summaryrefslogtreecommitdiff
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
authorMel Gorman <mel@csn.ul.ie>2009-02-10 14:02:27 +0000
committerLinus Torvalds <torvalds@linux-foundation.org>2009-02-10 10:48:42 -0800
commit5a6fe125950676015f5108fb71b2a67441755003 (patch)
treec985fac46de39392466c4917c497b50bdc9c0757 /mm/hugetlb.c
parent4c098bcd55fad34dcf224bf8343db6a9ac58fc68 (diff)
Do not account for the address space used by hugetlbfs using VM_ACCOUNT
When overcommit is disabled, the core VM accounts for pages used by anonymous shared, private mappings and special mappings. It keeps track of VMAs that should be accounted for with VM_ACCOUNT and VMAs that never had a reserve with VM_NORESERVE. Overcommit for hugetlbfs is much riskier than overcommit for base pages due to contiguity requirements. It avoids overcommiting on both shared and private mappings using reservation counters that are checked and updated during mmap(). This ensures (within limits) that hugepages exist in the future when faults occurs or it is too easy to applications to be SIGKILLed. As hugetlbfs makes its own reservations of a different unit to the base page size, VM_ACCOUNT should never be set. Even if the units were correct, we would double account for the usage in the core VM and hugetlbfs. VM_NORESERVE may be set because an application can request no reserves be made for hugetlbfs at the risk of getting killed later. With commit fc8744adc870a8d4366908221508bb113d8b72ee, VM_NORESERVE and VM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This breaks the accounting for both the core VM and hugetlbfs, can trigger an OOM storm when hugepage pools are too small lockups and corrupted counters otherwise are used. This patch brings hugetlbfs more in line with how the core VM treats VM_NORESERVE but prevents VM_ACCOUNT being set. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c39
1 files changed, 25 insertions, 14 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 618e98304080..207464209546 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2269,14 +2269,12 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
int hugetlb_reserve_pages(struct inode *inode,
long from, long to,
- struct vm_area_struct *vma)
+ struct vm_area_struct *vma,
+ int acctflag)
{
- long ret, chg;
+ long ret = 0, chg;
struct hstate *h = hstate_inode(inode);
- if (vma && vma->vm_flags & VM_NORESERVE)
- return 0;
-
/*
* Shared mappings base their reservation on the number of pages that
* are already allocated on behalf of the file. Private mappings need
@@ -2285,22 +2283,25 @@ int hugetlb_reserve_pages(struct inode *inode,
*/
if (!vma || vma->vm_flags & VM_SHARED)
chg = region_chg(&inode->i_mapping->private_list, from, to);
- else {
- struct resv_map *resv_map = resv_map_alloc();
- if (!resv_map)
- return -ENOMEM;
-
+ else
chg = to - from;
- set_vma_resv_map(vma, resv_map);
- set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
- }
-
if (chg < 0)
return chg;
if (hugetlb_get_quota(inode->i_mapping, chg))
return -ENOSPC;
+
+ /*
+ * Only apply hugepage reservation if asked. We still have to
+ * take the filesystem quota because it is an upper limit
+ * defined for the mount and not necessarily memory as a whole
+ */
+ if (acctflag & VM_NORESERVE) {
+ reset_vma_resv_huge_pages(vma);
+ return 0;
+ }
+
ret = hugetlb_acct_memory(h, chg);
if (ret < 0) {
hugetlb_put_quota(inode->i_mapping, chg);
@@ -2308,6 +2309,16 @@ int hugetlb_reserve_pages(struct inode *inode,
}
if (!vma || vma->vm_flags & VM_SHARED)
region_add(&inode->i_mapping->private_list, from, to);
+ else {
+ struct resv_map *resv_map = resv_map_alloc();
+
+ if (!resv_map)
+ return -ENOMEM;
+
+ set_vma_resv_map(vma, resv_map);
+ set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
+ }
+
return 0;
}