summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorMike Kravetz <mike.kravetz@oracle.com>2019-01-08 15:23:32 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-01-08 17:15:11 -0800
commite7c58097793ef15d58fadf190ee58738fbf447cd (patch)
tree7dd04f50d4daadba4f8f3550a6d39d1a0ac2cda7 /mm
parent8ab88c7169b7fba98812ead6524b9d05bc76cf00 (diff)
downloadlinux-e7c58097793ef15d58fadf190ee58738fbf447cd.tar.gz
linux-e7c58097793ef15d58fadf190ee58738fbf447cd.tar.bz2
linux-e7c58097793ef15d58fadf190ee58738fbf447cd.zip
hugetlbfs: revert "Use i_mmap_rwsem to fix page fault/truncate race"
This reverts c86aa7bbfd5568ba8a82d3635d8f7b8a8e06fe54 The reverted commit caused ABBA deadlocks when file migration raced with file eviction for specific hugetlbfs files. This was discovered with a modified version of the LTP move_pages12 test. The purpose of the reverted patch was to close a long existing race between hugetlbfs file truncation and page faults. After more analysis of the patch and impacted code, it was determined that i_mmap_rwsem can not be used for all required synchronization. Therefore, revert this patch while working an another approach to the underlying issue. Link: http://lkml.kernel.org/r/20190103235452.29335-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Jan Stancek <jstancek@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Prakash Sangappa <prakash.sangappa@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/hugetlb.c21
1 files changed, 11 insertions, 10 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 745088810965..aedc1b183cf9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3755,16 +3755,16 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
}
/*
- * We can not race with truncation due to holding i_mmap_rwsem.
- * Check once here for faults beyond end of file.
+ * Use page lock to guard against racing truncation
+ * before we get page_table_lock.
*/
- size = i_size_read(mapping->host) >> huge_page_shift(h);
- if (idx >= size)
- goto out;
-
retry:
page = find_lock_page(mapping, idx);
if (!page) {
+ size = i_size_read(mapping->host) >> huge_page_shift(h);
+ if (idx >= size)
+ goto out;
+
/*
* Check for page in userfault range
*/
@@ -3854,6 +3854,9 @@ retry:
}
ptl = huge_pte_lock(h, mm, ptep);
+ size = i_size_read(mapping->host) >> huge_page_shift(h);
+ if (idx >= size)
+ goto backout;
ret = 0;
if (!huge_pte_none(huge_ptep_get(ptep)))
@@ -3956,10 +3959,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
/*
* Acquire i_mmap_rwsem before calling huge_pte_alloc and hold
- * until finished with ptep. This serves two purposes:
- * 1) It prevents huge_pmd_unshare from being called elsewhere
- * and making the ptep no longer valid.
- * 2) It synchronizes us with file truncation.
+ * until finished with ptep. This prevents huge_pmd_unshare from
+ * being called elsewhere and making the ptep no longer valid.
*
* ptep could have already be assigned via huge_pte_offset. That
* is OK, as huge_pte_alloc will return the same value unless