[PATCH v3 2/3] mm/khugepaged: Fix GUP-fast interaction by sending IPI

[Jann Horn]

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.

Cc: stable@xxxxxxxxxx
Fixes: ba76149f47d8 ("thp: khugepaged")
Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
---
replaced the mmu_gather-based scheme with an RCU call as suggested by
Peter Xu

 include/asm-generic/tlb.h | 4 ++++
 mm/khugepaged.c           | 2 ++
 mm/mmu_gather.c           | 4 +---
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 492dce43236ea..cab7cfebf40bd 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -222,12 +222,16 @@ 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 674b111a24fa7..c3d3ce596bff7 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1057,6 +1057,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	_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);
 	result =  __collapse_huge_page_isolate(vma, address, pte, cc,
@@ -1415,6 +1416,7 @@ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *v
 		lockdep_assert_held_write(&vma->anon_vma->root->rwsem);
 
 	pmd = pmdp_collapse_flush(vma, addr, pmdp);
+	tlb_remove_table_sync_one();
 	mm_dec_nr_ptes(mm);
 	page_table_check_pte_clear_range(mm, addr, pmd);
 	pte_free(mm, pmd_pgtable(pmd));
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index add4244e5790d..3a2c3f8cad2fe 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -153,7 +153,7 @@ 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
@@ -177,8 +177,6 @@ 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);
-- 
2.38.1.584.g0f3c55d4c2-goog