From 40bc831ab5f630431010d1ff867390b07418a7ee Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 21 Nov 2021 12:40:07 -0800 Subject: [PATCH] hugetlbfs: flush TLBs correctly after huge_pmd_unshare commit a4a118f2eead1d6c49e00765de89878288d4b890 upstream. When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB flush is missing. This TLB flush must be performed before releasing the i_mmap_rwsem, in order to prevent an unshared PMDs page from being released and reused before the TLB flush took place. Arguably, a comprehensive solution would use mmu_gather interface to batch the TLB flushes and the PMDs page release, however it is not an easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2) deferring the release of the page reference for the PMDs page until after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into thinking PMDs are shared when they are not. Fix __unmap_hugepage_range() by adding the missing TLB flush, and forcing a flush when unshare is successful. Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6 Signed-off-by: Nadav Amit Reviewed-by: Mike Kravetz Cc: Aneesh Kumar K.V Cc: KAMEZAWA Hiroyuki Cc: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6e92ab0..fce705f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3913,6 +3913,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3941,10 +3942,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -4001,6 +4000,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, -- 2.7.4