From: Nico Pache Date: Fri, 5 Jun 2026 16:14:15 +0000 (-0600) Subject: mm/khugepaged: add per-order mTHP collapse failure statistics X-Git-Tag: v7.2-rc1~59^2~105 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=b5b8b329c4b456806e3bcc6bf3490fbc508e9080;p=thirdparty%2Fkernel%2Flinux.git mm/khugepaged: add per-order mTHP collapse failure statistics 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 encountering a swap PTE. - 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 encountering a shared PTE. 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 do not 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. We will add support for mTHP collapse for anonymous pages next; lets also track when this happens at the PMD level within the per-mTHP stats. Link: https://lore.kernel.org/20260605161422.213817-9-npache@redhat.com Signed-off-by: Nico Pache Reviewed-by: Lorenzo Stoakes Acked-by: David Hildenbrand (Arm) Reviewed-by: Lance Yang Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Anshuman Khandual Cc: Bagas Sanjaya Cc: Baolin Wang Cc: Barry Song Cc: Brendan Jackman Cc: Byungchul Park Cc: Catalin Marinas Cc: David Rientjes Cc: Dev Jain Cc: Gregory Price Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Joshua Hahn Cc: Kefeng Wang Cc: Liam R. Howlett Cc: "Masami Hiramatsu (Google)" Cc: Mathieu Desnoyers Cc: Matthew Brost Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Nanyong Sun Cc: Pedro Falcato Cc: Peter Xu Cc: Rafael Aquini Cc: Rakie Kim Cc: Randy Dunlap Cc: Ryan Roberts Cc: Shivank Garg Cc: Steven Rostedt Cc: Suren Baghdasaryan Cc: Takashi Iwai (SUSE) Cc: Thomas Hellström Cc: Usama Arif Cc: Usama Arif Cc: Vishal Moola (Oracle) Cc: Vlastimil Babka Cc: Wei Yang Cc: Will Deacon Cc: Yang Shi Cc: Zach O'Keefe Cc: Zi Yan Signed-off-by: Andrew Morton --- diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index a74844e01f1e8..b98e18c801850 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -714,6 +714,20 @@ 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 collapse attempts that failed due to exceeding the + max_ptes_none threshold. + +collapse_exceed_swap_pte + The number of collapse attempts that failed due to exceeding the + max_ptes_swap threshold. For non-PMD orders this occurs if a mTHP range + contains at least one swap PTE. + +collapse_exceed_shared_pte + The number of collapse attempts that failed due to exceeding the + max_ptes_shared threshold. For non-PMD orders this occurs if a mTHP range + contains at least one 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 e225d1d4a3fef..89f4c22d7d62e 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 c8b851dd518af..b4062396ce877 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -720,6 +720,10 @@ 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, @@ -736,6 +740,9 @@ 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 c7819a854f14c..a496484157a17 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -651,7 +651,9 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma, if (pte_none_or_zero(pteval)) { if (++none_or_zero > max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; - count_vm_event(THP_SCAN_EXCEED_NONE_PTE); + if (is_pmd_order(order)) + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_NONE); goto out; } continue; @@ -693,7 +695,9 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma, */ if (++shared > max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; - count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); + if (is_pmd_order(order)) + count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED); goto out; } } @@ -1152,6 +1156,7 @@ static enum scan_result __collapse_huge_page_swapin(struct mm_struct *mm, * range. */ if (!is_pmd_order(order)) { + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SWAP); pte_unmap(pte); mmap_read_unlock(mm); result = SCAN_EXCEED_SWAP_PTE; @@ -1464,6 +1469,8 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm, if (++none_or_zero > max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); + count_mthp_stat(HPAGE_PMD_ORDER, + MTHP_STAT_COLLAPSE_EXCEED_NONE); goto out_unmap; } continue; @@ -1472,6 +1479,8 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm, if (++unmapped > max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); + count_mthp_stat(HPAGE_PMD_ORDER, + MTHP_STAT_COLLAPSE_EXCEED_SWAP); goto out_unmap; } /* @@ -1529,6 +1538,8 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm, if (++shared > max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); + count_mthp_stat(HPAGE_PMD_ORDER, + MTHP_STAT_COLLAPSE_EXCEED_SHARED); goto out_unmap; } }