From mboxrd@z Thu Jan 1 00:00:00 1970 From: Shannon Zhao Subject: Re: [PATCH v7 1/4] arm64, numa: adding numa support for arm64 platforms. Date: Fri, 27 Nov 2015 16:00:00 +0800 Message-ID: <56580D80.2050806@huawei.com> References: <1447780843-9223-1-git-send-email-gkulkarni@caviumnetworks.com> <1447780843-9223-2-git-send-email-gkulkarni@caviumnetworks.com> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1447780843-9223-2-git-send-email-gkulkarni-M3mlKVOIwJVv6pq1l3V1OdBPR1lH4CV8@public.gmane.org> Sender: devicetree-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Ganapatrao Kulkarni , linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Will.Deacon-5wv7dgnIgG8@public.gmane.org, catalin.marinas-5wv7dgnIgG8@public.gmane.org, grant.likely-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, leif.lindholm-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, rfranz-YGCgFSpz5w/QT0dZR+AlfA@public.gmane.org, ard.biesheuvel-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, msalter-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, robh+dt-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org, steve.capper-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, hanjun.guo-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, al.stone-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, arnd-r2nGTMty4D4@public.gmane.org, pawel.moll-5wv7dgnIgG8@public.gmane.org, mark.rutland-5wv7dgnIgG8@public.gmane.org, ijc+devicetree-KcIKpvwj1kUDXYZnReoRVg@public.gmane.org, galak-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org, rjw-LthD3rsA81gm4RdzfppkhA@public.gmane.org, lenb-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org, marc.zyngier-5wv7dgnIgG8@public.gmane.org, rrichter-YGCgFSpz5w/QT0dZR+AlfA@public.gmane.org, Prasun.Kapoor-M3mlKVOIwJVv6pq1l3V1OdBPR1lH4CV8@public.gmane.org Cc: gpkulkarni-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org List-Id: devicetree@vger.kernel.org On 2015/11/18 1:20, Ganapatrao Kulkarni wrote: > Adding numa support for arm64 based platforms. > This patch adds by default the dummy numa node and > maps all memory and cpus to node 0. > using this patch, numa can be simulated on single node arm64 platforms. > > Reviewed-by: Robert Richter > Signed-off-by: Ganapatrao Kulkarni I've tested this patch on QEMU VM. Tested-by: Shannon Zhao > --- > arch/arm64/Kconfig | 25 +++ > arch/arm64/include/asm/mmzone.h | 17 ++ > arch/arm64/include/asm/numa.h | 47 +++++ > arch/arm64/kernel/setup.c | 4 + > arch/arm64/kernel/smp.c | 2 + > arch/arm64/mm/Makefile | 1 + > arch/arm64/mm/init.c | 30 +++- > arch/arm64/mm/numa.c | 384 ++++++++++++++++++++++++++++++++++++++++ > 8 files changed, 506 insertions(+), 4 deletions(-) > create mode 100644 arch/arm64/include/asm/mmzone.h > create mode 100644 arch/arm64/include/asm/numa.h > create mode 100644 arch/arm64/mm/numa.c > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index 9ac16a4..7d8fb42 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -71,6 +71,7 @@ config ARM64 > select HAVE_GENERIC_DMA_COHERENT > select HAVE_HW_BREAKPOINT if PERF_EVENTS > select HAVE_MEMBLOCK > + select HAVE_MEMBLOCK_NODE_MAP if NUMA > select HAVE_PATA_PLATFORM > select HAVE_PERF_EVENTS > select HAVE_PERF_REGS > @@ -482,6 +483,30 @@ config HOTPLUG_CPU > Say Y here to experiment with turning CPUs off and on. CPUs > can be controlled through /sys/devices/system/cpu. > > +# Common NUMA Features > +config NUMA > + bool "Numa Memory Allocation and Scheduler Support" > + depends on SMP > + help > + Enable NUMA (Non Uniform Memory Access) support. > + > + The kernel will try to allocate memory used by a CPU on the > + local memory controller of the CPU and add some more > + NUMA awareness to the kernel. > + > +config NODES_SHIFT > + int "Maximum NUMA Nodes (as a power of 2)" > + range 1 10 > + default "2" > + depends on NEED_MULTIPLE_NODES > + help > + Specify the maximum number of NUMA Nodes available on the target > + system. Increases memory reserved to accommodate various tables. > + > +config USE_PERCPU_NUMA_NODE_ID > + def_bool y > + depends on NUMA > + > source kernel/Kconfig.preempt > source kernel/Kconfig.hz > > diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h > new file mode 100644 > index 0000000..6ddd468 > --- /dev/null > +++ b/arch/arm64/include/asm/mmzone.h > @@ -0,0 +1,17 @@ > +#ifndef __ASM_ARM64_MMZONE_H_ > +#define __ASM_ARM64_MMZONE_H_ > + > +#ifdef CONFIG_NUMA > + > +#include > +#include > + > +#include > +#include > + > +extern struct pglist_data *node_data[]; > + > +#define NODE_DATA(nid) (node_data[(nid)]) > + > +#endif /* CONFIG_NUMA */ > +#endif /* __ASM_ARM64_MMZONE_H_ */ > diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h > new file mode 100644 > index 0000000..c00f3a4 > --- /dev/null > +++ b/arch/arm64/include/asm/numa.h > @@ -0,0 +1,47 @@ > +#ifndef _ASM_NUMA_H > +#define _ASM_NUMA_H > + > +#include > +#include > + > +#ifdef CONFIG_NUMA > + > +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) > +#define ZONE_ALIGN (1UL << (MAX_ORDER + PAGE_SHIFT)) > + > +/* currently, arm64 implements flat NUMA topology */ > +#define parent_node(node) (node) > + > +extern int __node_distance(int from, int to); > +#define node_distance(a, b) __node_distance(a, b) > + > +/* dummy definitions for pci functions */ > +#define pcibus_to_node(node) 0 > +#define cpumask_of_pcibus(bus) 0 > + > +extern int cpu_to_node_map[NR_CPUS]; > +extern nodemask_t numa_nodes_parsed __initdata; > + > +/* Mappings between node number and cpus on that node. */ > +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; > +extern void numa_clear_node(unsigned int cpu); > +#ifdef CONFIG_DEBUG_PER_CPU_MAPS > +extern const struct cpumask *cpumask_of_node(int node); > +#else > +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ > +static inline const struct cpumask *cpumask_of_node(int node) > +{ > + return node_to_cpumask_map[node]; > +} > +#endif > + > +void __init arm64_numa_init(void); > +int __init numa_add_memblk(int nodeid, u64 start, u64 end); > +void __init numa_set_distance(int from, int to, int distance); > +void __init numa_reset_distance(void); > +void numa_store_cpu_info(unsigned int cpu); > +#else /* CONFIG_NUMA */ > +static inline void numa_store_cpu_info(unsigned int cpu) { } > +static inline void arm64_numa_init(void) { } > +#endif /* CONFIG_NUMA */ > +#endif /* _ASM_NUMA_H */ > diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c > index 8119479..d9b9761 100644 > --- a/arch/arm64/kernel/setup.c > +++ b/arch/arm64/kernel/setup.c > @@ -53,6 +53,7 @@ > #include > #include > #include > +#include > #include > #include > #include > @@ -372,6 +373,9 @@ static int __init topology_init(void) > { > int i; > > + for_each_online_node(i) > + register_one_node(i); > + > for_each_possible_cpu(i) { > struct cpu *cpu = &per_cpu(cpu_data.cpu, i); > cpu->hotpluggable = 1; > diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c > index b1adc51..d6e7d6a 100644 > --- a/arch/arm64/kernel/smp.c > +++ b/arch/arm64/kernel/smp.c > @@ -45,6 +45,7 @@ > #include > #include > #include > +#include > #include > #include > #include > @@ -125,6 +126,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) > static void smp_store_cpu_info(unsigned int cpuid) > { > store_cpu_topology(cpuid); > + numa_store_cpu_info(cpuid); > } > > /* > diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile > index 57f57fd..2e57922 100644 > --- a/arch/arm64/mm/Makefile > +++ b/arch/arm64/mm/Makefile > @@ -6,4 +6,5 @@ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o > obj-$(CONFIG_ARM64_PTDUMP) += dump.o > > obj-$(CONFIG_KASAN) += kasan_init.o > +obj-$(CONFIG_NUMA) += numa.o > KASAN_SANITIZE_kasan_init.o := n > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 17bf39a..8dc9c5d 100644 > --- a/arch/arm64/mm/init.c > +++ b/arch/arm64/mm/init.c > @@ -37,6 +37,7 @@ > > #include > #include > +#include > #include > #include > #include > @@ -77,6 +78,19 @@ static phys_addr_t max_zone_dma_phys(void) > return min(offset + (1ULL << 32), memblock_end_of_DRAM()); > } > > +#ifdef CONFIG_NUMA > +static void __init zone_sizes_init(unsigned long min, unsigned long max) > +{ > + unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; > + > + if (IS_ENABLED(CONFIG_ZONE_DMA)) > + max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys()); > + max_zone_pfns[ZONE_NORMAL] = max; > + > + free_area_init_nodes(max_zone_pfns); > +} > + > +#else > static void __init zone_sizes_init(unsigned long min, unsigned long max) > { > struct memblock_region *reg; > @@ -116,6 +130,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) > > free_area_init_node(0, zone_size, min, zhole_size); > } > +#endif /* CONFIG_NUMA */ > > #ifdef CONFIG_HAVE_ARCH_PFN_VALID > int pfn_valid(unsigned long pfn) > @@ -133,10 +148,15 @@ static void arm64_memory_present(void) > static void arm64_memory_present(void) > { > struct memblock_region *reg; > + int nid = 0; > > - for_each_memblock(memory, reg) > - memory_present(0, memblock_region_memory_base_pfn(reg), > - memblock_region_memory_end_pfn(reg)); > + for_each_memblock(memory, reg) { > +#ifdef CONFIG_NUMA > + nid = reg->nid; > +#endif > + memory_present(nid, memblock_region_memory_base_pfn(reg), > + memblock_region_memory_end_pfn(reg)); > + } > } > #endif > > @@ -193,6 +213,9 @@ void __init bootmem_init(void) > > early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT); > > + max_pfn = max_low_pfn = max; > + > + arm64_numa_init(); > /* > * Sparsemem tries to allocate bootmem in memory_present(), so must be > * done after the fixed reservations. > @@ -203,7 +226,6 @@ void __init bootmem_init(void) > zone_sizes_init(min, max); > > high_memory = __va((max << PAGE_SHIFT) - 1) + 1; > - max_pfn = max_low_pfn = max; > } > > #ifndef CONFIG_SPARSEMEM_VMEMMAP > diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c > new file mode 100644 > index 0000000..e3afbf8 > --- /dev/null > +++ b/arch/arm64/mm/numa.c > @@ -0,0 +1,384 @@ > +/* > + * NUMA support, based on the x86 implementation. > + * > + * Copyright (C) 2015 Cavium Inc. > + * Author: Ganapatrao Kulkarni > + * > + * This program is free software; you can redistribute it and/or modify > + * it under the terms of the GNU General Public License version 2 as > + * published by the Free Software Foundation. > + * > + * This program 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 General Public License for more details. > + * > + * You should have received a copy of the GNU General Public License > + * along with this program. If not, see . > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include > + > +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; > +EXPORT_SYMBOL(node_data); > +nodemask_t numa_nodes_parsed __initdata; > +int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; > + > +static int numa_off; > +static int numa_distance_cnt; > +static u8 *numa_distance; > + > +static __init int numa_parse_early_param(char *opt) > +{ > + if (!opt) > + return -EINVAL; > + if (!strncmp(opt, "off", 3)) { > + pr_info("%s\n", "NUMA turned off"); > + numa_off = 1; > + } > + return 0; > +} > +early_param("numa", numa_parse_early_param); > + > +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; > +EXPORT_SYMBOL(node_to_cpumask_map); > + > +#ifdef CONFIG_DEBUG_PER_CPU_MAPS > +/* > + * Returns a pointer to the bitmask of CPUs on Node 'node'. > + */ > +const struct cpumask *cpumask_of_node(int node) > +{ > + > + if (WARN_ON(node >= nr_node_ids)) > + return cpu_none_mask; > + > + if (WARN_ON(node_to_cpumask_map[node] == NULL)) > + return cpu_online_mask; > + > + return node_to_cpumask_map[node]; > +} > +EXPORT_SYMBOL(cpumask_of_node); > +#endif > + > +static void map_cpu_to_node(unsigned int cpu, int nid) > +{ > + set_cpu_numa_node(cpu, nid); > + if (nid >= 0) > + cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); > +} > + > +static void unmap_cpu_to_node(unsigned int cpu) > +{ > + int nid = cpu_to_node(cpu); > + > + if (nid >= 0) > + cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); > + set_cpu_numa_node(cpu, NUMA_NO_NODE); > +} > + > +void numa_clear_node(unsigned int cpu) > +{ > + unmap_cpu_to_node(cpu); > +} > + > +/* > + * Allocate node_to_cpumask_map based on number of available nodes > + * Requires node_possible_map to be valid. > + * > + * Note: cpumask_of_node() is not valid until after this is done. > + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) > + */ > +static void __init setup_node_to_cpumask_map(void) > +{ > + unsigned int cpu; > + int node; > + > + /* setup nr_node_ids if not done yet */ > + if (nr_node_ids == MAX_NUMNODES) > + setup_nr_node_ids(); > + > + /* allocate and clear the mapping */ > + for (node = 0; node < nr_node_ids; node++) { > + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); > + cpumask_clear(node_to_cpumask_map[node]); > + } > + > + for_each_possible_cpu(cpu) > + set_cpu_numa_node(cpu, NUMA_NO_NODE); > + > + /* cpumask_of_node() will now work */ > + pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); > +} > + > +/* > + * Set the cpu to node and mem mapping > + */ > +void numa_store_cpu_info(unsigned int cpu) > +{ > + map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]); > +} > + > +/** > + * numa_add_memblk - Set node id to memblk > + * @nid: NUMA node ID of the new memblk > + * @start: Start address of the new memblk > + * @size: Size of the new memblk > + * > + * RETURNS: > + * 0 on success, -errno on failure. > + */ > +int __init numa_add_memblk(int nid, u64 start, u64 size) > +{ > + int ret; > + > + ret = memblock_set_node(start, size, &memblock.memory, nid); > + if (ret < 0) { > + pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n", > + start, (start + size - 1), nid); > + return ret; > + } > + > + node_set(nid, numa_nodes_parsed); > + pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n", > + start, (start + size - 1), nid); > + return ret; > +} > +EXPORT_SYMBOL(numa_add_memblk); > + > +/* Initialize NODE_DATA for a node on the local memory */ > +static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) > +{ > + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); > + u64 nd_pa; > + void *nd; > + int tnid; > + > + 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 = __va(nd_pa); > + > + /* report and initialize */ > + pr_info(" NODE_DATA [mem %#010Lx-%#010Lx]\n", > + nd_pa, nd_pa + nd_size - 1); > + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); > + if (tnid != nid) > + pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid); > + > + 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; > + NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; > +} > + > +/** > + * numa_reset_distance - Reset NUMA distance table > + * > + * The current table is freed. > + * The next numa_set_distance() call will create a new one. > + */ > +void __init numa_reset_distance(void) > +{ > + size_t size; > + > + if (!numa_distance) > + return; > + > + size = numa_distance_cnt * numa_distance_cnt * > + sizeof(numa_distance[0]); > + > + memblock_free(__pa(numa_distance), size); > + numa_distance_cnt = 0; > + numa_distance = NULL; > +} > + > +static int __init numa_alloc_distance(void) > +{ > + size_t size; > + u64 phys; > + int i, j; > + > + size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); > + phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), > + size, PAGE_SIZE); > + if (WARN_ON(!phys)) > + return -ENOMEM; > + > + memblock_reserve(phys, size); > + > + numa_distance = __va(phys); > + numa_distance_cnt = nr_node_ids; > + > + /* fill with the default distances */ > + for (i = 0; i < numa_distance_cnt; i++) > + for (j = 0; j < numa_distance_cnt; j++) > + numa_distance[i * numa_distance_cnt + j] = i == j ? > + LOCAL_DISTANCE : REMOTE_DISTANCE; > + > + pr_debug("NUMA: Initialized distance table, cnt=%d\n", > + numa_distance_cnt); > + > + return 0; > +} > + > +/** > + * numa_set_distance - Set NUMA distance from one NUMA to another > + * @from: the 'from' node to set distance > + * @to: the 'to' node to set distance > + * @distance: NUMA distance > + * > + * Set the distance from node @from to @to to @distance. If distance table > + * doesn't exist, one which is large enough to accommodate all the currently > + * known nodes will be created. > + * > + * If such table cannot be allocated, a warning is printed and further > + * calls are ignored until the distance table is reset with > + * numa_reset_distance(). > + * > + * If @from or @to is higher than the highest known node or lower than zero > + * at the time of table creation or @distance doesn't make sense, the call > + * is ignored. > + * This is to allow simplification of specific NUMA config implementations. > + */ > +void __init numa_set_distance(int from, int to, int distance) > +{ > + if (!numa_distance) > + return; > + > + if (from >= numa_distance_cnt || to >= numa_distance_cnt || > + from < 0 || to < 0) { > + pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n", > + from, to, distance); > + return; > + } > + > + if ((u8)distance != distance || > + (from == to && distance != LOCAL_DISTANCE)) { > + pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", > + from, to, distance); > + return; > + } > + > + numa_distance[from * numa_distance_cnt + to] = distance; > +} > +EXPORT_SYMBOL(numa_set_distance); > + > +int __node_distance(int from, int to) > +{ > + if (from >= numa_distance_cnt || to >= numa_distance_cnt) > + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; > + return numa_distance[from * numa_distance_cnt + to]; > +} > +EXPORT_SYMBOL(__node_distance); > + > +static int __init numa_register_nodes(void) > +{ > + int nid; > + struct memblock_region *mblk; > + > + /* Check that valid nid is set to memblks */ > + for_each_memblock(memory, mblk) > + if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) > + return -EINVAL; > + > + /* Finally register nodes. */ > + for_each_node_mask(nid, numa_nodes_parsed) { > + unsigned long start_pfn, end_pfn; > + > + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); > + setup_node_data(nid, start_pfn, end_pfn); > + node_set_online(nid); > + } > + > + /* Setup online nodes to actual nodes*/ > + node_possible_map = numa_nodes_parsed; > + > + /* Dump memblock with node info and return. */ > + memblock_dump_all(); > + return 0; > +} > + > +static int __init numa_init(int (*init_func)(void)) > +{ > + int ret; > + > + nodes_clear(numa_nodes_parsed); > + nodes_clear(node_possible_map); > + nodes_clear(node_online_map); > + numa_reset_distance(); > + > + ret = init_func(); > + if (ret < 0) > + return ret; > + > + if (nodes_empty(numa_nodes_parsed)) > + return -EINVAL; > + > + ret = numa_register_nodes(); > + if (ret < 0) > + return ret; > + > + ret = numa_alloc_distance(); > + if (ret < 0) > + return ret; > + > + setup_node_to_cpumask_map(); > + > + /* init boot processor */ > + cpu_to_node_map[0] = 0; > + map_cpu_to_node(0, 0); > + > + return 0; > +} > + > +/** > + * dummy_numa_init - Fallback dummy NUMA init > + * > + * Used if there's no underlying NUMA architecture, NUMA initialization > + * fails, or NUMA is disabled on the command line. > + * > + * Must online at least one node and add memory blocks that cover all > + * allowed memory. This function must not fail. > + */ > +static int __init dummy_numa_init(void) > +{ > + struct memblock_region *mblk; > + > + pr_info("%s\n", "No NUMA configuration found"); > + pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", > + 0LLU, PFN_PHYS(max_pfn) - 1); > + for_each_memblock(memory, mblk) > + numa_add_memblk(0, mblk->base, mblk->size); > + numa_off = 1; > + > + return 0; > +} > + > +/** > + * arm64_numa_init - Initialize NUMA > + * > + * Try each configured NUMA initialization method until one succeeds. The > + * last fallback is dummy single node config encomapssing whole memory and > + * never fails. > + */ > +void __init arm64_numa_init(void) > +{ > + numa_init(dummy_numa_init); > +} > -- Shannon -- To unsubscribe from this list: send the line "unsubscribe devicetree" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html From mboxrd@z Thu Jan 1 00:00:00 1970 From: zhaoshenglong@huawei.com (Shannon Zhao) Date: Fri, 27 Nov 2015 16:00:00 +0800 Subject: [PATCH v7 1/4] arm64, numa: adding numa support for arm64 platforms. In-Reply-To: <1447780843-9223-2-git-send-email-gkulkarni@caviumnetworks.com> References: <1447780843-9223-1-git-send-email-gkulkarni@caviumnetworks.com> <1447780843-9223-2-git-send-email-gkulkarni@caviumnetworks.com> Message-ID: <56580D80.2050806@huawei.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 2015/11/18 1:20, Ganapatrao Kulkarni wrote: > Adding numa support for arm64 based platforms. > This patch adds by default the dummy numa node and > maps all memory and cpus to node 0. > using this patch, numa can be simulated on single node arm64 platforms. > > Reviewed-by: Robert Richter > Signed-off-by: Ganapatrao Kulkarni I've tested this patch on QEMU VM. Tested-by: Shannon Zhao > --- > arch/arm64/Kconfig | 25 +++ > arch/arm64/include/asm/mmzone.h | 17 ++ > arch/arm64/include/asm/numa.h | 47 +++++ > arch/arm64/kernel/setup.c | 4 + > arch/arm64/kernel/smp.c | 2 + > arch/arm64/mm/Makefile | 1 + > arch/arm64/mm/init.c | 30 +++- > arch/arm64/mm/numa.c | 384 ++++++++++++++++++++++++++++++++++++++++ > 8 files changed, 506 insertions(+), 4 deletions(-) > create mode 100644 arch/arm64/include/asm/mmzone.h > create mode 100644 arch/arm64/include/asm/numa.h > create mode 100644 arch/arm64/mm/numa.c > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index 9ac16a4..7d8fb42 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -71,6 +71,7 @@ config ARM64 > select HAVE_GENERIC_DMA_COHERENT > select HAVE_HW_BREAKPOINT if PERF_EVENTS > select HAVE_MEMBLOCK > + select HAVE_MEMBLOCK_NODE_MAP if NUMA > select HAVE_PATA_PLATFORM > select HAVE_PERF_EVENTS > select HAVE_PERF_REGS > @@ -482,6 +483,30 @@ config HOTPLUG_CPU > Say Y here to experiment with turning CPUs off and on. CPUs > can be controlled through /sys/devices/system/cpu. > > +# Common NUMA Features > +config NUMA > + bool "Numa Memory Allocation and Scheduler Support" > + depends on SMP > + help > + Enable NUMA (Non Uniform Memory Access) support. > + > + The kernel will try to allocate memory used by a CPU on the > + local memory controller of the CPU and add some more > + NUMA awareness to the kernel. > + > +config NODES_SHIFT > + int "Maximum NUMA Nodes (as a power of 2)" > + range 1 10 > + default "2" > + depends on NEED_MULTIPLE_NODES > + help > + Specify the maximum number of NUMA Nodes available on the target > + system. Increases memory reserved to accommodate various tables. > + > +config USE_PERCPU_NUMA_NODE_ID > + def_bool y > + depends on NUMA > + > source kernel/Kconfig.preempt > source kernel/Kconfig.hz > > diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h > new file mode 100644 > index 0000000..6ddd468 > --- /dev/null > +++ b/arch/arm64/include/asm/mmzone.h > @@ -0,0 +1,17 @@ > +#ifndef __ASM_ARM64_MMZONE_H_ > +#define __ASM_ARM64_MMZONE_H_ > + > +#ifdef CONFIG_NUMA > + > +#include > +#include > + > +#include > +#include > + > +extern struct pglist_data *node_data[]; > + > +#define NODE_DATA(nid) (node_data[(nid)]) > + > +#endif /* CONFIG_NUMA */ > +#endif /* __ASM_ARM64_MMZONE_H_ */ > diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h > new file mode 100644 > index 0000000..c00f3a4 > --- /dev/null > +++ b/arch/arm64/include/asm/numa.h > @@ -0,0 +1,47 @@ > +#ifndef _ASM_NUMA_H > +#define _ASM_NUMA_H > + > +#include > +#include > + > +#ifdef CONFIG_NUMA > + > +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) > +#define ZONE_ALIGN (1UL << (MAX_ORDER + PAGE_SHIFT)) > + > +/* currently, arm64 implements flat NUMA topology */ > +#define parent_node(node) (node) > + > +extern int __node_distance(int from, int to); > +#define node_distance(a, b) __node_distance(a, b) > + > +/* dummy definitions for pci functions */ > +#define pcibus_to_node(node) 0 > +#define cpumask_of_pcibus(bus) 0 > + > +extern int cpu_to_node_map[NR_CPUS]; > +extern nodemask_t numa_nodes_parsed __initdata; > + > +/* Mappings between node number and cpus on that node. */ > +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; > +extern void numa_clear_node(unsigned int cpu); > +#ifdef CONFIG_DEBUG_PER_CPU_MAPS > +extern const struct cpumask *cpumask_of_node(int node); > +#else > +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ > +static inline const struct cpumask *cpumask_of_node(int node) > +{ > + return node_to_cpumask_map[node]; > +} > +#endif > + > +void __init arm64_numa_init(void); > +int __init numa_add_memblk(int nodeid, u64 start, u64 end); > +void __init numa_set_distance(int from, int to, int distance); > +void __init numa_reset_distance(void); > +void numa_store_cpu_info(unsigned int cpu); > +#else /* CONFIG_NUMA */ > +static inline void numa_store_cpu_info(unsigned int cpu) { } > +static inline void arm64_numa_init(void) { } > +#endif /* CONFIG_NUMA */ > +#endif /* _ASM_NUMA_H */ > diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c > index 8119479..d9b9761 100644 > --- a/arch/arm64/kernel/setup.c > +++ b/arch/arm64/kernel/setup.c > @@ -53,6 +53,7 @@ > #include > #include > #include > +#include > #include > #include > #include > @@ -372,6 +373,9 @@ static int __init topology_init(void) > { > int i; > > + for_each_online_node(i) > + register_one_node(i); > + > for_each_possible_cpu(i) { > struct cpu *cpu = &per_cpu(cpu_data.cpu, i); > cpu->hotpluggable = 1; > diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c > index b1adc51..d6e7d6a 100644 > --- a/arch/arm64/kernel/smp.c > +++ b/arch/arm64/kernel/smp.c > @@ -45,6 +45,7 @@ > #include > #include > #include > +#include > #include > #include > #include > @@ -125,6 +126,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) > static void smp_store_cpu_info(unsigned int cpuid) > { > store_cpu_topology(cpuid); > + numa_store_cpu_info(cpuid); > } > > /* > diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile > index 57f57fd..2e57922 100644 > --- a/arch/arm64/mm/Makefile > +++ b/arch/arm64/mm/Makefile > @@ -6,4 +6,5 @@ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o > obj-$(CONFIG_ARM64_PTDUMP) += dump.o > > obj-$(CONFIG_KASAN) += kasan_init.o > +obj-$(CONFIG_NUMA) += numa.o > KASAN_SANITIZE_kasan_init.o := n > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 17bf39a..8dc9c5d 100644 > --- a/arch/arm64/mm/init.c > +++ b/arch/arm64/mm/init.c > @@ -37,6 +37,7 @@ > > #include > #include > +#include > #include > #include > #include > @@ -77,6 +78,19 @@ static phys_addr_t max_zone_dma_phys(void) > return min(offset + (1ULL << 32), memblock_end_of_DRAM()); > } > > +#ifdef CONFIG_NUMA > +static void __init zone_sizes_init(unsigned long min, unsigned long max) > +{ > + unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; > + > + if (IS_ENABLED(CONFIG_ZONE_DMA)) > + max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys()); > + max_zone_pfns[ZONE_NORMAL] = max; > + > + free_area_init_nodes(max_zone_pfns); > +} > + > +#else > static void __init zone_sizes_init(unsigned long min, unsigned long max) > { > struct memblock_region *reg; > @@ -116,6 +130,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) > > free_area_init_node(0, zone_size, min, zhole_size); > } > +#endif /* CONFIG_NUMA */ > > #ifdef CONFIG_HAVE_ARCH_PFN_VALID > int pfn_valid(unsigned long pfn) > @@ -133,10 +148,15 @@ static void arm64_memory_present(void) > static void arm64_memory_present(void) > { > struct memblock_region *reg; > + int nid = 0; > > - for_each_memblock(memory, reg) > - memory_present(0, memblock_region_memory_base_pfn(reg), > - memblock_region_memory_end_pfn(reg)); > + for_each_memblock(memory, reg) { > +#ifdef CONFIG_NUMA > + nid = reg->nid; > +#endif > + memory_present(nid, memblock_region_memory_base_pfn(reg), > + memblock_region_memory_end_pfn(reg)); > + } > } > #endif > > @@ -193,6 +213,9 @@ void __init bootmem_init(void) > > early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT); > > + max_pfn = max_low_pfn = max; > + > + arm64_numa_init(); > /* > * Sparsemem tries to allocate bootmem in memory_present(), so must be > * done after the fixed reservations. > @@ -203,7 +226,6 @@ void __init bootmem_init(void) > zone_sizes_init(min, max); > > high_memory = __va((max << PAGE_SHIFT) - 1) + 1; > - max_pfn = max_low_pfn = max; > } > > #ifndef CONFIG_SPARSEMEM_VMEMMAP > diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c > new file mode 100644 > index 0000000..e3afbf8 > --- /dev/null > +++ b/arch/arm64/mm/numa.c > @@ -0,0 +1,384 @@ > +/* > + * NUMA support, based on the x86 implementation. > + * > + * Copyright (C) 2015 Cavium Inc. > + * Author: Ganapatrao Kulkarni > + * > + * This program is free software; you can redistribute it and/or modify > + * it under the terms of the GNU General Public License version 2 as > + * published by the Free Software Foundation. > + * > + * This program 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 General Public License for more details. > + * > + * You should have received a copy of the GNU General Public License > + * along with this program. If not, see . > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include > + > +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; > +EXPORT_SYMBOL(node_data); > +nodemask_t numa_nodes_parsed __initdata; > +int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; > + > +static int numa_off; > +static int numa_distance_cnt; > +static u8 *numa_distance; > + > +static __init int numa_parse_early_param(char *opt) > +{ > + if (!opt) > + return -EINVAL; > + if (!strncmp(opt, "off", 3)) { > + pr_info("%s\n", "NUMA turned off"); > + numa_off = 1; > + } > + return 0; > +} > +early_param("numa", numa_parse_early_param); > + > +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; > +EXPORT_SYMBOL(node_to_cpumask_map); > + > +#ifdef CONFIG_DEBUG_PER_CPU_MAPS > +/* > + * Returns a pointer to the bitmask of CPUs on Node 'node'. > + */ > +const struct cpumask *cpumask_of_node(int node) > +{ > + > + if (WARN_ON(node >= nr_node_ids)) > + return cpu_none_mask; > + > + if (WARN_ON(node_to_cpumask_map[node] == NULL)) > + return cpu_online_mask; > + > + return node_to_cpumask_map[node]; > +} > +EXPORT_SYMBOL(cpumask_of_node); > +#endif > + > +static void map_cpu_to_node(unsigned int cpu, int nid) > +{ > + set_cpu_numa_node(cpu, nid); > + if (nid >= 0) > + cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); > +} > + > +static void unmap_cpu_to_node(unsigned int cpu) > +{ > + int nid = cpu_to_node(cpu); > + > + if (nid >= 0) > + cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); > + set_cpu_numa_node(cpu, NUMA_NO_NODE); > +} > + > +void numa_clear_node(unsigned int cpu) > +{ > + unmap_cpu_to_node(cpu); > +} > + > +/* > + * Allocate node_to_cpumask_map based on number of available nodes > + * Requires node_possible_map to be valid. > + * > + * Note: cpumask_of_node() is not valid until after this is done. > + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) > + */ > +static void __init setup_node_to_cpumask_map(void) > +{ > + unsigned int cpu; > + int node; > + > + /* setup nr_node_ids if not done yet */ > + if (nr_node_ids == MAX_NUMNODES) > + setup_nr_node_ids(); > + > + /* allocate and clear the mapping */ > + for (node = 0; node < nr_node_ids; node++) { > + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); > + cpumask_clear(node_to_cpumask_map[node]); > + } > + > + for_each_possible_cpu(cpu) > + set_cpu_numa_node(cpu, NUMA_NO_NODE); > + > + /* cpumask_of_node() will now work */ > + pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); > +} > + > +/* > + * Set the cpu to node and mem mapping > + */ > +void numa_store_cpu_info(unsigned int cpu) > +{ > + map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]); > +} > + > +/** > + * numa_add_memblk - Set node id to memblk > + * @nid: NUMA node ID of the new memblk > + * @start: Start address of the new memblk > + * @size: Size of the new memblk > + * > + * RETURNS: > + * 0 on success, -errno on failure. > + */ > +int __init numa_add_memblk(int nid, u64 start, u64 size) > +{ > + int ret; > + > + ret = memblock_set_node(start, size, &memblock.memory, nid); > + if (ret < 0) { > + pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n", > + start, (start + size - 1), nid); > + return ret; > + } > + > + node_set(nid, numa_nodes_parsed); > + pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n", > + start, (start + size - 1), nid); > + return ret; > +} > +EXPORT_SYMBOL(numa_add_memblk); > + > +/* Initialize NODE_DATA for a node on the local memory */ > +static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) > +{ > + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); > + u64 nd_pa; > + void *nd; > + int tnid; > + > + 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 = __va(nd_pa); > + > + /* report and initialize */ > + pr_info(" NODE_DATA [mem %#010Lx-%#010Lx]\n", > + nd_pa, nd_pa + nd_size - 1); > + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); > + if (tnid != nid) > + pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid); > + > + 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; > + NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; > +} > + > +/** > + * numa_reset_distance - Reset NUMA distance table > + * > + * The current table is freed. > + * The next numa_set_distance() call will create a new one. > + */ > +void __init numa_reset_distance(void) > +{ > + size_t size; > + > + if (!numa_distance) > + return; > + > + size = numa_distance_cnt * numa_distance_cnt * > + sizeof(numa_distance[0]); > + > + memblock_free(__pa(numa_distance), size); > + numa_distance_cnt = 0; > + numa_distance = NULL; > +} > + > +static int __init numa_alloc_distance(void) > +{ > + size_t size; > + u64 phys; > + int i, j; > + > + size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); > + phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), > + size, PAGE_SIZE); > + if (WARN_ON(!phys)) > + return -ENOMEM; > + > + memblock_reserve(phys, size); > + > + numa_distance = __va(phys); > + numa_distance_cnt = nr_node_ids; > + > + /* fill with the default distances */ > + for (i = 0; i < numa_distance_cnt; i++) > + for (j = 0; j < numa_distance_cnt; j++) > + numa_distance[i * numa_distance_cnt + j] = i == j ? > + LOCAL_DISTANCE : REMOTE_DISTANCE; > + > + pr_debug("NUMA: Initialized distance table, cnt=%d\n", > + numa_distance_cnt); > + > + return 0; > +} > + > +/** > + * numa_set_distance - Set NUMA distance from one NUMA to another > + * @from: the 'from' node to set distance > + * @to: the 'to' node to set distance > + * @distance: NUMA distance > + * > + * Set the distance from node @from to @to to @distance. If distance table > + * doesn't exist, one which is large enough to accommodate all the currently > + * known nodes will be created. > + * > + * If such table cannot be allocated, a warning is printed and further > + * calls are ignored until the distance table is reset with > + * numa_reset_distance(). > + * > + * If @from or @to is higher than the highest known node or lower than zero > + * at the time of table creation or @distance doesn't make sense, the call > + * is ignored. > + * This is to allow simplification of specific NUMA config implementations. > + */ > +void __init numa_set_distance(int from, int to, int distance) > +{ > + if (!numa_distance) > + return; > + > + if (from >= numa_distance_cnt || to >= numa_distance_cnt || > + from < 0 || to < 0) { > + pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n", > + from, to, distance); > + return; > + } > + > + if ((u8)distance != distance || > + (from == to && distance != LOCAL_DISTANCE)) { > + pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", > + from, to, distance); > + return; > + } > + > + numa_distance[from * numa_distance_cnt + to] = distance; > +} > +EXPORT_SYMBOL(numa_set_distance); > + > +int __node_distance(int from, int to) > +{ > + if (from >= numa_distance_cnt || to >= numa_distance_cnt) > + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; > + return numa_distance[from * numa_distance_cnt + to]; > +} > +EXPORT_SYMBOL(__node_distance); > + > +static int __init numa_register_nodes(void) > +{ > + int nid; > + struct memblock_region *mblk; > + > + /* Check that valid nid is set to memblks */ > + for_each_memblock(memory, mblk) > + if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) > + return -EINVAL; > + > + /* Finally register nodes. */ > + for_each_node_mask(nid, numa_nodes_parsed) { > + unsigned long start_pfn, end_pfn; > + > + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); > + setup_node_data(nid, start_pfn, end_pfn); > + node_set_online(nid); > + } > + > + /* Setup online nodes to actual nodes*/ > + node_possible_map = numa_nodes_parsed; > + > + /* Dump memblock with node info and return. */ > + memblock_dump_all(); > + return 0; > +} > + > +static int __init numa_init(int (*init_func)(void)) > +{ > + int ret; > + > + nodes_clear(numa_nodes_parsed); > + nodes_clear(node_possible_map); > + nodes_clear(node_online_map); > + numa_reset_distance(); > + > + ret = init_func(); > + if (ret < 0) > + return ret; > + > + if (nodes_empty(numa_nodes_parsed)) > + return -EINVAL; > + > + ret = numa_register_nodes(); > + if (ret < 0) > + return ret; > + > + ret = numa_alloc_distance(); > + if (ret < 0) > + return ret; > + > + setup_node_to_cpumask_map(); > + > + /* init boot processor */ > + cpu_to_node_map[0] = 0; > + map_cpu_to_node(0, 0); > + > + return 0; > +} > + > +/** > + * dummy_numa_init - Fallback dummy NUMA init > + * > + * Used if there's no underlying NUMA architecture, NUMA initialization > + * fails, or NUMA is disabled on the command line. > + * > + * Must online at least one node and add memory blocks that cover all > + * allowed memory. This function must not fail. > + */ > +static int __init dummy_numa_init(void) > +{ > + struct memblock_region *mblk; > + > + pr_info("%s\n", "No NUMA configuration found"); > + pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", > + 0LLU, PFN_PHYS(max_pfn) - 1); > + for_each_memblock(memory, mblk) > + numa_add_memblk(0, mblk->base, mblk->size); > + numa_off = 1; > + > + return 0; > +} > + > +/** > + * arm64_numa_init - Initialize NUMA > + * > + * Try each configured NUMA initialization method until one succeeds. The > + * last fallback is dummy single node config encomapssing whole memory and > + * never fails. > + */ > +void __init arm64_numa_init(void) > +{ > + numa_init(dummy_numa_init); > +} > -- Shannon