Re: [PATCH v8 2/3] mm/memory_hotplug: split memmap_on_memory requests across memblocks

[David Hildenbrand <david@redhat.com>]

On 01.11.23 23:51, Vishal Verma wrote:
> The MHP_MEMMAP_ON_MEMORY flag for hotplugged memory is restricted to
> 'memblock_size' chunks of memory being added. Adding a larger span of
> memory precludes memmap_on_memory semantics.
> 
> For users of hotplug such as kmem, large amounts of memory might get
> added from the CXL subsystem. In some cases, this amount may exceed the
> available 'main memory' to store the memmap for the memory being added.
> In this case, it is useful to have a way to place the memmap on the
> memory being added, even if it means splitting the addition into
> memblock-sized chunks.
> 
> Change add_memory_resource() to loop over memblock-sized chunks of
> memory if caller requested memmap_on_memory, and if other conditions for
> it are met. Teach try_remove_memory() to also expect that a memory
> range being removed might have been split up into memblock sized chunks,
> and to loop through those as needed.
> 
> This does preclude being able to use PUD mappings in the direct map; a
> proposal to how this could be optimized in the future is laid out
> here[1].
> 
> [1]: https://lore.kernel.org/linux-mm/b6753402-2de9-25b2-36e9-eacd49752b19@redhat.com/
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Michal Hocko <mhocko@suse.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Dan Williams <dan.j.williams@intel.com>
> Cc: Dave Jiang <dave.jiang@intel.com>
> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> Cc: Huang Ying <ying.huang@intel.com>
> Suggested-by: David Hildenbrand <david@redhat.com>
> Reviewed-by: Dan Williams <dan.j.williams@intel.com>
> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
> ---
>   mm/memory_hotplug.c | 213 ++++++++++++++++++++++++++++++++++------------------
>   1 file changed, 138 insertions(+), 75 deletions(-)
> 
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 6be7de9efa55..d242e49d7f7b 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1380,6 +1380,84 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>   	return arch_supports_memmap_on_memory(vmemmap_size);
>   }
>   
> +static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size)
> +{
> +	unsigned long memblock_size = memory_block_size_bytes();
> +	u64 cur_start;
> +
> +	/*
> +	 * For memmap_on_memory, the altmaps were added on a per-memblock
> +	 * basis; we have to process each individual memory block.
> +	 */
> +	for (cur_start = start; cur_start < start + size;
> +	     cur_start += memblock_size) {
> +		struct vmem_altmap *altmap = NULL;
> +		struct memory_block *mem;
> +
> +		mem = find_memory_block(pfn_to_section_nr(PFN_DOWN(cur_start)));
> +		WARN_ON_ONCE(!mem);
> +		if (!mem)
> +			continue;

Nit:

if (WARN_ON_ONCE(!mem))
	continue;

> +	for (cur_start = start; cur_start < start + size;
> +	     cur_start += memblock_size) {
> +		struct mhp_params params = { .pgprot =
> +						     pgprot_mhp(PAGE_KERNEL) };
> +		struct vmem_altmap mhp_altmap = {
> +			.base_pfn = PHYS_PFN(cur_start),
> +			.end_pfn = PHYS_PFN(cur_start + memblock_size - 1),
> +		};
> +
> +		mhp_altmap.free = memory_block_memmap_on_memory_pages();
> +		params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap),
> +					GFP_KERNEL);
> +		if (!params.altmap)
> +			return -ENOMEM;

As already spotted, we have to cleanup.

> +
> +		/* call arch's memory hotadd */
> +		ret = arch_add_memory(nid, cur_start, memblock_size, &params);
> +		if (ret < 0) {
> +			kfree(params.altmap);
> +			goto out;
> +		}
> +
> +		/* create memory block devices after memory was added */
> +		ret = create_memory_block_devices(cur_start, memblock_size,
> +						  params.altmap, group);
> +		if (ret) {
> +			arch_remove_memory(cur_start, memblock_size, NULL);
> +			kfree(params.altmap);
> +			goto out;
> +		}
> +	}
> +
> +	return 0;
> +out:
> +	if (ret && (cur_start != start))

Nit: I think you can drop the inner parentheses.

> @@ -2146,11 +2208,31 @@ void try_offline_node(int nid)
>   }
>   EXPORT_SYMBOL(try_offline_node);
>   
> +static int memory_blocks_have_altmaps(u64 start, u64 size)
> +{
> +	u64 num_memblocks = size / memory_block_size_bytes();
> +	u64 num_altmaps = 0;
> +
> +	if (!mhp_memmap_on_memory())
> +		return 0;
> +
> +	walk_memory_blocks(start, size, &num_altmaps,
> +			   count_memory_range_altmaps_cb);
> +
> +	if (num_altmaps == 0)
> +		return 0;
> +
> +	if (num_memblocks != num_altmaps) {
> +		WARN_ONCE(1, "Not all memblocks in range have altmaps");

Nit:

if (WARN_ON_ONCE(num_memblocks != num_altmaps))
	return -EINVAL;

Should be sufficient.

[...]

>   	/* remove memmap entry */
>   	firmware_map_remove(start, start + size, "System RAM");
>   
> -	/*
> -	 * Memory block device removal under the device_hotplug_lock is
> -	 * a barrier against racing online attempts.
> -	 */
> -	remove_memory_block_devices(start, size);
> -
>   	mem_hotplug_begin();
>   
> -	arch_remove_memory(start, size, altmap);
> -
> -	/* Verify that all vmemmap pages have actually been freed. */
> -	if (altmap) {
> -		WARN(altmap->alloc, "Altmap not fully unmapped");
> -		kfree(altmap);
> +	rc = memory_blocks_have_altmaps(start, size);
> +	if (rc < 0) {
> +		goto err;

Nit: Maybe better to just

if (rc < 0) {
	mem_hotplug_done();
	return rc
} else ...

And avoid the error label below. Makes the code easier to read.

> +	} else if (rc == 0) {

Nit: else if (!rc)



With the cleanup fixed,

Acked-by: David Hildenbrand <david@redhat.com>

-- 
Cheers,

David / dhildenb