From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754206AbcFGIMU (ORCPT ); Tue, 7 Jun 2016 04:12:20 -0400 Received: from szxga02-in.huawei.com ([119.145.14.65]:60183 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753896AbcFGIIr (ORCPT ); Tue, 7 Jun 2016 04:08:47 -0400 From: Zhen Lei To: Catalin Marinas , Will Deacon , linux-arm-kernel , Ganapatrao Kulkarni , Robert Richter , "David Daney" , Rob Herring , "Frank Rowand" , Grant Likely , devicetree , linux-kernel CC: Zefan Li , Xinwei Hu , "Tianhong Ding" , Hanjun Guo , Zhen Lei Subject: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES Date: Tue, 7 Jun 2016 16:08:15 +0800 Message-ID: <1465286898-13828-12-git-send-email-thunder.leizhen@huawei.com> X-Mailer: git-send-email 1.9.5.msysgit.1 In-Reply-To: <1465286898-13828-1-git-send-email-thunder.leizhen@huawei.com> References: <1465286898-13828-1-git-send-email-thunder.leizhen@huawei.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.177.23.164] X-CFilter-Loop: Reflected X-Mirapoint-Virus-RAPID-Raw: score=unknown(0), refid=str=0001.0A090203.57568108.008F,ss=1,re=0.000,recu=0.000,reip=0.000,cl=1,cld=1,fgs=0, ip=0.0.0.0, so=2013-06-18 04:22:30, dmn=2013-03-21 17:37:32 X-Mirapoint-Loop-Id: ec2b5f522788fbf6d1f5dd2df17ba886 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Some numa nodes may have no memory. For example: 1. cpu0 on node0 2. cpu1 on node1 3. device0 access the momory from node0 and node1 take the same time. So, we can not simply classify device0 to node0 or node1, but we can define a node2 which distances to node0 and node1 are the same. Signed-off-by: Zhen Lei --- arch/arm64/Kconfig | 4 ++++ arch/arm64/kernel/smp.c | 1 + arch/arm64/mm/numa.c | 43 +++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 46 insertions(+), 2 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05c1bf1..5904a62 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK def_bool y depends on NUMA +config HAVE_MEMORYLESS_NODES + def_bool y + depends on NUMA + source kernel/Kconfig.preempt source kernel/Kconfig.hz diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d099306..9e15297 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void) } bootcpu_valid = true; + early_map_cpu_to_node(0, of_node_to_nid(dn)); /* * cpu_logical_map has already been diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index df5c842..d73b0a0 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid) nid = 0; cpu_to_node_map[cpu] = nid; + + /* + * We should set the numa node of cpu0 as soon as possible, because it + * has already been set up online before. cpu_to_node(0) will soon be + * called. + */ + if (!cpu) + set_cpu_numa_node(cpu, nid); } #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) return ret; } +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t size) +{ + int i, best_nid, distance; + u64 pa; + DECLARE_BITMAP(nodes_map, MAX_NUMNODES); + + bitmap_zero(nodes_map, MAX_NUMNODES); + bitmap_set(nodes_map, nid, 1); + +find_nearest_node: + best_nid = NUMA_NO_NODE; + distance = INT_MAX; + + for_each_clear_bit(i, nodes_map, MAX_NUMNODES) + if (numa_distance[nid][i] < distance) { + best_nid = i; + distance = numa_distance[nid][i]; + } + + pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid); + if (!pa) { + BUG_ON(best_nid == NUMA_NO_NODE); + bitmap_set(nodes_map, best_nid, 1); + goto find_nearest_node; + } + + return pa; +} + /** * Initialize NODE_DATA for a node on the local memory */ @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); - nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) + nd_pa = alloc_node_data_from_nearest_node(nid, nd_size); nd = __va(nd_pa); /* report and initialize */ @@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) if (tnid != nid) pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid); - node_data[nid] = nd; + NODE_DATA(nid) = nd; memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); NODE_DATA(nid)->node_id = nid; NODE_DATA(nid)->node_start_pfn = start_pfn; -- 2.5.0