The patch titled
Subject: hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix
has been added to the -mm tree. Its filename is
hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix.patch
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 and is updated
there every 3-4 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix
It would be better to make an explicit check for mapping != null before
calling i_mmap_lock_write/try_to_unmap. In this way, unrelated changes to
code above will not potentially lead to the possibility of mapping ==
null.
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: "Kirill A . Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: Prakash Sangappa <prakash.sangappa@xxxxxxxxxx>
Cc: Colin Ian King <colin.king@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/mm/hugetlb.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix
+++ a/mm/hugetlb.c
@@ -3250,6 +3250,14 @@ int copy_hugetlb_page_range(struct mm_st
mmu_notifier_range_init(&range, src, vma->vm_start,
vma->vm_end, MMU_NOTIFY_CLEAR);
mmu_notifier_invalidate_range_start(&range);
+ } else {
+ /*
+ * For shared mappings i_mmap_rwsem must be held to call
+ * huge_pte_alloc, otherwise the returned ptep could go
+ * away if part of a shared pmd and another thread calls
+ * huge_pmd_unshare.
+ */
+ i_mmap_lock_read(mapping);
}
for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
@@ -3259,18 +3267,8 @@ int copy_hugetlb_page_range(struct mm_st
if (!src_pte)
continue;
- /*
- * i_mmap_rwsem must be held to call huge_pte_alloc.
- * Continue to hold until finished with dst_pte, otherwise
- * it could go away if part of a shared pmd.
- *
- * Technically, i_mmap_rwsem is only needed in the non-cow
- * case as cow mappings are not shared.
- */
- i_mmap_lock_read(mapping);
dst_pte = huge_pte_alloc(dst, addr, sz);
if (!dst_pte) {
- i_mmap_unlock_read(mapping);
ret = -ENOMEM;
break;
}
@@ -3285,10 +3283,8 @@ int copy_hugetlb_page_range(struct mm_st
* after taking the lock below.
*/
dst_entry = huge_ptep_get(dst_pte);
- if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) {
- i_mmap_unlock_read(mapping);
+ if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
continue;
- }
dst_ptl = huge_pte_lock(h, dst, dst_pte);
src_ptl = huge_pte_lockptr(h, src, src_pte);
@@ -3337,12 +3333,12 @@ int copy_hugetlb_page_range(struct mm_st
}
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
-
- i_mmap_unlock_read(mapping);
}
if (cow)
mmu_notifier_invalidate_range_end(&range);
+ else
+ i_mmap_unlock_read(mapping);
return ret;
}
--- a/mm/memory-failure.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix
+++ a/mm/memory-failure.c
@@ -966,7 +966,7 @@ static bool hwpoison_user_mappings(struc
enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
LIST_HEAD(tokill);
- bool unmap_success;
+ bool unmap_success = true;
int kill = 1, forcekill;
struct page *hpage = *hpagep;
bool mlocked = PageMlocked(hpage);
@@ -1030,7 +1030,7 @@ static bool hwpoison_user_mappings(struc
if (!PageHuge(hpage)) {
unmap_success = try_to_unmap(hpage, ttu);
- } else {
+ } else if (mapping) {
/*
* For hugetlb pages, try_to_unmap could potentially call
* huge_pmd_unshare. Because of this, take semaphore in
--- a/mm/rmap.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix
+++ a/mm/rmap.c
@@ -25,6 +25,7 @@
* page->flags PG_locked (lock_page)
* hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
* mapping->i_mmap_rwsem
+ * hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
* anon_vma->rwsem
* mm->page_table_lock or pte_lock
* zone_lru_lock (in mark_page_accessed, isolate_lru_page)
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization.patch
hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization-fix.patch
hugetlbfs-use-i_mmap_rwsem-to-fix-page-fault-truncate-race.patch
