ 'none', 'direct', 'complex' ] } + +## +# @HmatCacheWritePolicy: +# +# Cache write policy in the Memory Side Cache +# Information Structure of HMAT +# +# For more information of @HmatCacheWritePolicy see +# the chapter 5.2.27.5: Table 5-143: Field "Cache Attributes" of ACPI 6.3 spec. +# +# @none: None +# +# @write-back: Write Back (WB) +# +# @write-through: Write Through (WT) +# +# Since: 4.2 +## +{ 'enum': 'HmatCacheWritePolicy', + 'data': [ 'none', 'write-back', 'write-through' ] } + +## +# @NumaHmatCacheOptions: +# +# Set the memory side cache information for a given memory domain. +# +# For more information of @NumaHmatCacheOptions see +# the chapter 5.2.27.5: Table 5-143: Field "Cache Attributes" of ACPI 6.3 spec. +# +# @node-id: the memory proximity domain to which the memory belongs. +# +# @size: the size of memory side cache in bytes. +# +# @total: the total cache levels for this memory proximity domain. +# +# @level: the cache level described in this structure. +# +# @assoc: the cache associativity, none/direct-mapped/complex(complex cache indexing). +# +# @policy: the write policy, none/write-back/write-through. +# +# @line: the cache Line size in bytes. +# +# Since: 4.2 +## +{ 'struct': 'NumaHmatCacheOptions', + 'data': { + 'node-id': 'uint32', + 'size': 'size', + 'total': 'uint8', + 'level': 'uint8', + 'assoc': 'HmatCacheAssociativity', + 'policy': 'HmatCacheWritePolicy', + 'line': 'uint16' }} + ## # @HostMemPolicy: # diff --git a/qemu-options.hx b/qemu-options.hx index 252495c288..f30cf27559 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -169,7 +169,8 @@ DEF("numa", HAS_ARG, QEMU_OPTION_numa, "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" "-numa dist,src=source,dst=destination,val=distance\n" "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n" - "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,latency=lat][,bandwidth=bw]\n", + "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,latency=lat][,bandwidth=bw]\n" + "-numa hmat-cache,node-id=node,size=size,total=total,level=level[,assoc=none|direct|complex][,policy=none|write-back|write-through][,line=size]\n", QEMU_ARCH_ALL) STEXI @item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] @@ -177,6 +178,7 @@ STEXI @itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance} @itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}] @itemx -numa hmat-lb,initiator=@var{node},target=@var{node},hierarchy=@var{str},data-type=@var{str}[,latency=@var{lat}][,bandwidth=@var{bw}] +@itemx -numa hmat-cache,node-id=@var{node},size=@var{size},total=@var{total},level=@var{level}[,assoc=@var{str}][,policy=@var{str}][,line=@var{size}] @findex -numa Define a NUMA node and assign RAM and VCPUs to it. Set the NUMA distance from a source node to a destination node. @@ -282,11 +284,19 @@ if NUM is 0, means the corresponding latency or bandwidth information is not pro And if input numbers without any unit, the latency unit will be 'ps' and the bandwidth will be MB/s. +In @samp{hmat-cache} option, @var{node-id} is the NUMA-id of the memory belongs. +@var{size} is the size of memory side cache in bytes. @var{total} is the total cache levels. +@var{level} is the cache level described in this structure. @var{assoc} is the cache associativity, +the possible value is 'none/direct(direct-mapped)/complex(complex cache indexing)'. +@var{policy} is the write policy. @var{line} is the cache Line size in bytes. + For example, the following option assigns NUMA node 0 and 1. Node 0 has 2 cpus and a ram, node 1 has only a ram. The processors in node 0 access memory in node 0 with access-latency 5 nanoseconds, access-bandwidth is 200 MB/s; The processors in NUMA node 0 access memory in NUMA node 1 with access-latency 10 nanoseconds, access-bandwidth is 100 MB/s. +And for memory side cache information, NUMA node 0 and 1 both have 1 level memory +cache, size is 0x20000 bytes, policy is write-back, the cache Line size is 8 bytes: @example -machine hmat=on \ -m 2G \ @@ -300,7 +310,9 @@ nanoseconds, access-bandwidth is 100 MB/s. -numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-latency,latency=5ns \ -numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-bandwidth,bandwidth=200M \ -numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-latency,latency=10ns \ --numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,bandwidth=100M +-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,bandwidth=100M \ +-numa hmat-cache,node-id=0,size=0x20000,total=1,level=1,assoc=direct,policy=write-back,line=8 \ +-numa hmat-cache,node-id=1,size=0x20000,total=1,level=1,assoc=direct,policy=write-back,line=8 @end example ETEXI From patchwork Sun Sep 1 14:21:19 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tao Xu X-Patchwork-Id: 11125297 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id C275616B1 for ; Sun, 1 Sep 2019 14:30:29 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 9546B2342C for ; Sun, 1 Sep 2019 14:30:29 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 9546B2342C Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Received: from localhost ([::1]:57808 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qs7-0005CU-Ky for patchwork-qemu-devel@patchwork.kernel.org; Sun, 01 Sep 2019 10:30:27 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39593) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i4Qjn-0004o4-El for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:52 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i4Qjl-0004y0-Dl for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:51 -0400 Received: from mga12.intel.com ([192.55.52.136]:16719) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i4Qjj-0004jJ-Au for qemu-devel@nongnu.org; Sun, 01 Sep 2019 10:21:47 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Sep 2019 07:21:47 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,455,1559545200"; d="scan'208";a="211453146" Received: from tao-optiplex-7060.sh.intel.com ([10.239.159.36]) by fmsmga002.fm.intel.com with ESMTP; 01 Sep 2019 07:21:45 -0700 From: Tao Xu To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com Date: Sun, 1 Sep 2019 22:21:19 +0800 Message-Id: <20190901142119.20482-12-tao3.xu@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190901142119.20482-1-tao3.xu@intel.com> References: <20190901142119.20482-1-tao3.xu@intel.com> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH v10 11/11] tests/bios-tables-test: add test cases for ACPI HMAT X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Jingqi Liu , tao3.xu@intel.com, fan.du@intel.com, qemu-devel@nongnu.org, daniel@linux.ibm.com, jonathan.cameron@huawei.com, dan.j.williams@intel.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" ACPI table HMAT has been introduced, QEMU now builds HMAT tables for Heterogeneous Memory with boot option '-numa node'. Add test cases on PC and Q35 machines with 2 numa nodes. Because HMAT is generated when system enable numa, the following tables need to be added for this test: tests/acpi-test-data/pc/*.acpihmat tests/acpi-test-data/pc/HMAT.* tests/acpi-test-data/q35/*.acpihmat tests/acpi-test-data/q35/HMAT.* Reviewed-by: Daniel Black Reviewed-by: Jingqi Liu Suggested-by: Igor Mammedov Signed-off-by: Tao Xu --- Changes in v10: - Update test case, add "-machine hmat=on" --- tests/bios-tables-test.c | 44 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/tests/bios-tables-test.c b/tests/bios-tables-test.c index a356ac3489..633efd959b 100644 --- a/tests/bios-tables-test.c +++ b/tests/bios-tables-test.c @@ -871,6 +871,48 @@ static void test_acpi_piix4_tcg_dimm_pxm(void) test_acpi_tcg_dimm_pxm(MACHINE_PC); } +static void test_acpi_tcg_acpi_hmat(const char *machine) +{ + test_data data; + + memset(&data, 0, sizeof(data)); + data.machine = machine; + data.variant = ".acpihmat"; + test_acpi_one(" -machine hmat=on" + " -smp 2,sockets=2" + " -m 128M,slots=2,maxmem=1G" + " -object memory-backend-ram,size=64M,id=m0" + " -object memory-backend-ram,size=64M,id=m1" + " -numa node,nodeid=0,memdev=m0" + " -numa node,nodeid=1,memdev=m1,initiator=0" + " -numa cpu,node-id=0,socket-id=0" + " -numa cpu,node-id=0,socket-id=1" + " -numa hmat-lb,initiator=0,target=0,hierarchy=memory," + "data-type=access-latency,latency=5ns" + " -numa hmat-lb,initiator=0,target=0,hierarchy=memory," + "data-type=access-bandwidth,bandwidth=500M" + " -numa hmat-lb,initiator=0,target=1,hierarchy=memory," + "data-type=access-latency,latency=10ns" + " -numa hmat-lb,initiator=0,target=1,hierarchy=memory," + "data-type=access-bandwidth,bandwidth=100M" + " -numa hmat-cache,node-id=0,size=0x20000,total=1,level=1" + ",assoc=direct,policy=write-back,line=8" + " -numa hmat-cache,node-id=1,size=0x20000,total=1,level=1" + ",assoc=direct,policy=write-back,line=8", + &data); + free_test_data(&data); +} + +static void test_acpi_q35_tcg_acpi_hmat(void) +{ + test_acpi_tcg_acpi_hmat(MACHINE_Q35); +} + +static void test_acpi_piix4_tcg_acpi_hmat(void) +{ + test_acpi_tcg_acpi_hmat(MACHINE_PC); +} + static void test_acpi_virt_tcg(void) { test_data data = { @@ -915,6 +957,8 @@ int main(int argc, char *argv[]) qtest_add_func("acpi/q35/numamem", test_acpi_q35_tcg_numamem); qtest_add_func("acpi/piix4/dimmpxm", test_acpi_piix4_tcg_dimm_pxm); qtest_add_func("acpi/q35/dimmpxm", test_acpi_q35_tcg_dimm_pxm); + qtest_add_func("acpi/piix4/acpihmat", test_acpi_piix4_tcg_acpi_hmat); + qtest_add_func("acpi/q35/acpihmat", test_acpi_q35_tcg_acpi_hmat); } else if (strcmp(arch, "aarch64") == 0) { qtest_add_func("acpi/virt", test_acpi_virt_tcg); }