The patch titled Subject: arch, mm: pull out allocation of NODE_DATA to generic code has been added to the -mm mm-unstable branch. Its filename is arch-mm-pull-out-allocation-of-node_data-to-generic-code.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/arch-mm-pull-out-allocation-of-node_data-to-generic-code.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: "Mike Rapoport (Microsoft)" <rppt@xxxxxxxxxx> Subject: arch, mm: pull out allocation of NODE_DATA to generic code Date: Thu, 1 Aug 2024 09:08:09 +0300 Architectures that support NUMA duplicate the code that allocates NODE_DATA on the node-local memory with slight variations in reporting of the addresses where the memory was allocated. Use x86 version as the basis for the generic alloc_node_data() function and call this function in architecture specific numa initialization. Round up node data size to SMP_CACHE_BYTES rather than to PAGE_SIZE like x86 used to do since the bootmem era when allocation granularity was PAGE_SIZE anyway. Link: https://lkml.kernel.org/r/20240801060826.559858-10-rppt@xxxxxxxxxx Signed-off-by: Mike Rapoport (Microsoft) <rppt@xxxxxxxxxx> Acked-by: David Hildenbrand <david@xxxxxxxxxx> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx> Tested-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx> [arm64 + CXL via QEMU] Tested-by: Zi Yan <ziy@xxxxxxxxxx> # for x86_64 and arm64 Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx> Cc: Andreas Larsson <andreas@xxxxxxxxxxx> Cc: Arnd Bergmann <arnd@xxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Catalin Marinas <catalin.marinas@xxxxxxx> Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx> Cc: David S. Miller <davem@xxxxxxxxxxxxx> Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> Cc: Heiko Carstens <hca@xxxxxxxxxxxxx> Cc: Huacai Chen <chenhuacai@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Jiaxun Yang <jiaxun.yang@xxxxxxxxxxx> Cc: John Paul Adrian Glaubitz <glaubitz@xxxxxxxxxxxxxxxxxxx> Cc: Jonathan Corbet <corbet@xxxxxxx> Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx> Cc: Palmer Dabbelt <palmer@xxxxxxxxxxx> Cc: Rafael J. Wysocki <rafael@xxxxxxxxxx> Cc: Rob Herring (Arm) <robh@xxxxxxxxxx> Cc: Samuel Holland <samuel.holland@xxxxxxxxxx> Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx> Cc: Will Deacon <will@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- arch/loongarch/kernel/numa.c | 18 ----------------- arch/mips/loongson64/numa.c | 16 +-------------- arch/powerpc/mm/numa.c | 20 ------------------- arch/sh/mm/init.c | 7 ------ arch/sparc/mm/init_64.c | 9 +------- arch/x86/mm/numa.c | 34 --------------------------------- drivers/base/arch_numa.c | 21 -------------------- include/linux/numa.h | 2 + mm/numa.c | 27 ++++++++++++++++++++++++++ 9 files changed, 37 insertions(+), 117 deletions(-) --- a/arch/loongarch/kernel/numa.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/arch/loongarch/kernel/numa.c @@ -187,24 +187,6 @@ int __init numa_add_memblk(int nid, u64 return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -static void __init alloc_node_data(int nid) -{ - void *nd; - unsigned long nd_pa; - size_t nd_sz = roundup(sizeof(pg_data_t), PAGE_SIZE); - - nd_pa = memblock_phys_alloc_try_nid(nd_sz, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu Byte for node_data (initial node: %d)\n", nd_sz, nid); - return; - } - - nd = __va(nd_pa); - - node_data[nid] = nd; - memset(nd, 0, sizeof(pg_data_t)); -} - static void __init node_mem_init(unsigned int node) { unsigned long start_pfn, end_pfn; --- a/arch/mips/loongson64/numa.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/arch/mips/loongson64/numa.c @@ -81,12 +81,8 @@ static void __init init_topology_matrix( static void __init node_mem_init(unsigned int node) { - struct pglist_data *nd; unsigned long node_addrspace_offset; unsigned long start_pfn, end_pfn; - unsigned long nd_pa; - int tnid; - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); node_addrspace_offset = nid_to_addrbase(node); pr_info("Node%d's addrspace_offset is 0x%lx\n", @@ -96,16 +92,8 @@ static void __init node_mem_init(unsigne pr_info("Node%d: start_pfn=0x%lx, end_pfn=0x%lx\n", node, start_pfn, end_pfn); - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, node); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, node); - nd = __va(nd_pa); - memset(nd, 0, sizeof(struct pglist_data)); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != node) - pr_info("NODE_DATA(%d) on node %d\n", node, tnid); - node_data[node] = nd; + alloc_node_data(node); + NODE_DATA(node)->node_start_pfn = start_pfn; NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn; --- a/arch/powerpc/mm/numa.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/arch/powerpc/mm/numa.c @@ -1093,27 +1093,9 @@ void __init dump_numa_cpu_topology(void) static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) { u64 spanned_pages = end_pfn - start_pfn; - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); - u64 nd_pa; - void *nd; - int tnid; - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, nid); + alloc_node_data(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 = spanned_pages; --- a/arch/sh/mm/init.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/arch/sh/mm/init.c @@ -212,12 +212,7 @@ void __init allocate_pgdat(unsigned int get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #ifdef CONFIG_NUMA - NODE_DATA(nid) = memblock_alloc_try_nid( - sizeof(struct pglist_data), - SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, - MEMBLOCK_ALLOC_ACCESSIBLE, nid); - if (!NODE_DATA(nid)) - panic("Can't allocate pgdat for node %d\n", nid); + alloc_node_data(nid); #endif NODE_DATA(nid)->node_start_pfn = start_pfn; --- a/arch/sparc/mm/init_64.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/arch/sparc/mm/init_64.c @@ -1075,14 +1075,9 @@ static void __init allocate_node_data(in { struct pglist_data *p; unsigned long start_pfn, end_pfn; -#ifdef CONFIG_NUMA - NODE_DATA(nid) = memblock_alloc_node(sizeof(struct pglist_data), - SMP_CACHE_BYTES, nid); - if (!NODE_DATA(nid)) { - prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); - prom_halt(); - } +#ifdef CONFIG_NUMA + alloc_node_data(nid); NODE_DATA(nid)->node_id = nid; #endif --- a/arch/x86/mm/numa.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/arch/x86/mm/numa.c @@ -191,39 +191,6 @@ int __init numa_add_memblk(int nid, u64 return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -/* Allocate NODE_DATA for a node on the local memory */ -static void __init alloc_node_data(int nid) -{ - const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - u64 nd_pa; - void *nd; - int tnid; - - /* - * Allocate node data. Try node-local memory and then any node. - * Never allocate in DMA zone. - */ - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", - nd_size, nid); - return; - } - nd = __va(nd_pa); - - /* report and initialize */ - printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - - node_set_online(nid); -} - /** * numa_cleanup_meminfo - Cleanup a numa_meminfo * @mi: numa_meminfo to clean up @@ -571,6 +538,7 @@ static int __init numa_register_memblks( continue; alloc_node_data(nid); + node_set_online(nid); } /* Dump memblock with node info and return. */ --- a/drivers/base/arch_numa.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/drivers/base/arch_numa.c @@ -216,30 +216,11 @@ int __init numa_add_memblk(int nid, u64 */ 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; - if (start_pfn >= end_pfn) pr_info("Initmem setup node %d [<memory-less node>]\n", nid); - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, 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); + alloc_node_data(nid); - 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; --- a/include/linux/numa.h~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/include/linux/numa.h @@ -33,6 +33,8 @@ static inline bool numa_valid_node(int n extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) +void __init alloc_node_data(int nid); + /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); --- a/mm/numa.c~arch-mm-pull-out-allocation-of-node_data-to-generic-code +++ a/mm/numa.c @@ -1,11 +1,38 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/memblock.h> #include <linux/printk.h> #include <linux/numa.h> struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(node_data); +/* Allocate NODE_DATA for a node on the local memory */ +void __init alloc_node_data(int nid) +{ + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); + u64 nd_pa; + void *nd; + int tnid; + + /* Allocate node data. Try node-local memory and then any node. */ + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) + panic("Cannot allocate %zu bytes for node %d data\n", + nd_size, nid); + nd = __va(nd_pa); + + /* report and initialize */ + pr_info("NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, + 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)); +} + /* Stub functions: */ #ifndef memory_add_physaddr_to_nid _ Patches currently in -mm which might be from rppt@xxxxxxxxxx are mm-move-kernel-numac-to-mm.patch mips-sgi-ip27-make-node_data-the-same-as-on-all-other-architectures.patch mips-sgi-ip27-ensure-node_possible_map-only-contains-valid-nodes.patch mips-sgi-ip27-drop-have_arch_nodedata_extension.patch mips-loongson64-rename-__node_data-to-node_data.patch mips-loongson64-drop-have_arch_nodedata_extension.patch mm-drop-config_have_arch_nodedata_extension.patch arch-mm-move-definition-of-node_data-to-generic-code.patch arch-mm-pull-out-allocation-of-node_data-to-generic-code.patch x86-numa-simplify-numa_distance-allocation.patch x86-numa-use-get_pfn_range_for_nid-to-verify-that-node-spans-memory.patch x86-numa-move-fake_node_-defines-to-numa_emu.patch x86-numa_emu-simplify-allocation-of-phys_dist.patch x86-numa_emu-split-__apicid_to_node-update-to-a-helper-function.patch x86-numa_emu-use-a-helper-function-to-get-max_dma32_pfn.patch x86-numa-numa_addremove_cpu-make-cpu-parameter-unsigned.patch mm-introduce-numa_memblks.patch mm-move-numa_distance-and-related-code-from-x86-to-numa_memblks.patch mm-introduce-numa_emulation.patch mm-numa_memblks-introduce-numa_memblks_init.patch mm-numa_memblks-make-several-functions-and-variables-static.patch mm-numa_memblks-use-memblock_startend_of_dram-when-sanitizing-meminfo.patch of-numa-return-einval-when-no-numa-node-id-is-found.patch arch_numa-switch-over-to-numa_memblks.patch mm-make-range-to-target_node-lookup-facility-a-part-of-numa_memblks.patch docs-move-numa=fake-description-to-kernel-parameterstxt.patch