summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHuang Shijie <shijie@os.amperecomputing.com>2024-01-26 09:44:51 +0300
committerAndrew Morton <akpm@linux-foundation.org>2024-04-26 07:07:03 +0300
commitf9899c028151468d8c4af0bcbb3d5e87619b0973 (patch)
tree7cbea05d8d8125b809fe324457339e013e80baf0
parent4d9784c00a15631b68a5d95be907aa308f269551 (diff)
downloadlinux-f9899c028151468d8c4af0bcbb3d5e87619b0973.tar.xz
NUMA: early use of cpu_to_node() returns 0 instead of the correct node id
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@os.amperecomputing.com Signed-off-by: Huang Shijie <shijie@os.amperecomputing.com> Acked-by: Palmer Dabbelt <palmer@rivosinc.com> [RISC-V] Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jiaxun Yang <jiaxun.yang@flygoat.com> Cc: Josh Poimboeuf <jpoimboe@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Kelley (LINUX) <mikelley@microsoft.com> Cc: "Mike Rapoport (IBM)" <rppt@kernel.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Valentin Schneider <vschneid@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Cc: Yury Norov <yury.norov@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--init/main.c14
1 files changed, 14 insertions, 0 deletions
diff --git a/init/main.c b/init/main.c
index 6b4b656cef1d..0aecd2839c1f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -882,6 +882,19 @@ static void __init print_unknown_bootoptions(void)
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);