arch, mm: pull out allocation of NODE_DATA to generic code

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/20240807064110.1003856-10-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Zi Yan <ziy@nvidia.com> # for x86_64 and arm64
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> [arm64 + CXL via QEMU]
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Rob Herring (Arm) <robh@kernel.org>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/loongarch/kernel/numa.c

@@ -187,24 +187,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	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;

arch/mips/loongson64/numa.c

@@ -81,12 +81,8 @@ static void __init init_topology_matrix(void)
 
 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(unsigned int node)
 	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;
 

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);
-
-	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));
+
+	alloc_node_data(nid);
+
 	NODE_DATA(nid)->node_id = nid;
 	NODE_DATA(nid)->node_start_pfn = start_pfn;
 	NODE_DATA(nid)->node_spanned_pages = spanned_pages;

arch/sh/mm/init.c

@@ -212,12 +212,7 @@ void __init allocate_pgdat(unsigned int nid)
 	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;

arch/sparc/mm/init_64.c

@@ -1075,14 +1075,9 @@ static void __init allocate_node_data(int nid)
 {
 	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

arch/x86/mm/numa.c

@@ -191,39 +191,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	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(struct numa_meminfo *mi)
 			continue;
 
 		alloc_node_data(nid);
+		node_set_online(nid);
 	}
 
 	/* Dump memblock with node info and return. */

drivers/base/arch_numa.c

@@ -216,30 +216,11 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
  */
 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;

include/linux/numa.h

@@ -33,6 +33,7 @@ static inline bool numa_valid_node(int nid)
 extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)	(node_data[nid])
 
+void __init alloc_node_data(int nid);
 void __init alloc_offline_node_data(int nid);
 
 /* Generic implementation available */

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));
+}
+
 void __init alloc_offline_node_data(int nid)
 {
 	pg_data_t *pgdat;