Each page mapped in a process's address space must be correctly
accounted for in _mapcount. Normally the rules for this are
straightforward but hugetlbfs page table sharing is different. The page
table pages at the PMD level are reference counted while the mapcount
remains the same.
If this accounting is wrong, it causes bugs like this one reported by
Larry Woodman:
kernel BUG at mm/filemap.c:135!
invalid opcode: 0000 [#1] SMP
CPU 22
Modules linked in: bridge stp llc sunrpc binfmt_misc dcdbas microcode pcspkr acpi_pad acpi]
Pid: 18001, comm: mpitest Tainted: G W 3.3.0+ #4 Dell Inc. PowerEdge R620/07NDJ2
RIP: 0010:[<ffffffff8112cfed>] [<ffffffff8112cfed>] __delete_from_page_cache+0x15d/0x170
Process mpitest (pid: 18001, threadinfo ffff880428972000, task ffff880428b5cc20)
Call Trace:
delete_from_page_cache+0x40/0x80
truncate_hugepages+0x115/0x1f0
hugetlbfs_evict_inode+0x18/0x30
evict+0x9f/0x1b0
iput_final+0xe3/0x1e0
iput+0x3e/0x50
d_kill+0xf8/0x110
dput+0xe2/0x1b0
__fput+0x162/0x240
During fork(), copy_hugetlb_page_range() detects if huge_pte_alloc()
shared page tables with the check dst_pte == src_pte. The logic is if
the PMD page is the same, they must be shared. This assumes that the
sharing is between the parent and child. However, if the sharing is
with a different process entirely then this check fails as in this
diagram:
parent
|
------------>pmd
src_pte----------> data page
^
other--------->pmd--------------------|
^
child-----------|
dst_pte
For this situation to occur, it must be possible for Parent and Other to
have faulted and failed to share page tables with each other. This is
possible due to the following style of race.
PROC A PROC B
copy_hugetlb_page_range copy_hugetlb_page_range
src_pte == huge_pte_offset src_pte == huge_pte_offset
!src_pte so no sharing !src_pte so no sharing
(time passes)
hugetlb_fault hugetlb_fault
huge_pte_alloc huge_pte_alloc
huge_pmd_share huge_pmd_share
LOCK(i_mmap_mutex)
find nothing, no sharing
UNLOCK(i_mmap_mutex)
LOCK(i_mmap_mutex)
find nothing, no sharing
UNLOCK(i_mmap_mutex)
pmd_alloc pmd_alloc
LOCK(instantiation_mutex)
fault
UNLOCK(instantiation_mutex)
LOCK(instantiation_mutex)
fault
UNLOCK(instantiation_mutex)
These two processes are not poing to the same data page but are not
sharing page tables because the opportunity was missed. When either
process later forks, the src_pte == dst pte is potentially insufficient.
As the check falls through, the wrong PTE information is copied in
(harmless but wrong) and the mapcount is bumped for a page mapped by a
shared page table leading to the BUG_ON.
This patch addresses the issue by moving pmd_alloc into huge_pmd_share
which guarantees that the shared pud is populated in the same critical
section as pmd. This also means that huge_pte_offset test in
huge_pmd_share is serialized correctly now which in turn means that the
success of the sharing will be higher as the racing tasks see the pud
and pmd populated together.
Race identified and changelog written mostly by Mel Gorman.
{akpm@linux-foundation.org: attempt to make the huge_pmd_share() comment comprehensible, clean up coding style]
Reported-by: Larry Woodman <lwoodman@redhat.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Ken Chen <kenchen@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
eb48c07146