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>,
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>,
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>,
Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
Thomas Gleixner <tglx@linutronix.de>,
Vasily Gorbik <gor@linux.ibm.com>, Will Deacon <will@kernel.org>,
linux-arm-kernel@lists.infradead.org, loongarch@lists.linux.dev,
linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org,
linux-sh@vger.kernel.org, sparclinux@vger.kernel.org,
linux-acpi@vger.kernel.org, linux-cxl@vger.kernel.org,
nvdimm@lists.linux.dev, devicetree@vger.kernel.org,
linux-arch@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Subject: [PATCH 15/17] mm: make numa_memblks more self-contained
Date: Tue, 16 Jul 2024 14:13:44 +0300 [thread overview]
Message-ID: <20240716111346.3676969-16-rppt@kernel.org> (raw)
In-Reply-To: <20240716111346.3676969-1-rppt@kernel.org>
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Introduce numa_memblks_init() and move some code around to avoid several
global variables in numa_memblks.
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
arch/x86/mm/numa.c | 53 ++++---------------------
include/linux/numa_memblks.h | 9 +----
mm/numa_memblks.c | 77 +++++++++++++++++++++++++++---------
3 files changed, 68 insertions(+), 71 deletions(-)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 3848e68d771a..16bc703c9272 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -115,30 +115,19 @@ void __init setup_node_to_cpumask_map(void)
pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
}
-static int __init numa_register_memblks(struct numa_meminfo *mi)
+static int __init numa_register_nodes(void)
{
- int i, nid, err;
-
- err = numa_register_meminfo(mi);
- if (err)
- return err;
+ int nid;
if (!memblock_validate_numa_coverage(SZ_1M))
return -EINVAL;
/* Finally register nodes. */
for_each_node_mask(nid, node_possible_map) {
- u64 start = PFN_PHYS(max_pfn);
- u64 end = 0;
-
- for (i = 0; i < mi->nr_blks; i++) {
- if (nid != mi->blk[i].nid)
- continue;
- start = min(mi->blk[i].start, start);
- end = max(mi->blk[i].end, end);
- }
+ unsigned long start_pfn, end_pfn;
- if (start >= end)
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ if (start_pfn >= end_pfn)
continue;
alloc_node_data(nid);
@@ -178,39 +167,11 @@ static int __init numa_init(int (*init_func)(void))
for (i = 0; i < MAX_LOCAL_APIC; i++)
set_apicid_to_node(i, NUMA_NO_NODE);
- nodes_clear(numa_nodes_parsed);
- nodes_clear(node_possible_map);
- nodes_clear(node_online_map);
- memset(&numa_meminfo, 0, sizeof(numa_meminfo));
- WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
- NUMA_NO_NODE));
- WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
- NUMA_NO_NODE));
- /* In case that parsing SRAT failed. */
- WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
- numa_reset_distance();
-
- ret = init_func();
- if (ret < 0)
- return ret;
-
- /*
- * We reset memblock back to the top-down direction
- * here because if we configured ACPI_NUMA, we have
- * parsed SRAT in init_func(). It is ok to have the
- * reset here even if we did't configure ACPI_NUMA
- * or acpi numa init fails and fallbacks to dummy
- * numa init.
- */
- memblock_set_bottom_up(false);
-
- ret = numa_cleanup_meminfo(&numa_meminfo);
+ ret = numa_memblks_init(init_func, /* memblock_force_top_down */ true);
if (ret < 0)
return ret;
- numa_emulation(&numa_meminfo, numa_distance_cnt);
-
- ret = numa_register_memblks(&numa_meminfo);
+ ret = numa_register_nodes();
if (ret < 0)
return ret;
diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h
index f81f98678074..5c6e12ad0b7a 100644
--- a/include/linux/numa_memblks.h
+++ b/include/linux/numa_memblks.h
@@ -7,7 +7,6 @@
#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2)
-extern int numa_distance_cnt;
void __init numa_set_distance(int from, int to, int distance);
void __init numa_reset_distance(void);
@@ -22,17 +21,13 @@ struct numa_meminfo {
struct numa_memblk blk[NR_NODE_MEMBLKS];
};
-extern struct numa_meminfo numa_meminfo __initdata_or_meminfo;
-extern struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo;
-
int __init numa_add_memblk(int nodeid, u64 start, u64 end);
void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi);
int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
-int __init numa_register_meminfo(struct numa_meminfo *mi);
-void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
- const struct numa_meminfo *mi);
+int __init numa_memblks_init(int (*init_func)(void),
+ bool memblock_force_top_down);
#ifdef CONFIG_NUMA_EMU
int numa_emu_cmdline(char *str);
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index e0039549aaac..640f3a3ce0ee 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -7,13 +7,27 @@
#include <linux/numa.h>
#include <linux/numa_memblks.h>
-int numa_distance_cnt;
+static int numa_distance_cnt;
static u8 *numa_distance;
nodemask_t numa_nodes_parsed __initdata;
-struct numa_meminfo numa_meminfo __initdata_or_meminfo;
-struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo;
+static struct numa_meminfo numa_meminfo __initdata_or_meminfo;
+static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo;
+
+/*
+ * Set nodes, which have memory in @mi, in *@nodemask.
+ */
+static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
+ const struct numa_meminfo *mi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
+ if (mi->blk[i].start != mi->blk[i].end &&
+ mi->blk[i].nid != NUMA_NO_NODE)
+ node_set(mi->blk[i].nid, *nodemask);
+}
/**
* numa_reset_distance - Reset NUMA distance table
@@ -287,20 +301,6 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
return 0;
}
-/*
- * Set nodes, which have memory in @mi, in *@nodemask.
- */
-void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
- const struct numa_meminfo *mi)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
- if (mi->blk[i].start != mi->blk[i].end &&
- mi->blk[i].nid != NUMA_NO_NODE)
- node_set(mi->blk[i].nid, *nodemask);
-}
-
/*
* Mark all currently memblock-reserved physical memory (which covers the
* kernel's own memory ranges) as hot-unswappable.
@@ -368,7 +368,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
}
}
-int __init numa_register_meminfo(struct numa_meminfo *mi)
+static int __init numa_register_meminfo(struct numa_meminfo *mi)
{
int i;
@@ -412,6 +412,47 @@ int __init numa_register_meminfo(struct numa_meminfo *mi)
return 0;
}
+int __init numa_memblks_init(int (*init_func)(void),
+ bool memblock_force_top_down)
+{
+ int ret;
+
+ nodes_clear(numa_nodes_parsed);
+ nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
+ memset(&numa_meminfo, 0, sizeof(numa_meminfo));
+ WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
+ NUMA_NO_NODE));
+ WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
+ NUMA_NO_NODE));
+ /* In case that parsing SRAT failed. */
+ WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
+ numa_reset_distance();
+
+ ret = init_func();
+ if (ret < 0)
+ return ret;
+
+ /*
+ * We reset memblock back to the top-down direction
+ * here because if we configured ACPI_NUMA, we have
+ * parsed SRAT in init_func(). It is ok to have the
+ * reset here even if we did't configure ACPI_NUMA
+ * or acpi numa init fails and fallbacks to dummy
+ * numa init.
+ */
+ if (memblock_force_top_down)
+ memblock_set_bottom_up(false);
+
+ ret = numa_cleanup_meminfo(&numa_meminfo);
+ if (ret < 0)
+ return ret;
+
+ numa_emulation(&numa_meminfo, numa_distance_cnt);
+
+ return numa_register_meminfo(&numa_meminfo);
+}
+
static int __init cmp_memblk(const void *a, const void *b)
{
const struct numa_memblk *ma = *(const struct numa_memblk **)a;
--
2.43.0
next prev parent reply other threads:[~2024-07-16 11:16 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-16 11:13 [PATCH 00/17] mm: introduce numa_memblks Mike Rapoport
2024-07-16 11:13 ` [PATCH 01/17] mm: move kernel/numa.c to mm/ Mike Rapoport
2024-07-17 14:35 ` David Hildenbrand
2024-07-19 13:55 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 02/17] MIPS: sgi-ip27: make NODE_DATA() the same as on all other architectures Mike Rapoport
2024-07-17 14:32 ` David Hildenbrand
2024-07-19 14:38 ` Jonathan Cameron
2024-07-22 7:34 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 03/17] MIPS: loongson64: rename __node_data to node_data Mike Rapoport
2024-07-16 13:07 ` Jiaxun Yang
2024-07-17 14:33 ` David Hildenbrand
2024-07-19 15:27 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 04/17] arch, mm: move definition of node_data to generic code Mike Rapoport
2024-07-17 14:35 ` David Hildenbrand
2024-07-19 15:39 ` Jonathan Cameron
2024-07-23 0:15 ` Davidlohr Bueso
2024-07-16 11:13 ` [PATCH 05/17] arch, mm: pull out allocation of NODE_DATA " Mike Rapoport
2024-07-17 14:42 ` David Hildenbrand
2024-07-18 7:02 ` Mike Rapoport
2024-07-19 15:07 ` David Hildenbrand
2024-07-19 15:34 ` Mike Rapoport
2024-07-19 15:46 ` David Hildenbrand
2024-07-19 15:51 ` Jonathan Cameron
2024-07-19 16:07 ` David Hildenbrand
2024-07-20 10:24 ` Mike Rapoport
2024-07-19 16:11 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 06/17] x86/numa: simplify numa_distance allocation Mike Rapoport
2024-07-19 16:28 ` Jonathan Cameron
2024-07-22 7:51 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 07/17] x86/numa: move FAKE_NODE_* defines to numa_emu Mike Rapoport
2024-07-19 16:30 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 08/17] x86/numa_emu: simplify allocation of phys_dist Mike Rapoport
2024-07-19 16:38 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 09/17] x86/numa_emu: split __apicid_to_node update to a helper function Mike Rapoport
2024-07-19 16:47 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 10/17] x86/numa_emu: use a helper function to get MAX_DMA32_PFN Mike Rapoport
2024-07-19 16:50 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 11/17] x86/numa: numa_{add,remove}_cpu: make cpu parameter unsigned Mike Rapoport
2024-07-19 16:57 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 12/17] mm: introduce numa_memblks Mike Rapoport
2024-07-19 18:16 ` Jonathan Cameron
2024-07-22 8:03 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 13/17] mm: move numa_distance and related code from x86 to numa_memblks Mike Rapoport
2024-07-18 21:46 ` Samuel Holland
2024-07-19 5:55 ` Mike Rapoport
2024-07-19 17:48 ` Jonathan Cameron
2024-07-20 12:25 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 14/17] mm: introduce numa_emulation Mike Rapoport
2024-07-19 16:03 ` Zi Yan
2024-07-20 12:09 ` Mike Rapoport
2024-07-16 11:13 ` Mike Rapoport [this message]
2024-07-19 18:07 ` [PATCH 15/17] mm: make numa_memblks more self-contained Jonathan Cameron
2024-07-20 12:32 ` Mike Rapoport
2024-07-22 8:05 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 16/17] arch_numa: switch over to numa_memblks Mike Rapoport
2024-07-19 18:16 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 17/17] mm: make range-to-target_node lookup facility a part of numa_memblks Mike Rapoport
2024-07-19 18:19 ` Jonathan Cameron
2024-07-19 13:33 ` [PATCH 00/17] mm: introduce numa_memblks Jonathan Cameron
2024-07-22 8:08 ` 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=20240716111346.3676969-16-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=dan.j.williams@intel.com \
--cc=dave.hansen@linux.intel.com \
--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-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=sparclinux@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=tsbogend@alpha.franken.de \
--cc=will@kernel.org \
--cc=x86@kernel.org \
/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).