From: Mike Rapoport <rppt@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Alexander Gordeev <agordeev@linux.ibm.com>,
Andreas Larsson <andreas@gaisler.com>,
Andrew Morton <akpm@linux-foundation.org>,
Arnd Bergmann <arnd@arndb.de>, Borislav Petkov <bp@alien8.de>,
Catalin Marinas <catalin.marinas@arm.com>,
Christophe Leroy <christophe.leroy@csgroup.eu>,
Dan Williams <dan.j.williams@intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
David Hildenbrand <david@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Davidlohr Bueso <dave@stgolabs.net>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Heiko Carstens <hca@linux.ibm.com>,
Huacai Chen <chenhuacai@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Jiaxun Yang <jiaxun.yang@flygoat.com>,
John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>,
Jonathan Cameron <jonathan.cameron@huawei.com>,
Jonathan Corbet <corbet@lwn.net>,
Michael Ellerman <mpe@ellerman.id.au>,
Mike Rapoport <rppt@kernel.org>,
Palmer Dabbelt <palmer@dabbelt.com>,
"Rafael J. Wysocki" <rafael@kernel.org>,
Rob Herring <robh@kernel.org>,
Samuel Holland <samuel.holland@sifive.com>,
Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
Thomas Gleixner <tglx@linutronix.de>,
Vasily Gorbik <gor@linux.ibm.com>, Will Deacon <will@kernel.org>,
Zi Yan <ziy@nvidia.com>,
devicetree@vger.kernel.org, linux-acpi@vger.kernel.org,
linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
linux-cxl@vger.kernel.org, linux-doc@vger.kernel.org,
linux-mips@vger.kernel.org, linux-mm@kvack.org,
linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org,
linux-sh@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
loongarch@lists.linux.dev, nvdimm@lists.linux.dev,
sparclinux@vger.kernel.org, x86@kernel.org,
Jonathan Cameron <Jonathan.Cameron@huawei.com>
Subject: [PATCH v4 09/26] arch, mm: pull out allocation of NODE_DATA to generic code
Date: Wed, 7 Aug 2024 09:40:53 +0300 [thread overview]
Message-ID: <20240807064110.1003856-10-rppt@kernel.org> (raw)
In-Reply-To: <20240807064110.1003856-1-rppt@kernel.org>
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
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.
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>
---
arch/loongarch/kernel/numa.c | 18 ------------------
arch/mips/loongson64/numa.c | 16 ++--------------
arch/powerpc/mm/numa.c | 24 +++---------------------
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 | 1 +
mm/numa.c | 27 +++++++++++++++++++++++++++
9 files changed, 38 insertions(+), 119 deletions(-)
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index acada671e020..84fe7f854820 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/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;
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index d56238745744..8388400d052f 100644
--- a/arch/mips/loongson64/numa.c
+++ b/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;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0744a9a2944b..3c1da08304d0 100644
--- a/arch/powerpc/mm/numa.c
+++ b/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;
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index d1fe90b2f5ff..2a88b0c9e70f 100644
--- a/arch/sh/mm/init.c
+++ b/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;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index c6c7f43cb1e8..21f8cbbd0581 100644
--- a/arch/sparc/mm/init_64.c
+++ b/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
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 7de725d6bb05..5e1dde26674b 100644
--- a/arch/x86/mm/numa.c
+++ b/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. */
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index ceac5b59bf2b..b6af7475ec44 100644
--- a/drivers/base/arch_numa.c
+++ b/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;
diff --git a/include/linux/numa.h b/include/linux/numa.h
index b41b1569781b..3567e40329eb 100644
--- a/include/linux/numa.h
+++ b/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 */
diff --git a/mm/numa.c b/mm/numa.c
index 64e1b7d2c1ee..1f1582dcdf4a 100644
--- a/mm/numa.c
+++ b/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;
--
2.43.0
next prev parent reply other threads:[~2024-08-07 6:43 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-07 6:40 [PATCH v4 00/26] mm: introduce numa_memblks Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 01/26] mm: move kernel/numa.c to mm/ Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 02/26] MIPS: sgi-ip27: make NODE_DATA() the same as on all other architectures Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 03/26] MIPS: sgi-ip27: ensure node_possible_map only contains valid nodes Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 04/26] MIPS: sgi-ip27: drop HAVE_ARCH_NODEDATA_EXTENSION Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 05/26] MIPS: loongson64: rename __node_data to node_data Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 06/26] MIPS: loongson64: drop HAVE_ARCH_NODEDATA_EXTENSION Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 07/26] arch, mm: move definition of node_data to generic code Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 08/26] mm: drop CONFIG_HAVE_ARCH_NODEDATA_EXTENSION Mike Rapoport
2024-08-07 6:40 ` Mike Rapoport [this message]
2024-08-07 6:40 ` [PATCH v4 10/26] x86/numa: simplify numa_distance allocation Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 11/26] x86/numa: use get_pfn_range_for_nid to verify that node spans memory Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 12/26] x86/numa: move FAKE_NODE_* defines to numa_emu Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 13/26] x86/numa_emu: simplify allocation of phys_dist Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 14/26] x86/numa_emu: split __apicid_to_node update to a helper function Mike Rapoport
2024-08-07 6:40 ` [PATCH v4 15/26] x86/numa_emu: use a helper function to get MAX_DMA32_PFN Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 16/26] x86/numa: numa_{add,remove}_cpu: make cpu parameter unsigned Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 17/26] mm: introduce numa_memblks Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 18/26] mm: move numa_distance and related code from x86 to numa_memblks Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 19/26] mm: introduce numa_emulation Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 20/26] mm: numa_memblks: introduce numa_memblks_init Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 21/26] mm: numa_memblks: make several functions and variables static Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 22/26] mm: numa_memblks: use memblock_{start,end}_of_DRAM() when sanitizing meminfo Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 23/26] of, numa: return -EINVAL when no numa-node-id is found Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 24/26] arch_numa: switch over to numa_memblks Mike Rapoport
2024-08-07 6:58 ` Arnd Bergmann
2024-08-07 18:18 ` Mike Rapoport
2024-08-07 18:53 ` Arnd Bergmann
2024-11-27 19:32 ` Marc Zyngier
2024-08-07 6:41 ` [PATCH v4 25/26] mm: make range-to-target_node lookup facility a part of numa_memblks Mike Rapoport
2024-08-07 6:41 ` [PATCH v4 26/26] docs: move numa=fake description to kernel-parameters.txt Mike Rapoport
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240807064110.1003856-10-rppt@kernel.org \
--to=rppt@kernel.org \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=andreas@gaisler.com \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=chenhuacai@kernel.org \
--cc=christophe.leroy@csgroup.eu \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=dave@stgolabs.net \
--cc=davem@davemloft.net \
--cc=david@redhat.com \
--cc=devicetree@vger.kernel.org \
--cc=glaubitz@physik.fu-berlin.de \
--cc=gor@linux.ibm.com \
--cc=gregkh@linuxfoundation.org \
--cc=hca@linux.ibm.com \
--cc=jiaxun.yang@flygoat.com \
--cc=jonathan.cameron@huawei.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-riscv@lists.infradead.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux-sh@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=loongarch@lists.linux.dev \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=nvdimm@lists.linux.dev \
--cc=palmer@dabbelt.com \
--cc=rafael@kernel.org \
--cc=robh@kernel.org \
--cc=samuel.holland@sifive.com \
--cc=sparclinux@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=tsbogend@alpha.franken.de \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=ziy@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).