From patchwork Thu Aug 25 09:23:24 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: "Aneesh Kumar K.V" X-Patchwork-Id: 12954420 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 937F1C3F6B0 for ; Thu, 25 Aug 2022 09:24:09 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 12BFD6B0074; Thu, 25 Aug 2022 05:24:09 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 103DA6B0075; Thu, 25 Aug 2022 05:24:09 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id EE8276B0078; Thu, 25 Aug 2022 05:24:08 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0015.hostedemail.com [216.40.44.15]) by kanga.kvack.org (Postfix) with ESMTP id DE4416B0074 for ; Thu, 25 Aug 2022 05:24:08 -0400 (EDT) Received: from smtpin27.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay10.hostedemail.com (Postfix) with ESMTP id A53D8C1B57 for ; Thu, 25 Aug 2022 09:24:08 +0000 (UTC) X-FDA: 79837578576.27.8A2FC33 Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) by imf19.hostedemail.com (Postfix) with ESMTP id 336371A0003 for ; Thu, 25 Aug 2022 09:24:07 +0000 (UTC) Received: from pps.filterd (m0098410.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.17.1.5/8.17.1.5) with ESMTP id 27P8kfb9028852; Thu, 25 Aug 2022 09:23:49 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ibm.com; h=from : to : cc : subject : date : message-id : mime-version : content-type : content-transfer-encoding; s=pp1; bh=/3HZdqo3/9MmZqqTy+mTYaXdrdbmOPa2CDTlqVxHdNY=; b=SWX1CcZMi4KUm7VlwL+0PEVV21P1HaGVDI5UkTi96MpMHd0dZHel2f3BXTGpd6SZJ6yY uBEsl40AIf4tThTb2Nk7LmEwyAukSmdSWYJsCXFmKMHV8KK8Vubd4K5fX2xePQnef8Pk gIjN3BXPaBD7ozss+E4IP000oAfCdr6zHlvpv2I2+EcwrhRDSk40RreRg5ozy3yhBp/F jhOXizCTAjedX20w1YFD8z5Rr9ZYFUwbrvKjR6k6fN0BMqJShcxVBzVrvdttpLbC0Ouw hi2DChjsnqsVDaXneuBq+3UGxxbrR1w/n7Zgqy1g/cICaF3oAOzWVWQQ2F6U+Fsu2Tyo 7A== Received: from pps.reinject (localhost [127.0.0.1]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 3j65vb9yhf-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 25 Aug 2022 09:23:48 +0000 Received: from m0098410.ppops.net (m0098410.ppops.net [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 27P8ms3I005261; Thu, 25 Aug 2022 09:23:48 GMT Received: from ppma01wdc.us.ibm.com (fd.55.37a9.ip4.static.sl-reverse.com [169.55.85.253]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 3j65vb9yfh-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 25 Aug 2022 09:23:48 +0000 Received: from pps.filterd (ppma01wdc.us.ibm.com [127.0.0.1]) by ppma01wdc.us.ibm.com (8.16.1.2/8.16.1.2) with SMTP id 27P9KpAI010630; Thu, 25 Aug 2022 09:23:46 GMT Received: from b03cxnp07029.gho.boulder.ibm.com (b03cxnp07029.gho.boulder.ibm.com [9.17.130.16]) by ppma01wdc.us.ibm.com with ESMTP id 3j2q896pt5-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 25 Aug 2022 09:23:46 +0000 Received: from b03ledav002.gho.boulder.ibm.com (b03ledav002.gho.boulder.ibm.com [9.17.130.233]) by b03cxnp07029.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 27P9Nj5b10289756 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 25 Aug 2022 09:23:45 GMT Received: from b03ledav002.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 447DC136053; Thu, 25 Aug 2022 09:23:45 +0000 (GMT) Received: from b03ledav002.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 344EE136051; Thu, 25 Aug 2022 09:23:39 +0000 (GMT) Received: from skywalker.ibmuc.com (unknown [9.43.112.25]) by b03ledav002.gho.boulder.ibm.com (Postfix) with ESMTP; Thu, 25 Aug 2022 09:23:38 +0000 (GMT) From: "Aneesh Kumar K.V" To: linux-mm@kvack.org, akpm@linux-foundation.org Cc: Wei Xu , Huang Ying , Yang Shi , Davidlohr Bueso , Tim C Chen , Michal Hocko , Linux Kernel Mailing List , Hesham Almatary , Dave Hansen , Jonathan Cameron , Alistair Popple , Dan Williams , Johannes Weiner , jvgediya.oss@gmail.com, Bharata B Rao , "Aneesh Kumar K.V" Subject: [RFC PATCH 1/2] mm/demotion: Expose memory type details via sysfs Date: Thu, 25 Aug 2022 14:53:24 +0530 Message-Id: <20220825092325.381517-1-aneesh.kumar@linux.ibm.com> X-Mailer: git-send-email 2.37.2 MIME-Version: 1.0 X-TM-AS-GCONF: 00 X-Proofpoint-GUID: bOSZGVN6wNReS-4JkG-MDBMc_ymk-p91 X-Proofpoint-ORIG-GUID: E41C2q33Hup9psnMxsI9t5Rna_7gjusW X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.895,Hydra:6.0.517,FMLib:17.11.122.1 definitions=2022-08-25_03,2022-08-22_02,2022-06-22_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 priorityscore=1501 phishscore=0 adultscore=0 impostorscore=0 mlxlogscore=999 lowpriorityscore=0 mlxscore=0 clxscore=1015 bulkscore=0 malwarescore=0 suspectscore=0 spamscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2207270000 definitions=main-2208250034 ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1661419448; a=rsa-sha256; cv=none; b=kYWRyjb8ID7pQNYC0xRg+Cneq6W3lwY58ba6hLc60PGnD2wUvTSYdVaHi5mGH2xgoNAYEz l1cqEGTKWoTl2teqPbwtr+3JjxG1DzJIH2ASAigw0m8DYejvMX1hMJ4kZc8uG5KWrRK+2e DrHZglFe4BhvA9kWsom8oMkmgs1y3IE= ARC-Authentication-Results: i=1; imf19.hostedemail.com; dkim=pass header.d=ibm.com header.s=pp1 header.b=SWX1CcZM; dmarc=pass (policy=none) header.from=ibm.com; spf=pass (imf19.hostedemail.com: domain of aneesh.kumar@linux.ibm.com designates 148.163.156.1 as permitted sender) smtp.mailfrom=aneesh.kumar@linux.ibm.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1661419448; 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: references:dkim-signature; bh=/3HZdqo3/9MmZqqTy+mTYaXdrdbmOPa2CDTlqVxHdNY=; b=4zbOcH9F54K3HrBKG7A0CSiSiKZheP9EC3U+4Tf0FNaNaX2+hdvkXE+EMP+2YROuOLj1T+ TILDwXUdJHG7KQ1qaDaGUMqnJMusiXpBdMhtQDD11XEaPcSNWtoIHw2t3p/p6nlWsV6TgJ nzXSJzsTlHDOQUDdw+plRwxBiNiap74= X-Stat-Signature: zjwnb51seyfgh94r9g7f8prkotbmx3xb X-Rspamd-Queue-Id: 336371A0003 X-Rspam-User: X-Rspamd-Server: rspam11 Authentication-Results: imf19.hostedemail.com; dkim=pass header.d=ibm.com header.s=pp1 header.b=SWX1CcZM; dmarc=pass (policy=none) header.from=ibm.com; spf=pass (imf19.hostedemail.com: domain of aneesh.kumar@linux.ibm.com designates 148.163.156.1 as permitted sender) smtp.mailfrom=aneesh.kumar@linux.ibm.com X-HE-Tag: 1661419447-284352 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: This patch adds /sys/devices/virtual/memtier/ where all memory tier related details can be found. All allocated memory types will be listed there as /sys/devices/virtual/memtier/memtypeN/ The nodes which are part of a specific memory type can be listed via /sys/devices/system/memtier/memtypeN/nodes. The adistance value of a specific memory type can be listed via /sys/devices/system/memtier/memtypeN/adistance. A directory listing looks like: :/sys/devices/virtual/memtier# tree memtype1 memtype1 ├── adistance ├── nodes ├── subsystem -> ../../../../bus/memtier └── uevent Since we will be using struct device to expose details via sysfs, drop struct kref and use struct device for refcounting the memtype. Signed-off-by: Aneesh Kumar K.V --- include/linux/memory-tiers.h | 3 +- mm/memory-tiers.c | 97 +++++++++++++++++++++++++++++++++--- 2 files changed, 91 insertions(+), 9 deletions(-) diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index ecd865922707..487209a572b2 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -6,6 +6,7 @@ #include #include #include +#include /* * Each tier cover a abstrace distance chunk size of 128 */ @@ -28,7 +29,7 @@ struct memory_dev_type { int adistance; /* Nodes of same abstract distance */ nodemask_t nodes; - struct kref kref; + struct device dev; }; #ifdef CONFIG_NUMA diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index ba844fe9cc8c..9eef3bd8d134 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include "internal.h" @@ -31,6 +32,15 @@ static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); static struct memory_dev_type *node_memory_types[MAX_NUMNODES]; static struct memory_dev_type *default_dram_type; + +#define MAX_MEMORY_TYPE_ID 20 +static DEFINE_IDR(memory_type_idr); +#define to_memory_type(device) container_of(device, struct memory_dev_type, dev) +static struct bus_type memory_tier_subsys = { + .name = "memtier", + .dev_name = "memtier", +}; + #ifdef CONFIG_MIGRATION static int top_tier_adistance; /* @@ -388,7 +398,7 @@ static inline void __init_node_memory_type(int node, struct memory_dev_type *mem { if (!node_memory_types[node]) { node_memory_types[node] = memtype; - kref_get(&memtype->kref); + get_device(&memtype->dev); } } @@ -460,33 +470,87 @@ static bool clear_node_memory_tier(int node) return cleared; } -static void release_memtype(struct kref *kref) +static ssize_t nodes_show(struct device *dev, + struct device_attribute *attr, char *buf) { - struct memory_dev_type *memtype; + int ret; + struct memory_dev_type *memtype = to_memory_type(dev); - memtype = container_of(kref, struct memory_dev_type, kref); + mutex_lock(&memory_tier_lock); + ret = sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&memtype->nodes)); + mutex_unlock(&memory_tier_lock); + return ret; +} +static DEVICE_ATTR_RO(nodes); + +static ssize_t adistance_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + struct memory_dev_type *memtype = to_memory_type(dev); + + mutex_lock(&memory_tier_lock); + ret = sysfs_emit(buf, "%d\n", memtype->adistance); + mutex_unlock(&memory_tier_lock); + return ret; +} +static DEVICE_ATTR_RO(adistance); + +static struct attribute *memtype_dev_attrs[] = { + &dev_attr_nodes.attr, + &dev_attr_adistance.attr, + NULL +}; + +static const struct attribute_group memtype_dev_group = { + .attrs = memtype_dev_attrs, +}; + +static const struct attribute_group *memtype_dev_groups[] = { + &memtype_dev_group, + NULL +}; + +static void memtype_device_release(struct device *dev) +{ + struct memory_dev_type *memtype = to_memory_type(dev); + + idr_remove(&memory_type_idr, memtype->dev.id); kfree(memtype); } struct memory_dev_type *alloc_memory_type(int adistance) { + int ret; struct memory_dev_type *memtype; - memtype = kmalloc(sizeof(*memtype), GFP_KERNEL); + memtype = kzalloc(sizeof(*memtype), GFP_KERNEL); if (!memtype) return ERR_PTR(-ENOMEM); memtype->adistance = adistance; INIT_LIST_HEAD(&memtype->tier_sibiling); memtype->nodes = NODE_MASK_NONE; - kref_init(&memtype->kref); + memtype->dev.id = idr_alloc(&memory_type_idr, NULL, + 1, MAX_MEMORY_TYPE_ID + 1, GFP_KERNEL); + memtype->dev.bus = &memory_tier_subsys; + memtype->dev.release = memtype_device_release; + memtype->dev.groups = memtype_dev_groups; + dev_set_name(&memtype->dev, "%s%d", "memtype", memtype->dev.id); + + ret = device_register(&memtype->dev); + if (ret) { + put_device(&memtype->dev); + return ERR_PTR(ret); + } + return memtype; } EXPORT_SYMBOL_GPL(alloc_memory_type); void destroy_memory_type(struct memory_dev_type *memtype) { - kref_put(&memtype->kref, release_memtype); + device_unregister(&memtype->dev); } EXPORT_SYMBOL_GPL(destroy_memory_type); @@ -504,7 +568,7 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype) mutex_lock(&memory_tier_lock); if (node_memory_types[node] == memtype) { node_memory_types[node] = NULL; - kref_put(&memtype->kref, release_memtype); + put_device(&memtype->dev); } mutex_unlock(&memory_tier_lock); } @@ -582,6 +646,23 @@ static int __init memory_tier_init(void) } subsys_initcall(memory_tier_init); +/* + * initialize sysfs subsys in core_initcall so that + * other kernel components can do alloc_memory_type + * before memory_tier_init + */ +static int __init memory_tier_sysfs_init(void) +{ + int err; + + err = subsys_virtual_register(&memory_tier_subsys, NULL); + if (err) + return err; + + return 0; +} +core_initcall(memory_tier_sysfs_init); + bool numa_demotion_enabled = false; #ifdef CONFIG_MIGRATION From patchwork Thu Aug 25 09:23:25 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: "Aneesh Kumar K.V" X-Patchwork-Id: 12954421 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 27B95C04AA5 for ; Thu, 25 Aug 2022 09:24:15 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id B64FB6B0075; Thu, 25 Aug 2022 05:24:14 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id B15D06B0078; Thu, 25 Aug 2022 05:24:14 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 98F606B007B; Thu, 25 Aug 2022 05:24:14 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0015.hostedemail.com [216.40.44.15]) by kanga.kvack.org (Postfix) with ESMTP id 8A7E56B0075 for ; Thu, 25 Aug 2022 05:24:14 -0400 (EDT) Received: from smtpin20.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay09.hostedemail.com (Postfix) with ESMTP id 6449381A96 for ; Thu, 25 Aug 2022 09:24:14 +0000 (UTC) X-FDA: 79837578828.20.9B8C130 Received: from mx0b-001b2d01.pphosted.com (mx0b-001b2d01.pphosted.com [148.163.158.5]) by imf08.hostedemail.com (Postfix) with ESMTP id F3D6116000F for ; Thu, 25 Aug 2022 09:24:13 +0000 (UTC) Received: from pps.filterd (m0098417.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.17.1.5/8.17.1.5) with ESMTP id 27P9GUBA018022; Thu, 25 Aug 2022 09:23:55 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ibm.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type : content-transfer-encoding; s=pp1; bh=X7s1R2edoGHobonvf5SDINGwSZCVZM7N9IyraazotsQ=; b=l8F9wuKGg3+y5hD+Q5ZBC0+/Z6FKBbdeTF3UEMPgefM/PKVa+BDvt52i4X97JtTKlk51 U6qpCwkl/sqN/V580ml+W+K/QclHp4Bymo3+916b4tK00EvZwtSeZjhR0X7BNFUtqcnL r3aS9pxkAwxCvOYjvwsdni828LsWTWdvV60jkQ4SBUmWRzFi6vyF1jx5buUuBQnd2f4h 3c49Bv9QkKe23ZT3WmFSi9DtOtIR/wMWRAEYA2wmxqzUBdonjo2epE9grAZ6pIgHLVQs e5jPNPNDRrxkf/3LtDXp53cu3o29x3AISIyju97GE/+PixG65+njuUWgLce/JxaG0a6C Mw== Received: from pps.reinject (localhost [127.0.0.1]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 3j66ab0brk-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 25 Aug 2022 09:23:54 +0000 Received: from m0098417.ppops.net (m0098417.ppops.net [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 27P9K7P5026733; Thu, 25 Aug 2022 09:23:54 GMT Received: from ppma02wdc.us.ibm.com (aa.5b.37a9.ip4.static.sl-reverse.com [169.55.91.170]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 3j66ab0bqk-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 25 Aug 2022 09:23:53 +0000 Received: from pps.filterd (ppma02wdc.us.ibm.com [127.0.0.1]) by ppma02wdc.us.ibm.com (8.16.1.2/8.16.1.2) with SMTP id 27P9KFKc031688; Thu, 25 Aug 2022 09:23:53 GMT Received: from b03cxnp07029.gho.boulder.ibm.com (b03cxnp07029.gho.boulder.ibm.com [9.17.130.16]) by ppma02wdc.us.ibm.com with ESMTP id 3j2q8aenkk-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 25 Aug 2022 09:23:53 +0000 Received: from b03ledav002.gho.boulder.ibm.com (b03ledav002.gho.boulder.ibm.com [9.17.130.233]) by b03cxnp07029.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 27P9NqAL2163434 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 25 Aug 2022 09:23:52 GMT Received: from b03ledav002.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 1D9A713604F; Thu, 25 Aug 2022 09:23:52 +0000 (GMT) Received: from b03ledav002.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id D995313605D; Thu, 25 Aug 2022 09:23:45 +0000 (GMT) Received: from skywalker.ibmuc.com (unknown [9.43.112.25]) by b03ledav002.gho.boulder.ibm.com (Postfix) with ESMTP; Thu, 25 Aug 2022 09:23:45 +0000 (GMT) From: "Aneesh Kumar K.V" To: linux-mm@kvack.org, akpm@linux-foundation.org Cc: Wei Xu , Huang Ying , Yang Shi , Davidlohr Bueso , Tim C Chen , Michal Hocko , Linux Kernel Mailing List , Hesham Almatary , Dave Hansen , Jonathan Cameron , Alistair Popple , Dan Williams , Johannes Weiner , jvgediya.oss@gmail.com, Bharata B Rao , "Aneesh Kumar K.V" Subject: [RFC PATCH 2/2] mm/demotion: Expose memory tier details via sysfs Date: Thu, 25 Aug 2022 14:53:25 +0530 Message-Id: <20220825092325.381517-2-aneesh.kumar@linux.ibm.com> X-Mailer: git-send-email 2.37.2 In-Reply-To: <20220825092325.381517-1-aneesh.kumar@linux.ibm.com> References: <20220825092325.381517-1-aneesh.kumar@linux.ibm.com> MIME-Version: 1.0 X-TM-AS-GCONF: 00 X-Proofpoint-GUID: CfOm5ZXVUAj_3-qYYNfb2PirpQdNuulp X-Proofpoint-ORIG-GUID: V9gQKqZzFXge2-eO-h-6a-lpTiKAK6L7 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.895,Hydra:6.0.517,FMLib:17.11.122.1 definitions=2022-08-25_03,2022-08-22_02,2022-06-22_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 clxscore=1015 mlxlogscore=999 impostorscore=0 lowpriorityscore=0 malwarescore=0 bulkscore=0 adultscore=0 spamscore=0 phishscore=0 suspectscore=0 mlxscore=0 priorityscore=1501 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2207270000 definitions=main-2208250034 ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1661419454; a=rsa-sha256; cv=none; b=tkekfw3xDlfsgpFLCezzSbsYIjAwlEyHyzUdSVDHZo9pDqGfTmBHmx9vqVfyRL+fy6wCx8 U8slg3wNjJ5kBUTUvPSQmrgx17c+f7Fsnxhzd1cmuVcVaES/9azfTgXEDfxb9Yio2eGTn4 B7fomf8+phAwtVunO38tcgDHKCmZTmk= ARC-Authentication-Results: i=1; imf08.hostedemail.com; dkim=pass header.d=ibm.com header.s=pp1 header.b=l8F9wuKG; dmarc=pass (policy=none) header.from=ibm.com; spf=pass (imf08.hostedemail.com: domain of aneesh.kumar@linux.ibm.com designates 148.163.158.5 as permitted sender) smtp.mailfrom=aneesh.kumar@linux.ibm.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1661419454; 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=X7s1R2edoGHobonvf5SDINGwSZCVZM7N9IyraazotsQ=; b=tViMPrFtunH8irTLUxHL1EXVfeazSTFewX1FnhxoAf7ya6HxQvKXbQHSpAp/juZ9AQBu2Q OQ19b5K+0/8TO/CEZauB1juIpcp7yqHoPzULZO9GQMO5SVUYwUGyyBd4RGBcgBFHeOJ+Nj hh/A5H3SRdV54Vyz+wmWWtukXM77cq0= Authentication-Results: imf08.hostedemail.com; dkim=pass header.d=ibm.com header.s=pp1 header.b=l8F9wuKG; dmarc=pass (policy=none) header.from=ibm.com; spf=pass (imf08.hostedemail.com: domain of aneesh.kumar@linux.ibm.com designates 148.163.158.5 as permitted sender) smtp.mailfrom=aneesh.kumar@linux.ibm.com X-Rspam-User: X-Rspamd-Queue-Id: F3D6116000F X-Rspamd-Server: rspam08 X-Stat-Signature: tojhnio3no8eibksyettauphq35n87im X-HE-Tag: 1661419453-962492 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: All allocated memory tiers will be listed as /sys/devices/virtual/memtier/memtierN/ Each memtier directory contains symbolic link for the memory types that are part of the memory tier. A directory hierarchy looks like :/sys/devices/virtual/memtier# tree memtier512/ memtier512/ ├── memtype1 -> ../memtype1 ├── memtype2 -> ../memtype2 ├── subsystem -> ../../../../bus/memtier └── uevent The nodes which are part of a specific memory type can be listed via /sys/devices/system/memtier/memtypeN/nodes. The adistance value of a specific memory type can be listed via /sys/devices/system/memtier/memtypeN/adistance. Signed-off-by: Aneesh Kumar K.V --- mm/memory-tiers.c | 62 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 47 insertions(+), 15 deletions(-) diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 9eef3bd8d134..4005c3124ff0 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -20,6 +20,7 @@ struct memory_tier { * adistance_start .. adistance_start + MEMTIER_CHUNK_SIZE */ int adistance_start; + struct device dev; /* All the nodes that are part of all the lower memory tiers. */ nodemask_t lower_tier_mask; }; @@ -36,6 +37,7 @@ static struct memory_dev_type *default_dram_type; #define MAX_MEMORY_TYPE_ID 20 static DEFINE_IDR(memory_type_idr); #define to_memory_type(device) container_of(device, struct memory_dev_type, dev) +#define to_memory_tier(device) container_of(device, struct memory_tier, dev) static struct bus_type memory_tier_subsys = { .name = "memtier", .dev_name = "memtier", @@ -103,8 +105,25 @@ static int top_tier_adistance; static struct demotion_nodes *node_demotion __read_mostly; #endif /* CONFIG_MIGRATION */ +static void memory_tier_device_release(struct device *dev) +{ + struct memory_tier *tier = to_memory_tier(dev); + /* + * synchronize_rcu in clear_node_memory_tier makes sure + * we don't have rcu access to this memory tier. + */ + kfree(tier); +} + +static void destroy_memory_tier(struct memory_tier *memtier) +{ + list_del(&memtier->list); + device_unregister(&memtier->dev); +} + static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype) { + int ret; bool found_slot = false; struct memory_tier *memtier, *new_memtier; int adistance = memtype->adistance; @@ -128,15 +147,14 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) { - list_add(&memtype->tier_sibiling, &memtier->memory_types); - return memtier; + goto link_memtype; } else if (adistance < memtier->adistance_start) { found_slot = true; break; } } - new_memtier = kmalloc(sizeof(struct memory_tier), GFP_KERNEL); + new_memtier = kzalloc(sizeof(struct memory_tier), GFP_KERNEL); if (!new_memtier) return ERR_PTR(-ENOMEM); @@ -147,8 +165,30 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty list_add_tail(&new_memtier->list, &memtier->list); else list_add_tail(&new_memtier->list, &memory_tiers); - list_add(&memtype->tier_sibiling, &new_memtier->memory_types); - return new_memtier; + + new_memtier->dev.id = adistance; + new_memtier->dev.bus = &memory_tier_subsys; + new_memtier->dev.release = memory_tier_device_release; + + ret = device_register(&new_memtier->dev); + if (ret) { + list_del(&memtier->list); + put_device(&memtier->dev); + return ERR_PTR(ret); + } + memtier = new_memtier; + +link_memtype: + list_add(&memtype->tier_sibiling, &memtier->memory_types); + /* + * ignore error below because the driver creating the device can get + * unloaded and hence the below sysfs create link can fail. We continue + * with the in memory representation. + */ + ret = sysfs_create_link(&memtier->dev.kobj, + &memtype->dev.kobj, kobject_name(&memtype->dev.kobj)); + + return memtier; } static struct memory_tier *__node_get_memory_tier(int node) @@ -424,16 +464,6 @@ static struct memory_tier *set_node_memory_tier(int node) return memtier; } -static void destroy_memory_tier(struct memory_tier *memtier) -{ - list_del(&memtier->list); - /* - * synchronize_rcu in clear_node_memory_tier makes sure - * we don't have rcu access to this memory tier. - */ - kfree(memtier); -} - static bool clear_node_memory_tier(int node) { bool cleared = false; @@ -462,6 +492,8 @@ static bool clear_node_memory_tier(int node) node_clear(node, memtype->nodes); if (nodes_empty(memtype->nodes)) { list_del_init(&memtype->tier_sibiling); + sysfs_delete_link(&memtier->dev.kobj, + &memtype->dev.kobj, kobject_name(&memtype->dev.kobj)); if (list_empty(&memtier->memory_types)) destroy_memory_tier(memtier); }