commit 2ba99c5e08812494bc57f319fb562f527d9bacd8 upstream.
Since commit 70cbc3cc78a99 ("mm: gup: fix the fast GUP race against THP
collapse"), the lockless_pages_from_mm() fastpath rechecks the pmd_t to
ensure that the page table was not removed by khugepaged in between.
However, lockless_pages_from_mm() still requires that the page table is
not concurrently freed. Fix it by sending IPIs (if the architecture uses
semi-RCU-style page table freeing) before freeing/reusing page tables.
Link: https://lkml.kernel.org/r/20221129154730.2274278-2-jannh@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20221128180252.1684965-2-jannh@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20221125213714.4115729-2-jannh@xxxxxxxxxx
Fixes: ba76149f47d8 ("thp: khugepaged")
Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
Acked-by: David Hildenbrand <david@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
[manual backport: two of the three places in khugepaged that can free
ptes were refactored into a common helper between 5.15 and 6.0]
Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
---
include/asm-generic/tlb.h | 4 ++++
mm/khugepaged.c | 3 +++
mm/mmu_gather.c | 4 +---
3 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 71942a1c642d..c99710b3027a 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -207,12 +207,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#define tlb_needs_table_invalidate() (true)
#endif
+void tlb_remove_table_sync_one(void);
+
#else
#ifdef tlb_needs_table_invalidate
#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
#endif
+static inline void tlb_remove_table_sync_one(void) { }
+
#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index fc02de08e912..1735123e462a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1156,6 +1156,7 @@ static void collapse_huge_page(struct mm_struct *mm,
_pmd = pmdp_collapse_flush(vma, address, pmd);
spin_unlock(pmd_ptl);
mmu_notifier_invalidate_range_end(&range);
+ tlb_remove_table_sync_one();
spin_lock(pte_ptl);
isolated = __collapse_huge_page_isolate(vma, address, pte,
@@ -1537,6 +1538,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
/* step 4: collapse pmd */
_pmd = pmdp_collapse_flush(vma, haddr, pmd);
mm_dec_nr_ptes(mm);
+ tlb_remove_table_sync_one();
pte_free(mm, pmd_pgtable(_pmd));
i_mmap_unlock_write(vma->vm_file->f_mapping);
@@ -1623,6 +1625,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
/* assume page table is clear */
_pmd = pmdp_collapse_flush(vma, addr, pmd);
mm_dec_nr_ptes(mm);
+ tlb_remove_table_sync_one();
pte_free(mm, pmd_pgtable(_pmd));
}
mmap_write_unlock(mm);
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 1b9837419bf9..8be26c7ddb47 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -139,7 +139,7 @@ static void tlb_remove_table_smp_sync(void *arg)
/* Simply deliver the interrupt */
}
-static void tlb_remove_table_sync_one(void)
+void tlb_remove_table_sync_one(void)
{
/*
* This isn't an RCU grace period and hence the page-tables cannot be
@@ -163,8 +163,6 @@ static void tlb_remove_table_free(struct mmu_table_batch *batch)
#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
-static void tlb_remove_table_sync_one(void) { }
-
static void tlb_remove_table_free(struct mmu_table_batch *batch)
{
__tlb_remove_table_free(batch);
--
2.39.0.rc0.267.gcb52ba06e7-goog
