From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8AF51C47089 for ; Mon, 5 Dec 2022 15:00:30 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 0FFB58E0002; Mon, 5 Dec 2022 10:00:30 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 089618E0001; Mon, 5 Dec 2022 10:00:30 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id E441A8E0002; Mon, 5 Dec 2022 10:00:29 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0017.hostedemail.com [216.40.44.17]) by kanga.kvack.org (Postfix) with ESMTP id CF6808E0001 for ; Mon, 5 Dec 2022 10:00:29 -0500 (EST) Received: from smtpin11.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay09.hostedemail.com (Postfix) with ESMTP id 9521280B24 for ; Mon, 5 Dec 2022 15:00:29 +0000 (UTC) X-FDA: 80208563778.11.A569A9A Received: from mx0a-00082601.pphosted.com (mx0b-00082601.pphosted.com [67.231.153.30]) by imf16.hostedemail.com (Postfix) with ESMTP id 59D77180021 for ; Mon, 5 Dec 2022 15:00:28 +0000 (UTC) Authentication-Results: imf16.hostedemail.com; dkim=pass header.d=meta.com header.s=s2048-2021-q4 header.b=ZDve+bap; spf=pass (imf16.hostedemail.com: domain of "prvs=3338591533=kbusch@meta.com" designates 67.231.153.30 as permitted sender) smtp.mailfrom="prvs=3338591533=kbusch@meta.com"; dmarc=pass (policy=reject) header.from=meta.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1670252428; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=jW6N9lNs9aHxnq0Gv9Edz1amHHS3PbY2z2d5+0qT2t4=; b=GCxto7DV1oSkw3JbAd/IyH/d5iJPETcs0LQCKhPlD+BdEEE/iUWMd13eFJAfiGnvoRDGx6 nYaun5AMZpL+V04GHkc3gEpkL4GgzsQvnfr2ZhQZncz1BF/7EZZJVRxPtFqn/Akaru2PdM rhjREV+ioUMh121J7vuVrZ3SgkofT0E= ARC-Authentication-Results: i=1; imf16.hostedemail.com; dkim=pass header.d=meta.com header.s=s2048-2021-q4 header.b=ZDve+bap; spf=pass (imf16.hostedemail.com: domain of "prvs=3338591533=kbusch@meta.com" designates 67.231.153.30 as permitted sender) smtp.mailfrom="prvs=3338591533=kbusch@meta.com"; dmarc=pass (policy=reject) header.from=meta.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1670252428; a=rsa-sha256; cv=none; b=PX75nENcktlcOudlqYJyhd/hWb5dk50ZMMNYQtaWiCjf3DG91CxY+4cGihW5cGKN5qJmZN VlT9xOmTamYNd/mR5DqEgVQztOa3iH5v/CWjXW7Bo1wuN5Ck0VUx2TqbagCbcSM9yPb7KR ZzYgO/Bnh6BX3OOsLYNk8gpdulIp2pA= Received: from pps.filterd (m0001303.ppops.net [127.0.0.1]) by m0001303.ppops.net (8.17.1.19/8.17.1.19) with ESMTP id 2B5C0SIW000740 for ; Mon, 5 Dec 2022 07:00:24 -0800 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=meta.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=s2048-2021-q4; bh=jW6N9lNs9aHxnq0Gv9Edz1amHHS3PbY2z2d5+0qT2t4=; b=ZDve+bapQAu7yDP8M4eZ++3X7Atj7Oi/MPdhOX8GOyN0o96Th+aa0aFtIrmp5gNK3eZS HzF3xxhFebuIGv3tqNRl5XfJNX9K6+4lD6lgY1dexHfkteTL8RPOFw97DAomCtSxxIsr 8acc7jar+0AVMiwkV8Vx32lnj+RfkqLMkgaenN7XvgNfN1U+/1N4HHpWpGQ3o1urOyRK 3Ti0b6tZ4n5xjP0Q2j7bZESHDlrEai4sXBg3oCxGH4HeWr2AeTRCouymw4bcvB/XmFO4 MvgXj2mCpC2mM6M7tvXpT6At2VZAC++PdbSJSZkV5CO26DjSDOIEXr/LZODVH26ZmerN qQ== Received: from mail.thefacebook.com ([163.114.132.120]) by m0001303.ppops.net (PPS) with ESMTPS id 3m9g8c1kks-2 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Mon, 05 Dec 2022 07:00:24 -0800 Received: from twshared10308.07.ash9.facebook.com (2620:10d:c085:108::8) by mail.thefacebook.com (2620:10d:c085:21d::6) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.31; Mon, 5 Dec 2022 07:00:22 -0800 Received: by devbig007.nao1.facebook.com (Postfix, from userid 544533) id A52D2C6156DD; Mon, 5 Dec 2022 07:00:09 -0800 (PST) From: Keith Busch To: , , Matthew Wilcox CC: Tony Battersby , Keith Busch Subject: [PATCH 01/11] dmapool: add alloc/free performance test Date: Mon, 5 Dec 2022 06:59:27 -0800 Message-ID: <20221205145937.54367-2-kbusch@meta.com> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20221205145937.54367-1-kbusch@meta.com> References: <20221205145937.54367-1-kbusch@meta.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-FB-Internal: Safe Content-Type: text/plain X-Proofpoint-GUID: F4ymp6hp2anZBkNQOxqVdSjuzL0k04Nh X-Proofpoint-ORIG-GUID: F4ymp6hp2anZBkNQOxqVdSjuzL0k04Nh X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.923,Hydra:6.0.545,FMLib:17.11.122.1 definitions=2022-12-05_01,2022-12-05_01,2022-06-22_01 X-Stat-Signature: hciw4irpftkhy91nmignggjtsqr3i7j5 X-Rspam-User: X-Spamd-Result: default: False [-3.40 / 9.00]; BAYES_HAM(-6.00)[100.00%]; R_MISSING_CHARSET(2.50)[]; MID_CONTAINS_FROM(1.00)[]; DMARC_POLICY_ALLOW(-0.50)[meta.com,reject]; R_DKIM_ALLOW(-0.20)[meta.com:s=s2048-2021-q4]; R_SPF_ALLOW(-0.20)[+ip4:67.231.153.30]; MIME_GOOD(-0.10)[text/plain]; RCVD_NO_TLS_LAST(0.10)[]; MIME_TRACE(0.00)[0:+]; DKIM_TRACE(0.00)[meta.com:+]; TO_MATCH_ENVRCPT_SOME(0.00)[]; FORGED_SENDER_VERP_SRS(0.00)[]; FROM_NEQ_ENVFROM(0.00)[kbusch@meta.com,prvs=3338591533=kbusch@meta.com]; FROM_HAS_DN(0.00)[]; RCVD_COUNT_FIVE(0.00)[5]; RCPT_COUNT_FIVE(0.00)[5]; TO_DN_SOME(0.00)[]; ARC_SIGNED(0.00)[hostedemail.com:s=arc-20220608:i=1]; PREVIOUSLY_DELIVERED(0.00)[linux-mm@kvack.org]; ARC_NA(0.00)[] X-Rspamd-Queue-Id: 59D77180021 X-Rspamd-Server: rspam06 X-HE-Tag: 1670252428-884861 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: Keith Busch Provide a module that allocates and frees many blocks of various sizes and report how long it takes. This is intended to provide a consistent way to measure how changes to the dma_pool_alloc/free routines affect timing. Signed-off-by: Keith Busch --- mm/Kconfig | 9 +++ mm/Makefile | 1 + mm/dmapool_test.c | 138 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 148 insertions(+) create mode 100644 mm/dmapool_test.c diff --git a/mm/Kconfig b/mm/Kconfig index 57e1d8c5b5052..12a78d64eeb72 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1044,6 +1044,15 @@ config GUP_TEST comment "GUP_TEST needs to have DEBUG_FS enabled" depends on !GUP_TEST && !DEBUG_FS =20 +config DMAPOOL_TEST + tristate "Enable a module to run time tests on dma_pool" + depends on HAS_DMA + help + Provides a module that will allocate and free many blocks of various + sizes and report how long it takes. This is intended to provide a + consistent way to measure how changes to the dma_pool_alloc/free + routines affect performance. + config GUP_GET_PTE_LOW_HIGH bool =20 diff --git a/mm/Makefile b/mm/Makefile index 8e105e5b3e293..3a08f5d7b1782 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_MEMCG) +=3D swap_cgroup.o endif obj-$(CONFIG_CGROUP_HUGETLB) +=3D hugetlb_cgroup.o obj-$(CONFIG_GUP_TEST) +=3D gup_test.o +obj-$(CONFIG_DMAPOOL_TEST) +=3D dmapool_test.o obj-$(CONFIG_MEMORY_FAILURE) +=3D memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) +=3D hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) +=3D kmemleak.o diff --git a/mm/dmapool_test.c b/mm/dmapool_test.c new file mode 100644 index 0000000000000..2873d91f509b4 --- /dev/null +++ b/mm/dmapool_test.c @@ -0,0 +1,138 @@ +#include +#include +#include +#include +#include +#include + +#define NR_TESTS (100) + +struct dma_pool_pair { + dma_addr_t dma; + void *v; +}; + +static const int block_sizes[] =3D { + 16, + 64, + 256, + 1024, + 4096 +}; + +static struct dma_pool *pool; +struct device test_dev; +u64 dma_mask; + +static inline int nr_blocks(int size) +{ + return clamp_t(int, (PAGE_SIZE / size) * 512, 1024, 8192); +} + +static int dmapool_test_alloc(struct dma_pool_pair *p, int blocks) +{ + int i; + + for (i =3D 0; i < blocks; i++) { + p[i].v =3D dma_pool_alloc(pool, GFP_KERNEL, + &p[i].dma); + if (!p[i].v) + goto pool_fail; + } + + for (i =3D 0; i < blocks; i++) + dma_pool_free(pool, p[i].v, p[i].dma); + + return 0; + +pool_fail: + for (--i; i >=3D 0; i--) + dma_pool_free(pool, p[i].v, p[i].dma); + return -ENOMEM; +} + +static int dmapool_test_block(int block_size) +{ + int blocks =3D nr_blocks(block_size); + ktime_t start_time, end_time; + struct dma_pool_pair *p; + int i, ret; + + p =3D kcalloc(blocks, sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + pool =3D dma_pool_create("test pool", &test_dev, block_size, + block_size, 0); + if (!pool) { + ret =3D -ENOMEM; + goto free_pairs; + } + + start_time =3D ktime_get(); + for (i =3D 0; i < NR_TESTS; i++) { + ret =3D dmapool_test_alloc(p, blocks); + if (ret) + goto free_pool; + if (need_resched()) + cond_resched(); + } + end_time =3D ktime_get(); + + printk("dmapool test: size:%-4d blocks:%-6d time:%llu\n", block_size, + blocks, ktime_us_delta(end_time, start_time)); + +free_pool: + dma_pool_destroy(pool); +free_pairs: + kfree(p); + return ret; +} + +static void dmapool_test_release(struct device *dev) +{ +} + +static int dmapool_checks(void) +{ + int i, ret; + + ret =3D dev_set_name(&test_dev, "dmapool-test"); + if (ret) + return ret; + + ret =3D device_register(&test_dev); + if (ret) { + printk("%s: register failed:%d\n", __func__, ret); + goto put_device; + } + + test_dev.release =3D dmapool_test_release; + test_dev.dma_ops =3D NULL; + test_dev.dma_mask =3D &dma_mask; + ret =3D dma_set_mask_and_coherent(&test_dev, DMA_BIT_MASK(64)); + if (ret) { + printk("%s: mask failed:%d\n", __func__, ret); + goto del_device; + } + + for (i =3D 0; i < ARRAY_SIZE(block_sizes); i++) { + ret =3D dmapool_test_block(block_sizes[i]); + if (ret) + break; + } + +del_device: + device_del(&test_dev); +put_device: + put_device(&test_dev); + return ret; +} + +static void dmapool_exit(void) +{ +} + +module_init(dmapool_checks); +module_exit(dmapool_exit); +MODULE_LICENSE("GPL"); --=20 2.30.2