mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH v2] mm: use memory barriers for non PMD-sized folios to sync
@ 2026-11-17  7:00 Baolin Wang
  2026-11-17 13:53 ` Lorenzo Stoakes (ARM)
  0 siblings, 1 reply; 2+ messages in thread
From: Baolin Wang @ 2026-11-17  7:00 UTC (permalink / raw)
  To: akpm, david, ljs
  Cc: riel, liam, vbabka, harry, jannh, lance.yang, rppt, surenb,
	mhocko, baolin.wang, linux-mm, linux-kernel

Commit 243cf1f67b36 ("mm: memory: fix truncation removing mapped folios")
uses PMD lock via sync_with_folio_pmd_zap() to synchronize when a cleared
PMD is found while unmapping a folio.

However, for non PMD-sized folios, the only PMD clear that can race with
this unmap is PTE table reclaim, which clears the PMD only after the rmaps
for the table have been removed. This is plain message passing, and taking
the PMD lock is more than needed, like I did in the previous patch[1].

Without barriers, the walker can observe the cleared PMD but a stale
mapcount on weakly ordered architectures:

CPU 0 (unmap folio)                 CPU 1 (MADV_DONTNEED, full PMD)
================================    ================================
folio_lock()
                                    lock(ptl)
                                    clear PTEs
                                    remove rmaps   /* W mapcount */
[mapcount load satisfied early,
 folio still mapped]
                                    pmd_clear()    /* W pmd */
                                    unlock(ptl)
pmdp_get_lockless() -> none         /* R pmd */
skip the PMD
folio_mapped() -> true              /* R mapcount, stale */
unmapping assumed to have failed

Pairing an smp_wmb() before the PMD clear with an smp_rmb() after the
PMD read forbids this outcome:

CPU 0 (unmap folio)                 CPU 1 (MADV_DONTNEED, full PMD)
================================    ================================
                                    remove rmaps   /* W mapcount */
                                    smp_wmb()
                                    pmd_clear()    /* W pmd */
pmdp_get_lockless() -> none         /* R pmd */
smp_rmb()
folio_mapped()                      /* R mapcount */

If R pmd observes W pmd, R mapcount must observe W mapcount, so
folio_mapped() no longer reports the removed mappings.

Pass a 'folio' parameter to sync_with_folio_pmd_zap(), allowing us to
skip those pfn walkers: pfn_mkclean_range and mapping_wrprotect_range,
which don't need synchronization.

Similarly, skip sync for page_mapped_in_vma() since the subsequent
operations don't check the folio's mapcount.

No changes for PMD-sized folios unmapping.

[1] https://lore.kernel.org/all/542c97482eae84f86704bcee56482633d1b32321.1791616645.git.baolin.wang@linux.alibaba.com/
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
Changes from v1:
 - Pass in a folio for sync_with_folio_pmd_zap(), per David.
---
 include/linux/rmap.h |  2 ++
 mm/internal.h        | 26 ++++++++++++++++++++++----
 mm/memory.c          | 12 ++++++++++--
 mm/page_vma_mapped.c |  4 ++--
 4 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 74cca0e3c726..62e7341de179 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -862,6 +862,7 @@ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
 #define PVMW_PGTABLE_CROSSED	(1 << 16)
 
 struct page_vma_mapped_walk {
+	struct folio *folio;
 	unsigned long pfn;
 	unsigned long nr_pages;
 	pgoff_t pgoff;	/* Only meaningful if nr_pages > 1 and not a KSM walk */
@@ -876,6 +877,7 @@ struct page_vma_mapped_walk {
 
 #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags)	\
 	struct page_vma_mapped_walk name = {				\
+		.folio = _folio,					\
 		.pfn = folio_pfn(_folio),				\
 		.nr_pages = folio_nr_pages(_folio),			\
 		.pgoff = folio_pgoff(_folio),				\
diff --git a/mm/internal.h b/mm/internal.h
index cd3675c044e0..ad7e051cb198 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -592,6 +592,7 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
  * sync_with_folio_pmd_zap - sync with concurrent zapping of folios
  * @mm: The mm_struct.
  * @pmdp: Pointer to the pmd that was found to be pmd_none().
+ * @folio: The folio being zapped.
  *
  * When we find a pmd_none() while unmapping a folio without holding the PTL,
  * zap_huge_pmd() may have cleared the PMD but not yet updated the folio
@@ -600,13 +601,30 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
  * against later mapcount reads. Skipping the PMD without synchronization
  * could make folio unmapping code assume that unmapping failed.
  *
- * Wait for concurrent zapping to complete by grabbing the PTL.
+ * Wait for concurrent zapping to complete by grabbing the PTL for PMD-sized
+ * folios, otherwise smp_rmb() is sufficient.
  */
-static inline void sync_with_folio_pmd_zap(struct mm_struct *mm, pmd_t *pmdp)
+static inline void sync_with_folio_pmd_zap(struct mm_struct *mm,
+		pmd_t *pmdp, struct folio *folio)
 {
-	spinlock_t *ptl = pmd_lock(mm, pmdp);
+	if (folio_test_pmd_mappable(folio)) {
+		spinlock_t *ptl = pmd_lock(mm, pmdp);
 
-	spin_unlock(ptl);
+		spin_unlock(ptl);
+		return;
+	}
+
+	/*
+	 * For non PMD-sized folios zapping, concurrent zap_empty_pte_table()
+	 * may clear the PMD after the rmaps for the table have been removed,
+	 * but later mapcount reads could still be observed before the PMD
+	 * read, making the folio appear to be still mapped after unmapping.
+	 * Order the PMD read before later mapcount reads, so that observing
+	 * the cleared PMD implies observing the rmap removals.
+	 *
+	 * Pairs with smp_wmb() in zap_pte_range().
+	 */
+	smp_rmb();
 }
 
 struct zap_details;
diff --git a/mm/memory.c b/mm/memory.c
index 529a9189e426..dcf205175f71 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2054,8 +2054,15 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	 * Clear the PMD after the rmaps for the table have been removed, in case
 	 * an incorrect mapcount is observed after unmapping the folio.
 	 */
-	if (can_reclaim_pt && direct_reclaim && addr == end)
+	if (can_reclaim_pt && direct_reclaim && addr == end) {
+		/*
+		 * rmap changes need to be observed before page tables get zapped.
+		 *
+		 * Pairs with smp_rmb() in sync_with_folio_pmd_zap().
+		 */
+		smp_wmb();
 		direct_reclaim = zap_empty_pte_table(mm, pmd, ptl, &pmdval);
+	}
 	pte_unmap_unlock(start_pte, ptl);
 
 	/*
@@ -2110,7 +2117,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 			/* fall through */
 		} else if (pmd_none(*pmd)) {
 			if (details && details->single_folio)
-				sync_with_folio_pmd_zap(tlb->mm, pmd);
+				sync_with_folio_pmd_zap(tlb->mm, pmd,
+							details->single_folio);
 			addr = next;
 			continue;
 		}
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index a931243ca42b..9b72ac408c70 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -294,8 +294,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 			spin_unlock(pvmw->ptl);
 			pvmw->ptl = NULL;
 		} else if (!pmd_present(pmde)) {
-			if (pvmw->flags & PVMW_SYNC)
-				sync_with_folio_pmd_zap(mm, pvmw->pmd);
+			if ((pvmw->flags & PVMW_SYNC) && pvmw->folio)
+				sync_with_folio_pmd_zap(mm, pvmw->pmd, pvmw->folio);
 
 			goto next_pmd;
 		}
-- 
2.47.3


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2026-11-17 13:54 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-17  7:00 [PATCH v2] mm: use memory barriers for non PMD-sized folios to sync Baolin Wang
2026-11-17 13:53 ` Lorenzo Stoakes (ARM)

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®