From: Nadav Amit <namit@xxxxxxxxxx>
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 <namit@xxxxxxxxxx>
Reviewed-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
include/asm-generic/tlb.h | 6 ++++++
mm/hugetlb.c | 19 +++++++++++++++++++
2 files changed, 25 insertions(+)
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -196,6 +196,12 @@ static inline void tlb_remove_check_page
#define tlb_end_vma __tlb_end_vma
#endif
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+ unsigned long address, unsigned long size)
+{
+ __tlb_adjust_range(tlb, address, size);
+}
+
#ifndef __tlb_remove_tlb_entry
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
#endif
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3386,6 +3386,7 @@ void __unmap_hugepage_range(struct mmu_g
unsigned long sz = huge_page_size(h);
const unsigned long mmun_start = start; /* For mmu_notifiers */
const unsigned long mmun_end = end; /* For mmu_notifiers */
+ bool force_flush = false;
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~huge_page_mask(h));
@@ -3407,6 +3408,8 @@ void __unmap_hugepage_range(struct mmu_g
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, &address, ptep)) {
spin_unlock(ptl);
+ tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+ force_flush = true;
continue;
}
@@ -3463,6 +3466,22 @@ void __unmap_hugepage_range(struct mmu_g
}
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
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(tlb);
}
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
