Re: [PATCH] memblock: update numa node of memblk reserved type

[Anshuman Khandual]

On 5/23/23 17:27, Kefeng Wang wrote:
> The numa node of memblk reserved type is wrong, it could update
> according to the numa node information from memblk memory type,
> let's fix it.

Indeed it's wrong at present and can be verified from sysfs file
(/sys/kernel/debug/memblock/reserved) accessed in user space.

> 
> Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
> ---
>  mm/memblock.c | 25 +++++++++++++++++++++++++
>  1 file changed, 25 insertions(+)
> 
> diff --git a/mm/memblock.c b/mm/memblock.c
> index a50447d970ef..45a0781cda31 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -1922,6 +1922,28 @@ phys_addr_t __init_memblock memblock_get_current_limit(void)
>  	return memblock.current_limit;
>  }
>  
> +static void __init_memblock memblock_reserved_update_node(void)
> +{
> +	struct memblock_region *rgn;
> +	phys_addr_t base, end, size;
> +	int ret;
> +
> +	if (!IS_ENABLED(CONFIG_NUMA))
> +		return;
> +
> +	for_each_mem_region(rgn) {
> +		base = rgn->base;
> +		size = rgn->size;
> +		end = base + size - 1;
> +
> +		ret = memblock_set_node(base, size, &memblock.reserved,
> +					memblock_get_region_node(rgn));
> +		if (ret)
> +			pr_err("memblock: Failed to update reserved [%pa-%pa] node",
> +			       &base, &end);
> +	}
> +}
> +
>  static void __init_memblock memblock_dump(struct memblock_type *type)
>  {
>  	phys_addr_t base, end, size;
> @@ -1955,6 +1977,7 @@ static void __init_memblock __memblock_dump_all(void)
>  		&memblock.memory.total_size,
>  		&memblock.reserved.total_size);
>  
> +	memblock_reserved_update_node();

__memblock_dump_all() gets called only when memblock_debug is enabled.
This helper should be called directly inside memblock_dump_all() right
at the beginning, regardless of memblock_debug.

diff --git a/mm/memblock.c b/mm/memblock.c
index 804fae92d56f..008c4e86d7f3 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1954,7 +1954,6 @@ static void __init_memblock __memblock_dump_all(void)
                &memblock.memory.total_size,
                &memblock.reserved.total_size);
 
-       memblock_reserved_update_node();
        memblock_dump(&memblock.memory);
        memblock_dump(&memblock.reserved);
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
@@ -1964,6 +1963,8 @@ static void __init_memblock __memblock_dump_all(void)
 
 void __init_memblock memblock_dump_all(void)
 {
+       memblock_reserved_update_node();
+
        if (memblock_debug)
                __memblock_dump_all();
 }

>  	memblock_dump(&memblock.memory);
>  	memblock_dump(&memblock.reserved);
>  #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
> @@ -2196,6 +2219,8 @@ static int memblock_debug_show(struct seq_file *m, void *private)
>  	unsigned int count = ARRAY_SIZE(flagname);
>  	phys_addr_t end;
>  
> +	memblock_reserved_update_node();
> +

This is redundant, should be dropped. Reserved memblock ranges need not
be scanned, each time the sysfs file is accessed from user space.

>  	for (i = 0; i < type->cnt; i++) {
>  		reg = &type->regions[i];
>  		end = reg->base + reg->size - 1;