Revision a247c3a97a0216b18a46243eda26081f1928ec37 authored by Andrea Arcangeli on 22 September 2010, 20:05:12 UTC, committed by Linus Torvalds on 23 September 2010, 00:22:39 UTC
The below bug in fork led to the rmap walk finding the parent huge-pmd twice instead of just once, because the anon_vma_chain objects of the child vma still point to the vma->vm_mm of the parent. The patch fixes it by making the rmap walk accurate during fork. It's not a big deal normally but it worth being accurate considering the cost is the same. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent df08cdc
File | Mode | Size |
---|---|---|
.gitignore | -rw-r--r-- | 20 bytes |
00-INDEX | -rw-r--r-- | 1.2 KB |
Makefile | -rw-r--r-- | 263 bytes |
active_mm.txt | -rw-r--r-- | 3.7 KB |
balance | -rw-r--r-- | 5.0 KB |
hugepage-mmap.c | -rw-r--r-- | 2.0 KB |
hugepage-shm.c | -rw-r--r-- | 2.5 KB |
hugetlbpage.txt | -rw-r--r-- | 14.8 KB |
hwpoison.txt | -rw-r--r-- | 5.6 KB |
ksm.txt | -rw-r--r-- | 4.3 KB |
locking | -rw-r--r-- | 6.0 KB |
map_hugetlb.c | -rw-r--r-- | 1.7 KB |
numa | -rw-r--r-- | 8.7 KB |
numa_memory_policy.txt | -rw-r--r-- | 22.6 KB |
overcommit-accounting | -rw-r--r-- | 2.2 KB |
page-types.c | -rw-r--r-- | 21.4 KB |
page_migration | -rw-r--r-- | 6.5 KB |
pagemap.txt | -rw-r--r-- | 5.5 KB |
slabinfo.c | -rw-r--r-- | 32.4 KB |
slub.txt | -rw-r--r-- | 10.2 KB |
unevictable-lru.txt | -rw-r--r-- | 32.9 KB |
Computing file changes ...