From: Alexander Zhu <[email protected]>
This patch introduces a shrinker that will remove THPs in the lowest
utilization bucket. As previously mentioned, we have observed that
almost all of the memory waste when THPs are always enabled
is contained in the lowest utilization bucket. The shrinker will
add these THPs to a list_lru and split anonymous THPs based off
information from kswapd. It requires the changes from
thp_utilization to identify the least utilized THPs, and the
changes to split_huge_page to identify and free zero pages
within THPs.
Signed-off-by: Alexander Zhu <[email protected]>
---
include/linux/huge_mm.h | 7 +++
include/linux/list_lru.h | 24 ++++++++++
include/linux/mm_types.h | 5 +++
mm/huge_memory.c | 96 ++++++++++++++++++++++++++++++++++++++--
mm/list_lru.c | 49 ++++++++++++++++++++
mm/page_alloc.c | 6 +++
6 files changed, 184 insertions(+), 3 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index d5520f5cc798..d6e55bf67625 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -193,6 +193,8 @@ static inline int split_huge_page(struct page *page)
}
void deferred_split_huge_page(struct page *page);
+void add_underutilized_thp(struct page *page);
+
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze, struct folio *folio);
@@ -303,6 +305,11 @@ static inline struct list_head *page_deferred_list(struct page *page)
return &page[2].deferred_list;
}
+static inline struct list_head *page_underutilized_thp_list(struct page *page)
+{
+ return &page[3].underutilized_thp_list;
+}
+
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index b35968ee9fb5..c2cf146ea880 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -89,6 +89,18 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
*/
bool list_lru_add(struct list_lru *lru, struct list_head *item);
+/**
+ * list_lru_add_page: add an element to the lru list's tail
+ * @list_lru: the lru pointer
+ * @page: the page containing the item
+ * @item: the item to be deleted.
+ *
+ * This function works the same as list_lru_add in terms of list
+ * manipulation. Used for non slab objects contained in the page.
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_add_page(struct list_lru *lru, struct page *page, struct list_head *item);
/**
* list_lru_del: delete an element to the lru list
* @list_lru: the lru pointer
@@ -102,6 +114,18 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
*/
bool list_lru_del(struct list_lru *lru, struct list_head *item);
+/**
+ * list_lru_del_page: delete an element to the lru list
+ * @list_lru: the lru pointer
+ * @page: the page containing the item
+ * @item: the item to be deleted.
+ *
+ * This function works the same as list_lru_del in terms of list
+ * manipulation. Used for non slab objects contained in the page.
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_del_page(struct list_lru *lru, struct page *page, struct list_head *item);
/**
* list_lru_count_one: return the number of objects currently held by @lru
* @lru: the lru pointer.
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index cf97f3884fda..05667a2030c0 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -151,6 +151,11 @@ struct page {
/* For both global and memcg */
struct list_head deferred_list;
};
+ struct { /* Third tail page of compound page */
+ unsigned long _compound_pad_3; /* compound_head */
+ unsigned long _compound_pad_4;
+ struct list_head underutilized_thp_list;
+ };
struct { /* Page table pages */
unsigned long _pt_pad_1; /* compound_head */
pgtable_t pmd_huge_pte; /* protected by page->ptl */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b905d9d1a3f2..deceadde2275 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -80,6 +80,8 @@ static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;
+struct list_lru huge_low_util_page_lru;
+
static void thp_utilization_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(thp_utilization_work, thp_utilization_workfn);
@@ -264,6 +266,51 @@ static struct shrinker huge_zero_page_shrinker = {
.seeks = DEFAULT_SEEKS,
};
+static enum lru_status low_util_free_page(struct list_head *item,
+ struct list_lru_one *lru,
+ spinlock_t *lock,
+ void *cb_arg)
+{
+ int bucket, num_utilized_pages;
+ struct page *head = compound_head(list_entry(item,
+ struct page,
+ underutilized_thp_list));
+
+ if (get_page_unless_zero(head)) {
+ lock_page(head);
+ list_lru_isolate(lru, item);
+ num_utilized_pages = thp_number_utilized_pages(head);
+ bucket = thp_utilization_bucket(num_utilized_pages);
+ if (bucket < THP_UTIL_BUCKET_NR - 1)
+ split_huge_page(head);
+ unlock_page(head);
+ put_page(head);
+ }
+
+ return LRU_REMOVED_RETRY;
+}
+
+static unsigned long shrink_huge_low_util_page_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ return HPAGE_PMD_NR * list_lru_shrink_count(&huge_low_util_page_lru, sc);
+}
+
+static unsigned long shrink_huge_low_util_page_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ return HPAGE_PMD_NR * list_lru_shrink_walk(&huge_low_util_page_lru,
+ sc, low_util_free_page, NULL);
+}
+
+static struct shrinker huge_low_util_page_shrinker = {
+ .count_objects = shrink_huge_low_util_page_count,
+ .scan_objects = shrink_huge_low_util_page_scan,
+ .seeks = DEFAULT_SEEKS,
+ .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE |
+ SHRINKER_NONSLAB,
+};
+
#ifdef CONFIG_SYSFS
static ssize_t enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
@@ -516,13 +563,18 @@ static int __init hugepage_init(void)
goto err_slab;
schedule_delayed_work(&thp_utilization_work, HZ);
+ err = register_shrinker(&huge_low_util_page_shrinker, "thp-low-util");
+ if (err)
+ goto err_low_util_shrinker;
err = register_shrinker(&huge_zero_page_shrinker, "thp-zero");
if (err)
goto err_hzp_shrinker;
err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split");
if (err)
goto err_split_shrinker;
-
+ err = list_lru_init_memcg(&huge_low_util_page_lru, &huge_low_util_page_shrinker);
+ if (err)
+ goto err_low_util_list_lru;
/*
* By default disable transparent hugepages on smaller systems,
* where the extra memory used could hurt more than TLB overhead
@@ -538,11 +590,16 @@ static int __init hugepage_init(void)
goto err_khugepaged;
return 0;
+
err_khugepaged:
+ list_lru_destroy(&huge_low_util_page_lru);
+err_low_util_list_lru:
unregister_shrinker(&deferred_split_shrinker);
err_split_shrinker:
unregister_shrinker(&huge_zero_page_shrinker);
err_hzp_shrinker:
+ unregister_shrinker(&huge_low_util_page_shrinker);
+err_low_util_shrinker:
khugepaged_destroy();
err_slab:
hugepage_exit_sysfs(hugepage_kobj);
@@ -617,6 +674,7 @@ void prep_transhuge_page(struct page *page)
*/
INIT_LIST_HEAD(page_deferred_list(page));
+ INIT_LIST_HEAD(page_underutilized_thp_list(page));
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
@@ -2519,8 +2577,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
(1L << PG_dirty)));
/* ->mapping in first tail page is compound_mapcount */
- VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
- page_tail);
+ VM_BUG_ON_PAGE(tail > 3 && page_tail->mapping != TAIL_MAPPING, page_tail);
page_tail->mapping = head->mapping;
page_tail->index = head->index + tail;
page_tail->private = 0;
@@ -2727,6 +2784,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
struct folio *folio = page_folio(page);
struct page *head = &folio->page;
struct deferred_split *ds_queue = get_deferred_split_queue(head);
+ struct list_head *underutilized_thp_list = page_underutilized_thp_list(head);
XA_STATE(xas, &head->mapping->i_pages, head->index);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
@@ -2825,6 +2883,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
list_del(page_deferred_list(head));
}
spin_unlock(&ds_queue->split_queue_lock);
+ if (!list_empty(underutilized_thp_list))
+ list_lru_del_page(&huge_low_util_page_lru, head, underutilized_thp_list);
if (mapping) {
int nr = thp_nr_pages(head);
@@ -2867,6 +2927,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
void free_transhuge_page(struct page *page)
{
struct deferred_split *ds_queue = get_deferred_split_queue(page);
+ struct list_head *underutilized_thp_list = page_underutilized_thp_list(page);
unsigned long flags;
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
@@ -2875,6 +2936,12 @@ void free_transhuge_page(struct page *page)
list_del(page_deferred_list(page));
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+ if (!list_empty(underutilized_thp_list))
+ list_lru_del_page(&huge_low_util_page_lru, page, underutilized_thp_list);
+
+ if (PageLRU(page))
+ __clear_page_lru_flags(page);
+
free_compound_page(page);
}
@@ -2915,6 +2982,26 @@ void deferred_split_huge_page(struct page *page)
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
}
+void add_underutilized_thp(struct page *page)
+{
+ VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+
+ if (PageSwapCache(page))
+ return;
+
+ /*
+ * Need to take a reference on the page to prevent the page from getting free'd from
+ * under us while we are adding the THP to the shrinker.
+ */
+ if (!get_page_unless_zero(page))
+ return;
+
+ if (!is_huge_zero_page(page) && is_anon_transparent_hugepage(page))
+ list_lru_add_page(&huge_low_util_page_lru, page, page_underutilized_thp_list(page));
+
+ put_page(page);
+}
+
static unsigned long deferred_split_count(struct shrinker *shrink,
struct shrink_control *sc)
{
@@ -3449,6 +3536,9 @@ static void thp_util_scan(unsigned long pfn_end)
if (bucket < 0)
continue;
+ if (bucket < THP_UTIL_BUCKET_NR - 1)
+ add_underutilized_thp(page);
+
thp_scan.buckets[bucket].nr_thps++;
thp_scan.buckets[bucket].nr_zero_pages += (HPAGE_PMD_NR - num_utilized_pages);
}
diff --git a/mm/list_lru.c b/mm/list_lru.c
index a05e5bef3b40..7e8b324cc840 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -140,6 +140,32 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
}
EXPORT_SYMBOL_GPL(list_lru_add);
+bool list_lru_add_page(struct list_lru *lru, struct page *page, struct list_head *item)
+{
+ int nid = page_to_nid(page);
+ struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_one *l;
+ struct mem_cgroup *memcg;
+
+ spin_lock(&nlru->lock);
+ if (list_empty(item)) {
+ memcg = page_memcg(page);
+ memcg_list_lru_alloc(memcg, lru, GFP_KERNEL);
+ l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+ list_add_tail(item, &l->list);
+ /* Set shrinker bit if the first element was added */
+ if (!l->nr_items++)
+ set_shrinker_bit(memcg, nid,
+ lru_shrinker_id(lru));
+ nlru->nr_items++;
+ spin_unlock(&nlru->lock);
+ return true;
+ }
+ spin_unlock(&nlru->lock);
+ return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_add_page);
+
bool list_lru_del(struct list_lru *lru, struct list_head *item)
{
int nid = page_to_nid(virt_to_page(item));
@@ -160,6 +186,29 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
}
EXPORT_SYMBOL_GPL(list_lru_del);
+bool list_lru_del_page(struct list_lru *lru, struct page *page, struct list_head *item)
+{
+ int nid = page_to_nid(page);
+ struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_one *l;
+ struct mem_cgroup *memcg;
+
+ spin_lock(&nlru->lock);
+ if (!list_empty(item)) {
+ memcg = page_memcg(page);
+ memcg_list_lru_alloc(memcg, lru, GFP_KERNEL);
+ l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+ list_del_init(item);
+ l->nr_items--;
+ nlru->nr_items--;
+ spin_unlock(&nlru->lock);
+ return true;
+ }
+ spin_unlock(&nlru->lock);
+ return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_del_page);
+
void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
{
list_del_init(item);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d04211f0ef0b..6058df395eea 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1327,6 +1327,12 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
* deferred_list.next -- ignore value.
*/
break;
+ case 3:
+ /*
+ * the third tail page: ->mapping is
+ * underutilized_thp_list.next -- ignore value.
+ */
+ break;
default:
if (page->mapping != TAIL_MAPPING) {
bad_page(page, "corrupted mapping in tail page");
--
2.30.2
Hi,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on shuah-kselftest/next]
[also build test WARNING on linus/master v6.0-rc7]
[cannot apply to akpm-mm/mm-everything next-20220928]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/alexlzhu-fb-com/mm-add-thp_utilization-metrics-to-sysfs/20220928-152511
base: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git next
config: i386-randconfig-s001
compiler: gcc-11 (Debian 11.3.0-5) 11.3.0
reproduce:
# apt-get install sparse
# sparse version: v0.6.4-39-gce1a6720-dirty
# https://github.com/intel-lab-lkp/linux/commit/4e04c6e127b5cc86d537b079af3bb3bf1c762ae4
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review alexlzhu-fb-com/mm-add-thp_utilization-metrics-to-sysfs/20220928-152511
git checkout 4e04c6e127b5cc86d537b079af3bb3bf1c762ae4
# save the config file
mkdir build_dir && cp config build_dir/.config
make W=1 C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__' O=build_dir ARCH=i386 SHELL=/bin/bash
If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <[email protected]>
sparse warnings: (new ones prefixed by >>)
>> mm/huge_memory.c:83:17: sparse: sparse: symbol 'huge_low_util_page_lru' was not declared. Should it be static?
mm/huge_memory.c:1730:20: sparse: sparse: context imbalance in 'madvise_free_huge_pmd' - unexpected unlock
mm/huge_memory.c:1767:28: sparse: sparse: context imbalance in 'zap_huge_pmd' - unexpected unlock
mm/huge_memory.c:1874:28: sparse: sparse: context imbalance in 'move_huge_pmd' - unexpected unlock
mm/huge_memory.c:2006:20: sparse: sparse: context imbalance in 'change_huge_pmd' - unexpected unlock
mm/huge_memory.c:2016:12: sparse: sparse: context imbalance in '__pmd_trans_huge_lock' - wrong count at exit
mm/huge_memory.c: note: in included file (through include/linux/mmzone.h, include/linux/gfp.h, include/linux/mm.h):
include/linux/page-flags.h:820:22: sparse: sparse: context imbalance in '__split_huge_page' - unexpected unlock
mm/huge_memory.c:2887:17: sparse: sparse: context imbalance in 'split_huge_page_to_list' - different lock contexts for basic block
--
0-DAY CI Kernel Test Service
https://01.org/lkp