summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorMike Kravetz <mike.kravetz@oracle.com>2018-10-06 01:51:29 +0300
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2018-10-13 10:27:22 +0300
commit5f4f5b1f4491627f83d6b1bd2ac7b7c5b87e5f0e (patch)
treebd075a38e23647e64ee7f47aaccb2664e3d3cf21 /include
parentab18409cf05f8e3d20ae3e5347f431947ecc397c (diff)
downloadlinux-5f4f5b1f4491627f83d6b1bd2ac7b7c5b87e5f0e.tar.xz
mm: migration: fix migration of huge PMD shared pages
commit 017b1660df89f5fb4bfe66c34e35f7d2031100c7 upstream. The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page. This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost. This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated. To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB. mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case. Link: http://lkml.kernel.org/r/20180823205917.16297-2-mike.kravetz@oracle.com [mike.kravetz@oracle.com: make _range_in_vma() a static inline] Link: http://lkml.kernel.org/r/6063f215-a5c8-2f0c-465a-2c515ddc952d@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/hugetlb.h14
-rw-r--r--include/linux/mm.h6
2 files changed, 20 insertions, 0 deletions
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 82a25880714a..7aa2de25c09c 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
pte_t *huge_pte_offset(struct mm_struct *mm,
unsigned long addr, unsigned long sz);
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
int write);
struct page *follow_huge_pd(struct vm_area_struct *vma,
@@ -169,6 +171,18 @@ static inline unsigned long hugetlb_total_pages(void)
return 0;
}
+static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
+ pte_t *ptep)
+{
+ return 0;
+}
+
+static inline void adjust_range_if_pmd_sharing_possible(
+ struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end)
+{
+}
+
#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; })
#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL)
#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; })
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a26cf767407e..58f2263de4de 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2322,6 +2322,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
return vma;
}
+static inline bool range_in_vma(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ return (vma && vma->vm_start <= start && end <= vma->vm_end);
+}
+
#ifdef CONFIG_MMU
pgprot_t vm_get_page_prot(unsigned long vm_flags);
void vma_set_page_prot(struct vm_area_struct *vma);