The quilt patch titled
Subject: NUMA: early use of cpu_to_node() returns 0 instead of the correct node id
has been removed from the -mm tree. Its filename was
numa-early-use-of-cpu_to_node-returns-0-instead-of-the-correct-node-id.patch
This patch was dropped because it was merged into the mm-nonmm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Huang Shijie <shijie@xxxxxxxxxxxxxxxxxxxxxx>
Subject: NUMA: early use of cpu_to_node() returns 0 instead of the correct node id
Date: Fri, 26 Jan 2024 14:44:51 +0800
During the kernel booting, the generic cpu_to_node() is called too early
in arm64, powerpc and riscv when CONFIG_NUMA is enabled.
There are at least four places in the common code where
the generic cpu_to_node() is called before it is initialized:
1.) early_trace_init() in kernel/trace/trace.c
2.) sched_init() in kernel/sched/core.c
3.) init_sched_fair_class() in kernel/sched/fair.c
4.) workqueue_init_early() in kernel/workqueue.c
This will harm performance since there is an increase in off node
accesses.
In order to fix the bug, the patch introduces early_numa_node_init() which
is called after smp_prepare_boot_cpu() in start_kernel.
early_numa_node_init will initialize the "numa_node" as soon as the
early_cpu_to_node() is ready, before the cpu_to_node() is called at the
first time.
Link: https://lkml.kernel.org/r/20240126064451.5465-1-shijie@xxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Huang Shijie <shijie@xxxxxxxxxxxxxxxxxxxxxx>
Acked-by: Palmer Dabbelt <palmer@xxxxxxxxxxxx> [RISC-V]
Cc: Albert Ou <aou@xxxxxxxxxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Huacai Chen <chenhuacai@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jakub Kicinski <kuba@xxxxxxxxxx>
Cc: Jiaxun Yang <jiaxun.yang@xxxxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Michael Kelley (LINUX) <mikelley@xxxxxxxxxxxxx>
Cc: "Mike Rapoport (IBM)" <rppt@xxxxxxxxxx>
Cc: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>
Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>
Cc: Rafael J. Wysocki <rafael@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yury Norov <yury.norov@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
init/main.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
--- a/init/main.c~numa-early-use-of-cpu_to_node-returns-0-instead-of-the-correct-node-id
+++ a/init/main.c
@@ -882,6 +882,19 @@ static void __init print_unknown_bootopt
memblock_free(unknown_options, len);
}
+static void __init early_numa_node_init(void)
+{
+#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
+#ifndef cpu_to_node
+ int cpu;
+
+ /* The early_cpu_to_node() should be ready here. */
+ for_each_possible_cpu(cpu)
+ set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
+#endif
+#endif
+}
+
asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector
void start_kernel(void)
{
@@ -912,6 +925,7 @@ void start_kernel(void)
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
+ early_numa_node_init();
boot_cpu_hotplug_init();
pr_notice("Kernel command line: %s\n", saved_command_line);
_
Patches currently in -mm which might be from shijie@xxxxxxxxxxxxxxxxxxxxxx are
