On Tue, 01 Aug 2023 23:55:37 -0600
Vishal Verma <vishal.l.verma@xxxxxxxxx> 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.
>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: David Hildenbrand <david@xxxxxxxxxx>
> Cc: Michal Hocko <mhocko@xxxxxxxx>
> Cc: Oscar Salvador <osalvador@xxxxxxx>
> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
> Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
> Cc: Huang Ying <ying.huang@xxxxxxxxx>
> Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
> Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>
A couple of trivial comments inline.
> ---
> mm/memory_hotplug.c | 150 ++++++++++++++++++++++++++++++++--------------------
> 1 file changed, 93 insertions(+), 57 deletions(-)
>
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index d282664f558e..cae03c8d4bbf 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1383,6 +1383,44 @@ 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 = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
> + if (!params.altmap)
> + return -ENOMEM;
> +
> + memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
> + }
> +
> + /* call arch's memory hotadd */
> + ret = arch_add_memory(nid, start, size, ¶ms);
> + 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) {
> + arch_remove_memory(start, size, NULL);
Maybe push this down to a second label?
> + goto error;
> + }
> +
> + return 0;
> +
> +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).
> @@ -1391,14 +1429,10 @@ 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;
>
> @@ -1439,28 +1473,21 @@ 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 = kmalloc(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;
> -
> - memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
> }
> - /* fallback to not using altmap */
> - }
> -
> - /* call arch's memory hotadd */
> - ret = arch_add_memory(nid, start, size, ¶ms);
> - 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) {
> @@ -1497,8 +1524,6 @@ 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);
> @@ -2149,40 +2174,14 @@ void try_offline_node(int nid)
> }
> EXPORT_SYMBOL(try_offline_node);
>
> -static int __ref try_remove_memory(u64 start, u64 size)
> +static void __ref __try_remove_memory(int nid, u64 start, u64 size)
> {
> - int ret;
> - struct memory_block *mem;
> - int rc = 0, nid = NUMA_NO_NODE;
> struct vmem_altmap *altmap = NULL;
> + struct memory_block *mem;
> + int ret;
>
> - BUG_ON(check_hotplug_memory_range(start, size));
> -
> - /*
> - * All memory blocks must be offlined before removing memory. Check
> - * whether all memory blocks in question are offline and return error
> - * if this is not the case.
> - *
> - * While at it, determine the nid. Note that if we'd have mixed nodes,
> - * we'd only try to offline the last determined one -- which is good
> - * enough for the cases we care about.
> - */
> - rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
> - 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.
> - */
> ret = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
> if (ret) {
> - 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
> @@ -2221,6 +2220,43 @@ static int __ref try_remove_memory(u64 start, u64 size)
> try_offline_node(nid);
>
> mem_hotplug_done();
> +}
> +
> +static int __ref try_remove_memory(u64 start, u64 size)
> +{
> + int ret, nid = NUMA_NO_NODE;
I'm not overly keen to see the trivial rename of rc -> ret in here.
Just makes it ever so slightly harder to compare old code and new code.
> +
> + BUG_ON(check_hotplug_memory_range(start, size));
> +
> + /*
> + * All memory blocks must be offlined before removing memory. Check
> + * whether all memory blocks in question are offline and return error
> + * if this is not the case.
> + *
> + * While at it, determine the nid. Note that if we'd have mixed nodes,
> + * we'd only try to offline the last determined one -- which is good
> + * enough for the cases we care about.
> + */
> + ret = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
> + if (ret)
> + return ret;
> +
> + /*
> + * For memmap_on_memory, the altmaps could have been added on
> + * a per-memblock basis. Loop through the entire range if so,
> + * and remove each memblock and its altmap.
> + */
> + if (mhp_memmap_on_memory()) {
> + unsigned long memblock_size = memory_block_size_bytes();
> + u64 cur_start;
> +
> + for (cur_start = start; cur_start < start + size;
> + cur_start += memblock_size)
> + __try_remove_memory(nid, cur_start, memblock_size);
> + } else {
> + __try_remove_memory(nid, start, size);
> + }
> +
> return 0;
> }
>
>
