aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorCyril Hrubis <chrubis@suse.cz>2013-04-29 15:08:33 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-04-29 15:54:38 -0700
commite8420a8ece80b3fe810415ecf061d54ca7fab266 (patch)
tree0da34b1c39cec5bcf6045ac6ea51155b3692553d /mm
parent70ddf637eebe47e61fb2be08a59315581b6d2f38 (diff)
mm/mmap: check for RLIMIT_AS before unmapping
Fix a corner case for MAP_FIXED when requested mapping length is larger than rlimit for virtual memory. In such case any overlapping mappings are unmapped before we check for the limit and return ENOMEM. The check is moved before the loop that unmaps overlapping parts of existing mappings. When we are about to hit the limit (currently mapped pages + len > limit) we scan for overlapping pages and check again accounting for them. This fixes situation when userspace program expects that the previous mappings are preserved after the mmap() syscall has returned with error. (POSIX clearly states that successfull mapping shall replace any previous mappings.) This corner case was found and can be tested with LTP testcase: testcases/open_posix_testsuite/conformance/interfaces/mmap/24-2.c In this case the mmap, which is clearly over current limit, unmaps dynamic libraries and the testcase segfaults right after returning into userspace. I've also looked at the second instance of the unmapping loop in the do_brk(). The do_brk() is called from brk() syscall and from vm_brk(). The brk() syscall checks for overlapping mappings and bails out when there are any (so it can't be triggered from the brk syscall). The vm_brk() is called only from binmft handlers so it shouldn't be triggered unless binmft handler created overlapping mappings. Signed-off-by: Cyril Hrubis <chrubis@suse.cz> Reviewed-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/mmap.c50
1 files changed, 46 insertions, 4 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index 43c4955535a..da3e9c04bf3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -6,6 +6,7 @@
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
*/
+#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/mm.h>
@@ -550,6 +551,34 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr,
return 0;
}
+static unsigned long count_vma_pages_range(struct mm_struct *mm,
+ unsigned long addr, unsigned long end)
+{
+ unsigned long nr_pages = 0;
+ struct vm_area_struct *vma;
+
+ /* Find first overlaping mapping */
+ vma = find_vma_intersection(mm, addr, end);
+ if (!vma)
+ return 0;
+
+ nr_pages = (min(end, vma->vm_end) -
+ max(addr, vma->vm_start)) >> PAGE_SHIFT;
+
+ /* Iterate over the rest of the overlaps */
+ for (vma = vma->vm_next; vma; vma = vma->vm_next) {
+ unsigned long overlap_len;
+
+ if (vma->vm_start > end)
+ break;
+
+ overlap_len = min(end, vma->vm_end) - vma->vm_start;
+ nr_pages += overlap_len >> PAGE_SHIFT;
+ }
+
+ return nr_pages;
+}
+
void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
struct rb_node **rb_link, struct rb_node *rb_parent)
{
@@ -1442,6 +1471,23 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long charged = 0;
struct inode *inode = file ? file_inode(file) : NULL;
+ /* Check against address space limit. */
+ if (!may_expand_vm(mm, len >> PAGE_SHIFT)) {
+ unsigned long nr_pages;
+
+ /*
+ * MAP_FIXED may remove pages of mappings that intersects with
+ * requested mapping. Account for the pages it would unmap.
+ */
+ if (!(vm_flags & MAP_FIXED))
+ return -ENOMEM;
+
+ nr_pages = count_vma_pages_range(mm, addr, addr + len);
+
+ if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages))
+ return -ENOMEM;
+ }
+
/* Clear old maps */
error = -ENOMEM;
munmap_back:
@@ -1451,10 +1497,6 @@ munmap_back:
goto munmap_back;
}
- /* Check against address space limit. */
- if (!may_expand_vm(mm, len >> PAGE_SHIFT))
- return -ENOMEM;
-
/*
* Private writable mapping: check memory availability
*/