Re: [PATCH 15/17] mm: make numa_memblks more self-contained

[Jonathan Cameron <Jonathan.Cameron@Huawei.com>]

On Tue, 16 Jul 2024 14:13:44 +0300
Mike Rapoport <rppt@kernel.org> wrote:

> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> Introduce numa_memblks_init() and move some code around to avoid several
> global variables in numa_memblks.

Hi Mike,

Adding the effectively always on memblock_force_top_down
deserves a comment on why. I assume because you are going to do
something with it later? 

There also seems to be more going on in here such as the change to
get_pfn_range_for_nid()  Perhaps break this up so each
change can have an explanation. 


> 
> 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);

It's not immediately obvious to me that this code is equivalent so I'd
prefer it in a separate patch with some description of why
it is a valid change.

> +		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);
The comment in parameter list seems unnecessary.
Maybe add a comment above the call instead if need to call that out?

>  	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/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>
>  

> +/*
> + * 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);
> +}

The code move doesn't have an obvious purpose. Maybe call that
out in the patch description if it is needed for a future patch.
Or do it in two goes so first just adds the static, 2nd shuffles
the code.

>  
>  /**
>   * 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;