[PATCH v12 mm-new 09/15] khugepaged: add per-order mTHP collapse failure statistics

[Nico Pache <npache@redhat.com>]

Add three new mTHP statistics to track collapse failures for different
orders when encountering swap PTEs, excessive none PTEs, and shared PTEs:

- collapse_exceed_swap_pte: Increment when mTHP collapse fails due to swap
	PTEs

- collapse_exceed_none_pte: Counts when mTHP collapse fails due to
  	exceeding the none PTE threshold for the given order

- collapse_exceed_shared_pte: Counts when mTHP collapse fails due to shared
  	PTEs

These statistics complement the existing THP_SCAN_EXCEED_* events by
providing per-order granularity for mTHP collapse attempts. The stats are
exposed via sysfs under
`/sys/kernel/mm/transparent_hugepage/hugepages-*/stats/` for each
supported hugepage size.

As we currently dont support collapsing mTHPs that contain a swap or
shared entry, those statistics keep track of how often we are
encountering failed mTHP collapses due to these restrictions.

Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Nico Pache <npache@redhat.com>
---
 Documentation/admin-guide/mm/transhuge.rst | 23 ++++++++++++++++++++++
 include/linux/huge_mm.h                    |  3 +++
 mm/huge_memory.c                           |  7 +++++++
 mm/khugepaged.c                            | 16 ++++++++++++---
 4 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index 13269a0074d4..7c71cda8aea1 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -709,6 +709,29 @@ nr_anon_partially_mapped
        an anonymous THP as "partially mapped" and count it here, even though it
        is not actually partially mapped anymore.
 
+collapse_exceed_none_pte
+       The number of anonymous mTHP pte ranges where the number of none PTEs
+       exceeded the max_ptes_none threshold. For mTHP collapse, khugepaged
+       checks a PMD region and tracks which PTEs are present. It then tries
+       to collapse to the largest enabled mTHP size. The allowed number of empty
+       PTEs is the max_ptes_none threshold scaled by the collapse order. This
+       counter records the number of times a collapse attempt was skipped for
+       this reason, and khugepaged moved on to try the next available mTHP size.
+
+collapse_exceed_swap_pte
+       The number of anonymous mTHP pte ranges which contain at least one swap
+       PTE. Currently khugepaged does not support collapsing mTHP regions
+       that contain a swap PTE. This counter can be used to monitor the
+       number of khugepaged mTHP collapses that failed due to the presence
+       of a swap PTE.
+
+collapse_exceed_shared_pte
+       The number of anonymous mTHP pte ranges which contain at least one shared
+       PTE. Currently khugepaged does not support collapsing mTHP pte ranges
+       that contain a shared PTE. This counter can be used to monitor the
+       number of khugepaged mTHP collapses that failed due to the presence
+       of a shared PTE.
+
 As the system ages, allocating huge pages may be expensive as the
 system uses memory compaction to copy data around memory to free a
 huge page for use. There are some counters in ``/proc/vmstat`` to help
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 3d29624c4f3f..4b2773235041 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -144,6 +144,9 @@ enum mthp_stat_item {
 	MTHP_STAT_SPLIT_DEFERRED,
 	MTHP_STAT_NR_ANON,
 	MTHP_STAT_NR_ANON_PARTIALLY_MAPPED,
+	MTHP_STAT_COLLAPSE_EXCEED_SWAP,
+	MTHP_STAT_COLLAPSE_EXCEED_NONE,
+	MTHP_STAT_COLLAPSE_EXCEED_SHARED,
 	__MTHP_STAT_COUNT
 };
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0063d1ba926e..7335b92969d6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -638,6 +638,10 @@ DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
 DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
 DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON);
 DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);
+DEFINE_MTHP_STAT_ATTR(collapse_exceed_swap_pte, MTHP_STAT_COLLAPSE_EXCEED_SWAP);
+DEFINE_MTHP_STAT_ATTR(collapse_exceed_none_pte, MTHP_STAT_COLLAPSE_EXCEED_NONE);
+DEFINE_MTHP_STAT_ATTR(collapse_exceed_shared_pte, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
+
 
 static struct attribute *anon_stats_attrs[] = {
 	&anon_fault_alloc_attr.attr,
@@ -654,6 +658,9 @@ static struct attribute *anon_stats_attrs[] = {
 	&split_deferred_attr.attr,
 	&nr_anon_attr.attr,
 	&nr_anon_partially_mapped_attr.attr,
+	&collapse_exceed_swap_pte_attr.attr,
+	&collapse_exceed_none_pte_attr.attr,
+	&collapse_exceed_shared_pte_attr.attr,
 	NULL,
 };
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d741af15e18c..053202141ea3 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -592,7 +592,9 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 				continue;
 			} else {
 				result = SCAN_EXCEED_NONE_PTE;
-				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
+				if (order == HPAGE_PMD_ORDER)
+					count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
+				count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_NONE);
 				goto out;
 			}
 		}
@@ -622,10 +624,17 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			 * shared may cause a future higher order collapse on a
 			 * rescan of the same range.
 			 */
-			if (order != HPAGE_PMD_ORDER || (cc->is_khugepaged &&
-			    shared > khugepaged_max_ptes_shared)) {
+			if (order != HPAGE_PMD_ORDER) {
+				result = SCAN_EXCEED_SHARED_PTE;
+				count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
+				goto out;
+			}
+
+			if (cc->is_khugepaged &&
+			    shared > khugepaged_max_ptes_shared) {
 				result = SCAN_EXCEED_SHARED_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
+				count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
 				goto out;
 			}
 		}
@@ -1073,6 +1082,7 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
 		 * range.
 		 */
 		if (order != HPAGE_PMD_ORDER) {
+			count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SWAP);
 			pte_unmap(pte);
 			mmap_read_unlock(mm);
 			result = SCAN_EXCEED_SWAP_PTE;
-- 
2.51.0