The patch titled
Subject: mm/rmap: integrate PMD-mapped folio splitting into pagewalk loop
has been added to the -mm mm-unstable branch. Its filename is
mm-rmap-integrate-pmd-mapped-folio-splitting-into-pagewalk-loop.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-rmap-integrate-pmd-mapped-folio-splitting-into-pagewalk-loop.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: Lance Yang <ioworker0@xxxxxxxxx>
Subject: mm/rmap: integrate PMD-mapped folio splitting into pagewalk loop
Date: Wed, 1 May 2024 12:26:59 +0800
In preparation for supporting try_to_unmap_one() to unmap PMD-mapped
folios, start the pagewalk first, then call split_huge_pmd_address() to
split the folio.
Link: https://lkml.kernel.org/r/20240501042700.83974-3-ioworker0@xxxxxxxxx
Signed-off-by: Lance Yang <ioworker0@xxxxxxxxx>
Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
Tested-by: SeongJae Park <sj@xxxxxxxxxx>
Cc: Barry Song <21cnbao@xxxxxxxxx>
Cc: Fangrui Song <maskray@xxxxxxxxxx>
Cc: Jeff Xie <xiehuan09@xxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Yin Fengwei <fengwei.yin@xxxxxxxxx>
Cc: Zach O'Keefe <zokeefe@xxxxxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/huge_mm.h | 20 ++++++++++++++++++
mm/huge_memory.c | 42 +++++++++++++++++++-------------------
mm/rmap.c | 24 ++++++++++++++++-----
3 files changed, 60 insertions(+), 26 deletions(-)
--- a/include/linux/huge_mm.h~mm-rmap-integrate-pmd-mapped-folio-splitting-into-pagewalk-loop
+++ a/include/linux/huge_mm.h
@@ -409,6 +409,20 @@ static inline bool thp_migration_support
return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
}
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, bool freeze, struct folio *folio);
+
+static inline void align_huge_pmd_range(struct vm_area_struct *vma,
+ unsigned long *start,
+ unsigned long *end)
+{
+ *start = ALIGN(*start, HPAGE_PMD_SIZE);
+ *end = ALIGN_DOWN(*end, HPAGE_PMD_SIZE);
+
+ VM_WARN_ON_ONCE(vma->vm_start > *start);
+ VM_WARN_ON_ONCE(vma->vm_end < *end);
+}
+
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline bool folio_test_pmd_mappable(struct folio *folio)
@@ -471,6 +485,12 @@ static inline void __split_huge_pmd(stru
unsigned long address, bool freeze, struct folio *folio) {}
static inline void split_huge_pmd_address(struct vm_area_struct *vma,
unsigned long address, bool freeze, struct folio *folio) {}
+static inline void split_huge_pmd_locked(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmd,
+ bool freeze, struct folio *folio) {}
+static inline void align_huge_pmd_range(struct vm_area_struct *vma,
+ unsigned long *start,
+ unsigned long *end) {}
#define split_huge_pud(__vma, __pmd, __address) \
do { } while (0)
--- a/mm/huge_memory.c~mm-rmap-integrate-pmd-mapped-folio-splitting-into-pagewalk-loop
+++ a/mm/huge_memory.c
@@ -2583,6 +2583,27 @@ static void __split_huge_pmd_locked(stru
pmd_populate(mm, pmd, pgtable);
}
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, bool freeze, struct folio *folio)
+{
+ VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
+ VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
+ VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
+ VM_BUG_ON(freeze && !folio);
+
+ /*
+ * When the caller requests to set up a migration entry, we
+ * require a folio to check the PMD against. Otherwise, there
+ * is a risk of replacing the wrong folio.
+ */
+ if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
+ is_pmd_migration_entry(*pmd)) {
+ if (folio && folio != pmd_folio(*pmd))
+ return;
+ __split_huge_pmd_locked(vma, pmd, address, freeze);
+ }
+}
+
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze, struct folio *folio)
{
@@ -2594,26 +2615,7 @@ void __split_huge_pmd(struct vm_area_str
(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
ptl = pmd_lock(vma->vm_mm, pmd);
-
- /*
- * If caller asks to setup a migration entry, we need a folio to check
- * pmd against. Otherwise we can end up replacing wrong folio.
- */
- VM_BUG_ON(freeze && !folio);
- VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
-
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
- is_pmd_migration_entry(*pmd)) {
- /*
- * It's safe to call pmd_page when folio is set because it's
- * guaranteed that pmd is present.
- */
- if (folio && folio != pmd_folio(*pmd))
- goto out;
- __split_huge_pmd_locked(vma, pmd, range.start, freeze);
- }
-
-out:
+ split_huge_pmd_locked(vma, range.start, pmd, freeze, folio);
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
}
--- a/mm/rmap.c~mm-rmap-integrate-pmd-mapped-folio-splitting-into-pagewalk-loop
+++ a/mm/rmap.c
@@ -1637,9 +1637,6 @@ static bool try_to_unmap_one(struct foli
if (flags & TTU_SYNC)
pvmw.flags = PVMW_SYNC;
- if (flags & TTU_SPLIT_HUGE_PMD)
- split_huge_pmd_address(vma, address, false, folio);
-
/*
* For THP, we have to assume the worse case ie pmd for invalidation.
* For hugetlb, it could be much worse if we need to do pud
@@ -1651,6 +1648,8 @@ static bool try_to_unmap_one(struct foli
range.end = vma_address_end(&pvmw);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, range.end);
+ if (flags & TTU_SPLIT_HUGE_PMD)
+ align_huge_pmd_range(vma, &range.start, &range.end);
if (folio_test_hugetlb(folio)) {
/*
* If sharing is possible, start and end will be adjusted
@@ -1665,9 +1664,6 @@ static bool try_to_unmap_one(struct foli
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
- /* Unexpected PMD-mapped THP? */
- VM_BUG_ON_FOLIO(!pvmw.pte, folio);
-
/*
* If the folio is in an mlock()d vma, we must not swap it out.
*/
@@ -1679,6 +1675,22 @@ static bool try_to_unmap_one(struct foli
goto walk_done_err;
}
+ if (!pvmw.pte && (flags & TTU_SPLIT_HUGE_PMD)) {
+ /*
+ * We temporarily have to drop the PTL and start once
+ * again from that now-PTE-mapped page table.
+ */
+ split_huge_pmd_locked(vma, range.start, pvmw.pmd, false,
+ folio);
+ pvmw.pmd = NULL;
+ spin_unlock(pvmw.ptl);
+ flags &= ~TTU_SPLIT_HUGE_PMD;
+ continue;
+ }
+
+ /* Unexpected PMD-mapped THP? */
+ VM_BUG_ON_FOLIO(!pvmw.pte, folio);
+
pfn = pte_pfn(ptep_get(pvmw.pte));
subpage = folio_page(folio, pfn - folio_pfn(folio));
address = pvmw.address;
_
Patches currently in -mm which might be from ioworker0@xxxxxxxxx are
mm-madvise-introduce-clear_young_dirty_ptes-batch-helper.patch
mm-arm64-override-clear_young_dirty_ptes-batch-helper.patch
mm-memory-add-any_dirty-optional-pointer-to-folio_pte_batch.patch
mm-madvise-optimize-lazyfreeing-with-mthp-in-madvise_free.patch
mm-rmap-remove-duplicated-exit-code-in-pagewalk-loop.patch
mm-rmap-integrate-pmd-mapped-folio-splitting-into-pagewalk-loop.patch
mm-vmscan-avoid-split-lazyfree-thp-during-shrink_folio_list.patch
