This is a note to let you know that I've just added the patch titled
arm64: irq: set the correct node for VMAP stack
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
arm64-irq-set-the-correct-node-for-vmap-stack.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit e1572a3f8ae24afd9713ea4d7f02f99e05a162fa
Author: Huang Shijie <shijie@xxxxxxxxxxxxxxxxxxxxxx>
Date: Fri Nov 24 11:15:13 2023 +0800
arm64: irq: set the correct node for VMAP stack
[ Upstream commit 75b5e0bf90bffaca4b1f19114065dc59f5cc161f ]
In current code, init_irq_stacks() will call cpu_to_node().
The cpu_to_node() depends on percpu "numa_node" which is initialized in:
arch_call_rest_init() --> rest_init() -- kernel_init()
--> kernel_init_freeable() --> smp_prepare_cpus()
But init_irq_stacks() is called in init_IRQ() which is before
arch_call_rest_init().
So in init_irq_stacks(), the cpu_to_node() does not work, it
always return 0. In NUMA, it makes the node 1 cpu accesses the IRQ stack which
is in the node 0.
This patch fixes it by:
1.) export the early_cpu_to_node(), and use it in the init_irq_stacks().
2.) change init_irq_stacks() to __init function.
Reviewed-by: Catalin Marinas <catalin.marinas@xxxxxxx>
Signed-off-by: Huang Shijie <shijie@xxxxxxxxxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20231124031513.81548-1-shijie@xxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index bda49430c9ea..dab45f19df49 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -19,6 +19,7 @@
#include <linux/kprobes.h>
#include <linux/scs.h>
#include <linux/seq_file.h>
+#include <asm/numa.h>
#include <linux/vmalloc.h>
#include <asm/daifflags.h>
#include <asm/vmap_stack.h>
@@ -48,13 +49,13 @@ static void init_irq_scs(void)
}
#ifdef CONFIG_VMAP_STACK
-static void init_irq_stacks(void)
+static void __init init_irq_stacks(void)
{
int cpu;
unsigned long *p;
for_each_possible_cpu(cpu) {
- p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
+ p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu));
per_cpu(irq_stack_ptr, cpu) = p;
}
}
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index 00fb4120a5b3..bce0902dccb4 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
-static int __init early_cpu_to_node(int cpu)
+int __init early_cpu_to_node(int cpu)
{
return cpu_to_node_map[cpu];
}
diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h
index 1a3ad6d29833..c32e0cf23c90 100644
--- a/include/asm-generic/numa.h
+++ b/include/asm-generic/numa.h
@@ -35,6 +35,7 @@ int __init numa_add_memblk(int nodeid, u64 start, u64 end);
void __init numa_set_distance(int from, int to, int distance);
void __init numa_free_distance(void);
void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+int __init early_cpu_to_node(int cpu);
void numa_store_cpu_info(unsigned int cpu);
void numa_add_cpu(unsigned int cpu);
void numa_remove_cpu(unsigned int cpu);
@@ -46,6 +47,7 @@ static inline void numa_add_cpu(unsigned int cpu) { }
static inline void numa_remove_cpu(unsigned int cpu) { }
static inline void arch_numa_init(void) { }
static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+static inline int early_cpu_to_node(int cpu) { return 0; }
#endif /* CONFIG_NUMA */
