Re: [PATCH resend] ksm: add merge_only_zero_pages to merge only empty anonymous pages

[Jinjiang Tu <tujinjiang@huawei.com>]

在 2026/11/9 10:02, Xu Xin (vivo) 写道:
> On Sat, Nov 07, 2026 at 04:13:40PM +0800, Jinjiang Tu wrote:
>> 在 2026/11/6 11:48, xu.xin@linux.dev 写道:
>>> From: "Xu Xin (vivo)" <xu.xin@linux.dev>
>>>
>>>     KSM side-channel exposure is desired. Many handset vendors may prefer
>>>     this knob, which can be used as a default fallback policy.
>>>
>>> - Not suitable for server and virtualization workloads containing many
>>>     non-zero duplicate pages, where vanilla KSM provides better memory
>>>     savings.
>> It’s a coincidence that I’m also working on similar optimizations.
>> In our scenario, we have a MySQL instance with over 700 GB of anonymous
>> memory. Most of this memory belongs to the buffer pool, which caches
>> data from storage; these pages cannot be merged. Of the remaining memory,
>> around 15 GB is consumed by hashtables, which contain many zero-filled
>> pages that are eligible for merging to reduce memory footprint.
>>
>> When we enabled KSM for the entire MySQL instance, ksmd created rmap_item
>> metadata for each candidate page.The massive metadata overhead wiped out
>> any gains from page merging, and even resulted in a negative benefit.
>>
>> For this reason, I’m trying to make ksmd merge only zero pages. The goal
>> is to have ksmd skip scanning non-zero pages entirely, thereby avoiding
>> the rmap_item metadata cost introduced by scanning non-mergeable pages.
> Skip generating ksm_rmap_item for non-zero pages ? That dose make sense to me.

Yes.

>
>> 1) Before get_next_rmap_item(), check whether the page is all zeros.
>> If not, skip it directly to avoid allocating an rmap_item.
>>
>> 2) When walking page tables to find candidate pages in ksm_next_page_pmd_entry(),
>> check whether the first and last contents are zero as a quick filter.
>> This is intended to speed up page-table traversal.
>>
>> Would you mind to collaborate? For example, by including my optimization
>> as the second patch in your patch series?
> Happy to do it.

Thanks.

>
>> Here is the diff. Basic functionality has been tested.
>>
>> diff --git a/mm/ksm.c b/mm/ksm.c
>> index dbfb8f98b189..8a02976b0aba 100644
>> --- a/mm/ksm.c
>> +++ b/mm/ksm.c
>> @@ -296,6 +296,9 @@ static unsigned int zero_checksum __read_mostly;
>>   /* Whether to merge empty (zeroed) pages with actual zero pages */
>>   static bool ksm_use_zero_pages __read_mostly;
>> +/* Whether to merge empty (zeroed) pages only */
>> +static bool ksm_only_merge_zero_pages __read_mostly;
>> +
>>   /* Skip pages that couldn't be de-duplicated previously */
>>   /* Default to true at least temporarily, for testing */
>>   static bool ksm_smart_scan = true;
>> @@ -2524,8 +2527,42 @@ struct ksm_next_page_arg {
>>   	struct folio *folio;
>>   	struct page *page;
>>   	unsigned long addr;
>> +	unsigned int nr_to_skip;
>>   };
>> +static inline bool page_maybe_zero(struct page *page)
>> +{
>> +	unsigned long *p;
>> +	bool ret = true;
>> +	unsigned int last_pos = PAGE_SIZE / sizeof(*p) - 1;
>> +
>> +	p = kmap_local_page(page);
>> +	if (p[0] || p[last_pos])
>> +		ret = false;
>> +	kunmap_local(p);
>> +	return ret;
>> +}
>> +
>> +static struct page *ksm_skip_nonzero_pages(struct page *page,
>> +					   unsigned long *addr,
>> +					   unsigned long nr,
>> +					   unsigned int *nr_to_skip)
>> +{
>> +	unsigned long i;
>> +
>> +	for (i = 0; i < nr; i++) {
>> +		if (!*nr_to_skip)
>> +			break;
>> +		(*nr_to_skip)--;
>> +		if (page_maybe_zero(page + i))
>> +			break;
>> +	}
>> +	if (i == nr)
>> +		return NULL;
>> +	*addr += i << PAGE_SHIFT;
>> +	return page + i;
>> +}
>> +
>>   static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long end,
>>   		struct mm_walk *walk)
>>   {
>> @@ -2563,6 +2600,13 @@ static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned lon
>>   				goto not_found_unlock;
>>   			page += ((addr & (PMD_SIZE - 1)) >> PAGE_SHIFT);
>> +			if (ksm_only_merge_zero_pages) {
>> +				page = ksm_skip_nonzero_pages(page, &addr,
>> +					(end - addr) >> PAGE_SHIFT,
>> +					&private->nr_to_skip);
>> +				if (!page)
>> +					goto not_found_unlock;
>> +			}
>>   			goto found_unlock;
>>   		}
>>   		spin_unlock(ptl);
>> @@ -2585,6 +2629,14 @@ static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned lon
>>   		if (folio_is_zone_device(folio) || !folio_test_anon(folio))
>>   			continue;
>> +
>> +		if (ksm_only_merge_zero_pages && !folio_test_ksm(folio)) {
>> +			page = ksm_skip_nonzero_pages(page, &addr, 1,
>> +						      &private->nr_to_skip);
>> +			if (!page)
>> +				continue;
>> +		}
>> +
>>   		goto found_unlock;
>>   	}
>> @@ -2609,6 +2661,33 @@ static struct mm_walk_ops ksm_next_page_ops = {
>>   	.walk_lock = PGWALK_RDLOCK,
>>   };
>> +static bool should_skip_page(struct ksm_rmap_item **rmap_list,
>> +				  unsigned long addr, struct folio *folio,
>> +				  struct page *page)
>> +{
>> +	struct ksm_rmap_item *rmap_item;
>> +
>> +	if (!ksm_only_merge_zero_pages)
>> +		return false;
>> +
>> +	if (folio_test_ksm(folio))
>> +		return false;
>> +
>> +	if (pages_identical(page, ZERO_PAGE(0)))
>> +		return false;
>> +
>> +	while (*rmap_list) {
>> +		rmap_item = *rmap_list;
>> +		if ((rmap_item->address & PAGE_MASK) > addr)
>> +			break;
>> +		*rmap_list = rmap_item->rmap_list;
>> +		remove_rmap_item_from_tree(rmap_item);
>> +		free_rmap_item(rmap_item);
>> +	}
>> +	return true;
>> +}
>> +
>> +
>>   static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
>>   {
>>   	struct mm_struct *mm;
>> @@ -2705,6 +2784,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
>>   			int found;
>> +			ksm_next_page_arg.nr_to_skip = 1024;
>>   			found = walk_page_range_vma(vma, ksm_scan.address,
>>   						    vma->vm_end,
>>   						    &ksm_next_page_ops,
>> @@ -2722,6 +2802,14 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
>>   			if (tmp_page) {
>>   				flush_anon_page(vma, tmp_page, ksm_scan.address);
>>   				flush_dcache_page(tmp_page);
>> +
>> +				if (should_skip_page(ksm_scan.rmap_list, ksm_scan.address, folio, tmp_page)) {
>> +					folio_put(folio);
>> +					ksm_scan.address += PAGE_SIZE;
>> +					mmap_read_unlock(mm);
>> +					return ERR_PTR(-EAGAIN);
>> +				}
>> +
>>   				rmap_item = get_next_rmap_item(mm_slot,
>>   					ksm_scan.rmap_list, ksm_scan.address);
>>   				if (rmap_item) {
>> @@ -2824,6 +2912,10 @@ static void ksm_do_scan(unsigned int scan_npages)
>>   		rmap_item = scan_get_next_rmap_item(&page);
>>   		if (!rmap_item)
>>   			return;
>> +		if (rmap_item == ERR_PTR(-EAGAIN)) {
>> +			ksm_pages_scanned++;
>> +			continue;
>> +		}
>>   		cmp_and_merge_page(page, rmap_item);
>>   		put_page(page);
>>   		ksm_pages_scanned++;
>> @@ -3674,6 +3766,28 @@ static ssize_t use_zero_pages_store(struct kobject *kobj,
>>   }
>>   KSM_ATTR(use_zero_pages);
>>