The patch titled
Subject: mm/khugepaged: add flag to predicate khugepaged-only behavior
has been added to the -mm mm-unstable branch. Its filename is
mm-khugepaged-add-flag-to-predicate-khugepaged-only-behavior.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-khugepaged-add-flag-to-predicate-khugepaged-only-behavior.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Zach O'Keefe" <zokeefe@xxxxxxxxxx>
Subject: mm/khugepaged: add flag to predicate khugepaged-only behavior
Date: Wed, 6 Jul 2022 16:59:24 -0700
Add .is_khugepaged flag to struct collapse_control so khugepaged-specific
behavior can be elided by MADV_COLLAPSE context.
Start by protecting khugepaged-specific heuristics by this flag. In
MADV_COLLAPSE, the user presumably has reason to believe the collapse will
be beneficial and khugepaged heuristics shouldn't prevent the user from
doing so:
1) sysfs-controlled knobs khugepaged_max_ptes_[none|swap|shared]
2) requirement that some pages in region being collapsed be young or
referenced
Link: https://lkml.kernel.org/r/20220706235936.2197195-7-zokeefe@xxxxxxxxxx
Signed-off-by: Zach O'Keefe <zokeefe@xxxxxxxxxx>
Cc: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: Chris Kennelly <ckennelly@xxxxxxxxxx>
Cc: Chris Zankel <chris@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Helge Deller <deller@xxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx>
Cc: James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Matt Turner <mattst88@xxxxxxxxx>
Cc: Max Filippov <jcmvbkbc@xxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Pasha Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Pavel Begunkov <asml.silence@xxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Rongwei Wang <rongwei.wang@xxxxxxxxxxxxxxxxx>
Cc: SeongJae Park <sj@xxxxxxxxxx>
Cc: Song Liu <songliubraving@xxxxxx>
Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/khugepaged.c | 62 +++++++++++++++++++++++++++++++---------------
1 file changed, 43 insertions(+), 19 deletions(-)
--- a/mm/khugepaged.c~mm-khugepaged-add-flag-to-predicate-khugepaged-only-behavior
+++ a/mm/khugepaged.c
@@ -73,6 +73,8 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepage
* default collapse hugepages if there is at least one pte mapped like
* it would have happened if the vma was large enough during page
* fault.
+ *
+ * Note that these are only respected if collapse was initiated by khugepaged.
*/
static unsigned int khugepaged_max_ptes_none __read_mostly;
static unsigned int khugepaged_max_ptes_swap __read_mostly;
@@ -86,6 +88,8 @@ static struct kmem_cache *mm_slot_cache
#define MAX_PTE_MAPPED_THP 8
struct collapse_control {
+ bool is_khugepaged;
+
/* Num pages scanned per node */
int node_load[MAX_NUMNODES];
@@ -554,6 +558,7 @@ static bool is_refcount_suitable(struct
static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
unsigned long address,
pte_t *pte,
+ struct collapse_control *cc,
struct list_head *compound_pagelist)
{
struct page *page = NULL;
@@ -567,7 +572,8 @@ static int __collapse_huge_page_isolate(
if (pte_none(pteval) || (pte_present(pteval) &&
is_zero_pfn(pte_pfn(pteval)))) {
if (!userfaultfd_armed(vma) &&
- ++none_or_zero <= khugepaged_max_ptes_none) {
+ (++none_or_zero <= khugepaged_max_ptes_none ||
+ !cc->is_khugepaged)) {
continue;
} else {
result = SCAN_EXCEED_NONE_PTE;
@@ -587,8 +593,8 @@ static int __collapse_huge_page_isolate(
VM_BUG_ON_PAGE(!PageAnon(page), page);
- if (page_mapcount(page) > 1 &&
- ++shared > khugepaged_max_ptes_shared) {
+ if (cc->is_khugepaged && page_mapcount(page) > 1 &&
+ ++shared > khugepaged_max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
goto out;
@@ -654,10 +660,14 @@ static int __collapse_huge_page_isolate(
if (PageCompound(page))
list_add_tail(&page->lru, compound_pagelist);
next:
- /* There should be enough young pte to collapse the page */
- if (pte_young(pteval) ||
- page_is_young(page) || PageReferenced(page) ||
- mmu_notifier_test_young(vma->vm_mm, address))
+ /*
+ * If collapse was initiated by khugepaged, check that there is
+ * enough young pte to justify collapsing the page
+ */
+ if (cc->is_khugepaged &&
+ (pte_young(pteval) || page_is_young(page) ||
+ PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm,
+ address)))
referenced++;
if (pte_write(pteval))
@@ -666,7 +676,7 @@ next:
if (unlikely(!writable)) {
result = SCAN_PAGE_RO;
- } else if (unlikely(!referenced)) {
+ } else if (unlikely(cc->is_khugepaged && !referenced)) {
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
@@ -745,6 +755,7 @@ static void khugepaged_alloc_sleep(void)
struct collapse_control khugepaged_collapse_control = {
+ .is_khugepaged = true,
.last_target_node = NUMA_NO_NODE,
};
@@ -1023,7 +1034,7 @@ static int collapse_huge_page(struct mm_
mmu_notifier_invalidate_range_end(&range);
spin_lock(pte_ptl);
- result = __collapse_huge_page_isolate(vma, address, pte,
+ result = __collapse_huge_page_isolate(vma, address, pte, cc,
&compound_pagelist);
spin_unlock(pte_ptl);
@@ -1114,7 +1125,8 @@ static int khugepaged_scan_pmd(struct mm
_pte++, _address += PAGE_SIZE) {
pte_t pteval = *_pte;
if (is_swap_pte(pteval)) {
- if (++unmapped <= khugepaged_max_ptes_swap) {
+ if (++unmapped <= khugepaged_max_ptes_swap ||
+ !cc->is_khugepaged) {
/*
* Always be strict with uffd-wp
* enabled swap entries. Please see
@@ -1133,7 +1145,8 @@ static int khugepaged_scan_pmd(struct mm
}
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
if (!userfaultfd_armed(vma) &&
- ++none_or_zero <= khugepaged_max_ptes_none) {
+ (++none_or_zero <= khugepaged_max_ptes_none ||
+ !cc->is_khugepaged)) {
continue;
} else {
result = SCAN_EXCEED_NONE_PTE;
@@ -1163,8 +1176,9 @@ static int khugepaged_scan_pmd(struct mm
goto out_unmap;
}
- if (page_mapcount(page) > 1 &&
- ++shared > khugepaged_max_ptes_shared) {
+ if (cc->is_khugepaged &&
+ page_mapcount(page) > 1 &&
+ ++shared > khugepaged_max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
goto out_unmap;
@@ -1218,14 +1232,22 @@ static int khugepaged_scan_pmd(struct mm
result = SCAN_PAGE_COUNT;
goto out_unmap;
}
- if (pte_young(pteval) ||
- page_is_young(page) || PageReferenced(page) ||
- mmu_notifier_test_young(vma->vm_mm, address))
+
+ /*
+ * If collapse was initiated by khugepaged, check that there is
+ * enough young pte to justify collapsing the page
+ */
+ if (cc->is_khugepaged &&
+ (pte_young(pteval) || page_is_young(page) ||
+ PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm,
+ address)))
referenced++;
}
if (!writable) {
result = SCAN_PAGE_RO;
- } else if (!referenced || (unmapped && referenced < HPAGE_PMD_NR/2)) {
+ } else if (cc->is_khugepaged &&
+ (!referenced ||
+ (unmapped && referenced < HPAGE_PMD_NR / 2))) {
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
@@ -1894,7 +1916,8 @@ static int khugepaged_scan_file(struct m
continue;
if (xa_is_value(page)) {
- if (++swap > khugepaged_max_ptes_swap) {
+ if (cc->is_khugepaged &&
+ ++swap > khugepaged_max_ptes_swap) {
result = SCAN_EXCEED_SWAP_PTE;
count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
break;
@@ -1945,7 +1968,8 @@ static int khugepaged_scan_file(struct m
rcu_read_unlock();
if (result == SCAN_SUCCEED) {
- if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {
+ if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none &&
+ cc->is_khugepaged) {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
} else {
_
Patches currently in -mm which might be from zokeefe@xxxxxxxxxx are
mm-khugepaged-remove-redundant-transhuge_vma_suitable-check.patch
mm-khugepaged-add-struct-collapse_control.patch
mm-khugepaged-dedup-and-simplify-hugepage-alloc-and-charging.patch
mm-khugepaged-pipe-enum-scan_result-codes-back-to-callers.patch
mm-khugepaged-add-flag-to-predicate-khugepaged-only-behavior.patch
mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check.patch
mm-khugepaged-record-scan_pmd_mapped-when-scan_pmd-finds-hugepage.patch
mm-madvise-introduce-madv_collapse-sync-hugepage-collapse.patch
mm-khugepaged-rename-prefix-of-shared-collapse-functions.patch
mm-madvise-add-huge_memory-mm_madvise_collapse-tracepoint.patch
mm-madvise-add-madv_collapse-to-process_madvise.patch
proc-smaps-add-pmdmappable-field-to-smaps.patch
selftests-vm-modularize-collapse-selftests.patch
selftests-vm-dedup-hugepage-allocation-logic.patch
selftests-vm-add-madv_collapse-collapse-context-to-selftests.patch
selftests-vm-add-selftest-to-verify-recollapse-of-thps.patch
selftests-vm-add-selftest-to-verify-multi-thp-collapse.patch
