[v6,2/3] mm/memory_hotplug: split memmap_on_memory requests across memblocks

  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 | 214 ++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 148 insertions(+), 66 deletions(-)
  

Vishal Verma <vishal.l.verma@intel.com> writes:

> 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 | 214 ++++++++++++++++++++++++++++++++++++----------------
>  1 file changed, 148 insertions(+), 66 deletions(-)
>
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 6be7de9efa55..83e5ec377aad 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1380,6 +1380,43 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>  	return arch_supports_memmap_on_memory(vmemmap_size);
>  }
>  
> +static int add_memory_create_devices(int nid, struct memory_group *group,
> +				     u64 start, u64 size, mhp_t mhp_flags)
> +{
> +	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
> +	struct vmem_altmap mhp_altmap = {
> +		.base_pfn =  PHYS_PFN(start),
> +		.end_pfn  =  PHYS_PFN(start + size - 1),
> +	};
> +	int ret;
> +
> +	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY)) {
> +		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;
> +	}
> +
> +	/* call arch's memory hotadd */
> +	ret = arch_add_memory(nid, start, size, &params);
> +	if (ret < 0)
> +		goto error;
> +
> +	/* create memory block devices after memory was added */
> +	ret = create_memory_block_devices(start, size, params.altmap, group);
> +	if (ret)
> +		goto err_bdev;
> +
> +	return 0;
> +
> +err_bdev:
> +	arch_remove_memory(start, size, NULL);
> +error:
> +	kfree(params.altmap);
> +	return ret;
> +}
> +
>  /*
>   * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
>   * and online/offline operations (triggered e.g. by sysfs).
> @@ -1388,14 +1425,10 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>   */
>  int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>  {
> -	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
> +	unsigned long memblock_size = memory_block_size_bytes();
>  	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
> -	struct vmem_altmap mhp_altmap = {
> -		.base_pfn =  PHYS_PFN(res->start),
> -		.end_pfn  =  PHYS_PFN(res->end),
> -	};
>  	struct memory_group *group = NULL;
> -	u64 start, size;
> +	u64 start, size, cur_start;
>  	bool new_node = false;
>  	int ret;
>  
> @@ -1436,28 +1469,21 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>  	/*
>  	 * Self hosted memmap array
>  	 */
> -	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
> -		if (mhp_supports_memmap_on_memory(size)) {
> -			mhp_altmap.free = memory_block_memmap_on_memory_pages();
> -			params.altmap = kmemdup(&mhp_altmap,
> -						sizeof(struct vmem_altmap),
> -						GFP_KERNEL);
> -			if (!params.altmap)
> +	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) &&
> +	    mhp_supports_memmap_on_memory(memblock_size)) {
> +		for (cur_start = start; cur_start < start + size;
> +		     cur_start += memblock_size) {
> +			ret = add_memory_create_devices(nid, group, cur_start,
> +							memblock_size,
> +							mhp_flags);
> +			if (ret)
>  				goto error;
>  		}
> -		/* fallback to not using altmap  */
> -	}
> -
> -	/* call arch's memory hotadd */
> -	ret = arch_add_memory(nid, start, size, &params);
> -	if (ret < 0)
> -		goto error_free;
> -
> -	/* create memory block devices after memory was added */
> -	ret = create_memory_block_devices(start, size, params.altmap, group);
> -	if (ret) {
> -		arch_remove_memory(start, size, NULL);
> -		goto error_free;
> +	} else {
> +		ret = add_memory_create_devices(nid, group, start, size,
> +						mhp_flags);

IIUC, if (mhp_flags & MHP_MEMMAP_ON_MEMORY) == true and
mhp_supports_memmap_on_memory(memblock_size) == false, we will go here
and allocate params.altmap in add_memory_create_devices().  If so, it
seems better to pass whether to create altmap instead of mhp_flags to
add_memory_create_devices().

--
Best Regards,
Huang, Ying

> +		if (ret)
> +			goto error;
>  	}
>  
>  	if (new_node) {

[snip]
  

On 17.10.23 07:44, 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 | 214 ++++++++++++++++++++++++++++++++++++----------------
>   1 file changed, 148 insertions(+), 66 deletions(-)
> 
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 6be7de9efa55..83e5ec377aad 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1380,6 +1380,43 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>   	return arch_supports_memmap_on_memory(vmemmap_size);
>   }
>   
> +static int add_memory_create_devices(int nid, struct memory_group *group,
> +				     u64 start, u64 size, mhp_t mhp_flags)
> +{
> +	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
> +	struct vmem_altmap mhp_altmap = {
> +		.base_pfn =  PHYS_PFN(start),
> +		.end_pfn  =  PHYS_PFN(start + size - 1),
> +	};
> +	int ret;
> +
> +	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY)) {
> +		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;
> +	}
> +
> +	/* call arch's memory hotadd */
> +	ret = arch_add_memory(nid, start, size, &params);
> +	if (ret < 0)
> +		goto error;
> +
> +	/* create memory block devices after memory was added */
> +	ret = create_memory_block_devices(start, size, params.altmap, group);
> +	if (ret)
> +		goto err_bdev;
> +
> +	return 0;
> +
> +err_bdev:
> +	arch_remove_memory(start, size, NULL);
> +error:
> +	kfree(params.altmap);
> +	return ret;
> +}
> +
>   /*
>    * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
>    * and online/offline operations (triggered e.g. by sysfs).
> @@ -1388,14 +1425,10 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>    */
>   int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>   {
> -	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
> +	unsigned long memblock_size = memory_block_size_bytes();
>   	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
> -	struct vmem_altmap mhp_altmap = {
> -		.base_pfn =  PHYS_PFN(res->start),
> -		.end_pfn  =  PHYS_PFN(res->end),
> -	};
>   	struct memory_group *group = NULL;
> -	u64 start, size;
> +	u64 start, size, cur_start;
>   	bool new_node = false;
>   	int ret;
>   
> @@ -1436,28 +1469,21 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>   	/*
>   	 * Self hosted memmap array
>   	 */
> -	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
> -		if (mhp_supports_memmap_on_memory(size)) {
> -			mhp_altmap.free = memory_block_memmap_on_memory_pages();
> -			params.altmap = kmemdup(&mhp_altmap,
> -						sizeof(struct vmem_altmap),
> -						GFP_KERNEL);
> -			if (!params.altmap)
> +	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) &&
> +	    mhp_supports_memmap_on_memory(memblock_size)) {
> +		for (cur_start = start; cur_start < start + size;
> +		     cur_start += memblock_size) {
> +			ret = add_memory_create_devices(nid, group, cur_start,
> +							memblock_size,
> +							mhp_flags);

Just like on the removal part, that function doesn't make any sense to 
be called with altmap and a bigger range.

Maybe better also move that loop into a function called 
"create_altmap_and_memory_blocks()" , to be the opposite of 
"remove_memory_blocks_and_altmaps()".

Then you can keep the existing !altmap code here in the "else" case. 
Again, similar to the removal code below.

> +			if (ret)
>   				goto error;
>   		}
> -		/* fallback to not using altmap  */
> -	}
> -
> -	/* call arch's memory hotadd */
> -	ret = arch_add_memory(nid, start, size, &params);
> -	if (ret < 0)
> -		goto error_free;
> -
> -	/* create memory block devices after memory was added */
> -	ret = create_memory_block_devices(start, size, params.altmap, group);
> -	if (ret) {
> -		arch_remove_memory(start, size, NULL);
> -		goto error_free;
> +	} else {
> +		ret = add_memory_create_devices(nid, group, start, size,
> +						mhp_flags);
> +		if (ret)
> +			goto error;
>   	}
>   
>   	if (new_node) {
> @@ -1494,8 +1520,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>   		walk_memory_blocks(start, size, NULL, online_memory_block);
>   
>   	return ret;
> -error_free:
> -	kfree(params.altmap);
>   error:
>   	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
>   		memblock_remove(start, size);
> @@ -2076,6 +2100,23 @@ static int test_has_altmap_cb(struct memory_block *mem, void *arg)
>   	return 0;
>   }


[...]

> +
> +static int memblocks_have_altmaps(u64 start, u64 size)
> +{
> +	struct memory_range_altmap_info altmap_info = {
> +		.num_memblocks = 0,
> +		.num_altmaps = 0
> +	};

You can get the number of memblocks simply by "size / 
memory_block_size_bytes()". So you can avoid the "struct" and just pass 
an int.

> +
> +	if (!mhp_memmap_on_memory())
> +		return 0;
> +
> +	walk_memory_blocks(start, size, &altmap_info,
> +			   count_memory_range_altmaps_cb);
> +
> +	if (!altmap_info.num_altmaps)
> +		return 0;
> +
> +	if (altmap_info.num_memblocks != altmap_info.num_altmaps) {
> +		WARN_ONCE(1, "Not all memblocks in range have altmaps");
> +		return -EINVAL;
> +	}
> +
> +	return 1;
> +}
> +
> +static int __ref try_remove_memory(u64 start, u64 size)
> +{
> +	int rc, nid = NUMA_NO_NODE;
>   
>   	BUG_ON(check_hotplug_memory_range(start, size));
>   
> @@ -2167,45 +2272,21 @@ static int __ref try_remove_memory(u64 start, u64 size)
>   	if (rc)
>   		return rc;
>   
> -	/*
> -	 * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
> -	 * the same granularity it was added - a single memory block.
> -	 */
> -	if (mhp_memmap_on_memory()) {
> -		rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
> -		if (rc) {
> -			if (size != memory_block_size_bytes()) {
> -				pr_warn("Refuse to remove %#llx - %#llx,"
> -					"wrong granularity\n",
> -					start, start + size);
> -				return -EINVAL;
> -			}
> -			altmap = mem->altmap;
> -			/*
> -			 * Mark altmap NULL so that we can add a debug
> -			 * check on memblock free.
> -			 */
> -			mem->altmap = NULL;
> -		}
> -	}
> -
>   	/* 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.
> -	 */

Maybe move that comment into the else branch and not into 
remove_memory_blocks_and_altmaps

> -	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 = memblocks_have_altmaps(start, size);

Don't use the term memblocks here, to not confuse it with the memblock 
allocator.

"memory blocks" or "memory block devices". it's complicated.

> +	if (rc < 0) {
> +		goto err;
> +	} else if (rc == 0) {
> +		/* no altmaps, do the removal directly */
> +		remove_memory_block_devices(start, size);
> +		arch_remove_memory(start, size, NULL);
> +	} else {
> +		/* all memblocks in the range have altmaps */
> +		remove_memory_blocks_and_altmaps(start, size);
>   	}
>   
>   	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
> @@ -2218,8 +2299,9 @@ static int __ref try_remove_memory(u64 start, u64 size)
>   	if (nid != NUMA_NO_NODE)
>   		try_offline_node(nid);
>   
> +err:
>   	mem_hotplug_done();
> -	return 0;
> +	return (rc < 0 ? rc : 0);
>   }
>   
>   /**
>