projects
/
openwrt
/
staging
/
blogic.git
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
| inline |
side by side
(parent:
f2deae9
)
Revert "Ignore madvise(MADV_WILLNEED) for hugetlbfs-backed regions"
author
Linus Torvalds
<
[email protected]
>
Wed, 13 May 2009 15:29:12 +0000
(08:29 -0700)
committer
Linus Torvalds
<
[email protected]
>
Wed, 13 May 2009 15:29:12 +0000
(08:29 -0700)
This reverts commit
a425a638c858fd10370b573bde81df3ba500e271
.
Now that the previous commit removed the "readpage" actor for hugetlb
files, read-ahead will no longer mess up the mapping, and there's no
longer any reason to treat hugetlbfs mappings specially.
Tested-and-acked-by: Mel Gorman <
[email protected]
>
Signed-off-by: Linus Torvalds <
[email protected]
>
mm/madvise.c
patch
|
blob
|
history
diff --git
a/mm/madvise.c
b/mm/madvise.c
index 36d6ea2b63405a8bd682b1e225bb3f748de2eda5..b9ce574827c8a2a48b972f0261decc234edf9e27 100644
(file)
--- a/
mm/madvise.c
+++ b/
mm/madvise.c
@@
-112,14
+112,6
@@
static long madvise_willneed(struct vm_area_struct * vma,
if (!file)
return -EBADF;
- /*
- * Page cache readahead assumes page cache pages are order-0 which
- * is not the case for hugetlbfs. Do not give a bad return value
- * but ignore the advice.
- */
- if (vma->vm_flags & VM_HUGETLB)
- return 0;
-
if (file->f_mapping->a_ops->get_xip_mem) {
/* no bad return value, but ignore advice */
return 0;