diff options
| author | Peter Zijlstra <a.p.zijlstra@chello.nl> | 2010-10-28 02:32:58 +0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-10-28 05:03:05 +0400 |
| commit | 20273941f2129aa5a432796d98a276ed73d60782 (patch) | |
| tree | 85da0d951ac10f239f81ad7f69559fdeb692095b /include/linux | |
| parent | a8e23a291852cd7c4fb5ca696dbb93912185ad10 (diff) | |
| download | linux-20273941f2129aa5a432796d98a276ed73d60782.tar.xz | |
mm: fix race in kunmap_atomic()
Christoph reported a nice splat which illustrated a race in the new stack
based kmap_atomic implementation.
The problem is that we pop our stack slot before we're completely done
resetting its state -- in particular clearing the PTE (sometimes that's
CONFIG_DEBUG_HIGHMEM). If an interrupt happens before we actually clear
the PTE used for the last slot, that interrupt can reuse the slot in a
dirty state, which triggers a BUG in kmap_atomic().
Fix this by introducing kmap_atomic_idx() which reports the current slot
index without actually releasing it and use that to find the PTE and delay
the _pop() until after we're completely done.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reported-by: Christoph Hellwig <hch@infradead.org>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/highmem.h | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 102f76be90da..e9138198e823 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -88,6 +88,11 @@ static inline int kmap_atomic_idx_push(void) return idx; } +static inline int kmap_atomic_idx(void) +{ + return __get_cpu_var(__kmap_atomic_idx) - 1; +} + static inline int kmap_atomic_idx_pop(void) { int idx = --__get_cpu_var(__kmap_atomic_idx); |