diff options
| author | Nico Pache <npache@redhat.com> | 2026-06-05 10:14:15 -0600 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2026-06-21 11:31:31 -0700 |
| commit | b5b8b329c4b456806e3bcc6bf3490fbc508e9080 (patch) | |
| tree | 862e0e6c49c62ddb016831217f787c3a06d43408 /mm | |
| parent | 3a460f245f000c6fbd07fd94e572268e4a7a420d (diff) | |
| download | ath-b5b8b329c4b456806e3bcc6bf3490fbc508e9080.tar.gz | |
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 <npache@redhat.com>
Reviewed-by: Lorenzo Stoakes <ljs@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nanyong Sun <sunnanyong@huawei.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rafael Aquini <raquini@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shivank Garg <shivankg@amd.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Takashi Iwai (SUSE) <tiwai@suse.de>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Usama Arif <usama.arif@linux.dev>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/huge_memory.c | 7 | ||||
| -rw-r--r-- | mm/khugepaged.c | 15 |
2 files changed, 20 insertions, 2 deletions
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; } } |