The patch titled
Subject: hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
hugetlb-dont-delete-vma_lock-in-hugetlb-madv_dontneed-processing.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlb-dont-delete-vma_lock-in-hugetlb-madv_dontneed-processing.patch
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing
Date: Sat, 22 Oct 2022 19:50:47 -0700
madvise(MADV_DONTNEED) ends up calling zap_page_range() to clear the page
tables associated with the address range. For hugetlb vmas,
zap_page_range will call __unmap_hugepage_range_final. However,
__unmap_hugepage_range_final assumes the passed vma is about to be removed
and deletes the vma_lock to prevent pmd sharing as the vma is on the way
out. In the case of madvise(MADV_DONTNEED) the vma remains, but the
missing vma_lock prevents pmd sharing and could potentially lead to issues
with truncation/fault races.
This issue was originally reported here [1] as a BUG triggered in
page_try_dup_anon_rmap. Prior to the introduction of the hugetlb
vma_lock, __unmap_hugepage_range_final cleared the VM_MAYSHARE flag to
prevent pmd sharing. Subsequent faults on this vma were confused as
VM_MAYSHARE indicates a sharable vma, but was not set so page_mapping was
not set in new pages added to the page table. This resulted in pages that
appeared anonymous in a VM_SHARED vma and triggered the BUG.
Create a new routine clear_hugetlb_page_range() that can be called from
madvise(MADV_DONTNEED) for hugetlb vmas. It has the same setup as
zap_page_range, but does not delete the vma_lock.
[1] https://lore.kernel.org/lkml/CAO4mrfdLMXsao9RF4fUE8-Wfde8xmjsKrTNMNC9wjUb6JudD0g@xxxxxxxxxxxxxx/
Link: https://lkml.kernel.org/r/20221023025047.470646-1-mike.kravetz@xxxxxxxxxx
Fixes: 90e7e7f5ef3f ("mm: enable MADV_DONTNEED for hugetlb mappings")
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Reported-by: Wei Chen <harperchen1110@xxxxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Mina Almasry <almasrymina@xxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 7 ++++
mm/hugetlb.c | 62 ++++++++++++++++++++++++++++++--------
mm/madvise.c | 5 ++-
3 files changed, 61 insertions(+), 13 deletions(-)
--- a/include/linux/hugetlb.h~hugetlb-dont-delete-vma_lock-in-hugetlb-madv_dontneed-processing
+++ a/include/linux/hugetlb.h
@@ -156,6 +156,8 @@ long follow_hugetlb_page(struct mm_struc
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *,
zap_flags_t);
+void clear_hugetlb_page_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
@@ -460,6 +462,11 @@ static inline void __unmap_hugepage_rang
BUG();
}
+static void __maybe_unused clear_hugetlb_page_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+
static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
unsigned int flags)
--- a/mm/hugetlb.c~hugetlb-dont-delete-vma_lock-in-hugetlb-madv_dontneed-processing
+++ a/mm/hugetlb.c
@@ -5194,28 +5194,66 @@ static void __unmap_hugepage_range(struc
tlb_flush_mmu_tlbonly(tlb);
}
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+static void __unmap_hugepage_range_locking(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page,
- zap_flags_t zap_flags)
+ zap_flags_t zap_flags, bool final)
{
hugetlb_vma_lock_write(vma);
i_mmap_lock_write(vma->vm_file->f_mapping);
__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
- /*
- * Unlock and free the vma lock before releasing i_mmap_rwsem. When
- * the vma_lock is freed, this makes the vma ineligible for pmd
- * sharing. And, i_mmap_rwsem is required to set up pmd sharing.
- * This is important as page tables for this unmapped range will
- * be asynchrously deleted. If the page tables are shared, there
- * will be issues when accessed by someone else.
- */
- __hugetlb_vma_unlock_write_free(vma);
+ if (final) {
+ /*
+ * Unlock and free the vma lock before releasing i_mmap_rwsem.
+ * When the vma_lock is freed, this makes the vma ineligible
+ * for pmd sharing. And, i_mmap_rwsem is required to set up
+ * pmd sharing. This is important as page tables for this
+ * unmapped range will be asynchrously deleted. If the page
+ * tables are shared, there will be issues when accessed by
+ * someone else.
+ */
+ __hugetlb_vma_unlock_write_free(vma);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+ } else {
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+ hugetlb_vma_unlock_write(vma);
+ }
+}
+
+void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, struct page *ref_page,
+ zap_flags_t zap_flags)
+{
+ __unmap_hugepage_range_locking(tlb, vma, start, end, ref_page,
+ zap_flags, true);
+}
+
+#ifdef CONFIG_ADVISE_SYSCALLS
+/*
+ * Similar setup as in zap_page_range(). madvise(MADV_DONTNEED) can not call
+ * zap_page_range for hugetlb vmas as __unmap_hugepage_range_final will delete
+ * the associated vma_lock.
+ */
+void clear_hugetlb_page_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+{
+ struct mmu_notifier_range range;
+ struct mmu_gather tlb;
+
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ start, end);
+ tlb_gather_mmu(&tlb, vma->vm_mm);
+ update_hiwater_rss(vma->vm_mm);
+
+ __unmap_hugepage_range_locking(&tlb, vma, start, end, NULL, 0, false);
- i_mmap_unlock_write(vma->vm_file->f_mapping);
+ mmu_notifier_invalidate_range_end(&range);
+ tlb_finish_mmu(&tlb);
}
+#endif
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page,
--- a/mm/madvise.c~hugetlb-dont-delete-vma_lock-in-hugetlb-madv_dontneed-processing
+++ a/mm/madvise.c
@@ -790,7 +790,10 @@ static int madvise_free_single_vma(struc
static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- zap_page_range(vma, start, end - start);
+ if (!is_vm_hugetlb_page(vma))
+ zap_page_range(vma, start, end - start);
+ else
+ clear_hugetlb_page_range(vma, start, end);
return 0;
}
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlb-dont-delete-vma_lock-in-hugetlb-madv_dontneed-processing.patch
hugetlb-simplify-hugetlb-handling-in-follow_page_mask.patch
