diff options
| author | Michel Lespinasse <walken@google.com> | 2012-10-08 16:31:50 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-09 16:22:42 +0900 |
| commit | 38a76013ad809beb0b52f60d365c960d035bd83c (patch) | |
| tree | c63ba707ab17dd1ff1e90650faf74570daa3cf9f /mm/mmap.c | |
| parent | 523d4e2008fd4a68b1a164e63e8c75b7b20f07e0 (diff) | |
| download | linux-3.10-38a76013ad809beb0b52f60d365c960d035bd83c.tar.gz linux-3.10-38a76013ad809beb0b52f60d365c960d035bd83c.tar.bz2 linux-3.10-38a76013ad809beb0b52f60d365c960d035bd83c.zip | |
mm: avoid taking rmap locks in move_ptes()
During mremap(), the destination VMA is generally placed after the
original vma in rmap traversal order: in move_vma(), we always have
new_pgoff >= vma->vm_pgoff, and as a result new_vma->vm_pgoff >=
vma->vm_pgoff unless vma_merge() merged the new vma with an adjacent one.
When the destination VMA is placed after the original in rmap traversal
order, we can avoid taking the rmap locks in move_ptes().
Essentially, this reintroduces the optimization that had been disabled in
"mm anon rmap: remove anon_vma_moveto_tail". The difference is that we
don't try to impose the rmap traversal order; instead we just rely on
things being in the desired order in the common case and fall back to
taking locks in the uncommon case. Also we skip the i_mmap_mutex in
addition to the anon_vma lock: in both cases, the vmas are traversed in
increasing vm_pgoff order with ties resolved in tree insertion order.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mmap.c')
| -rw-r--r-- | mm/mmap.c | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/mm/mmap.c b/mm/mmap.c index 81248992120..2d942353d68 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2371,7 +2371,8 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, - unsigned long addr, unsigned long len, pgoff_t pgoff) + unsigned long addr, unsigned long len, pgoff_t pgoff, + bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; @@ -2413,8 +2414,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, * linear if there are no pages mapped yet. */ VM_BUG_ON(faulted_in_anon_vma); - *vmap = new_vma; + *vmap = vma = new_vma; } + *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (new_vma) { @@ -2434,6 +2436,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); + *need_rmap_locks = false; } } return new_vma; |