mm: record MAP_NORESERVE status on vmas and fix small page mprotect reservations

With Mel's hugetlb private reservation support patches applied, strict
overcommit semantics are applied to both shared and private huge page
mappings.  This can be a problem if an application relied on unlimited
overcommit semantics for private mappings.  An example of this would be an
application which maps a huge area with the intention of using it very
sparsely.  These application would benefit from being able to opt-out of
the strict overcommit.  It should be noted that prior to hugetlb
supporting demand faulting all mappings were fully populated and so
applications of this type should be rare.

This patch stack implements the MAP_NORESERVE mmap() flag for huge page
mappings.  This flag has the same meaning as for small page mappings,
suppressing reservations for that mapping.

Thanks to Mel Gorman for reviewing a number of early versions of these
patches.

This patch:

When a small page mapping is created with mmap() reservations are created
by default for any memory pages required.  When the region is read/write
the reservation is increased for every page, no reservation is needed for
read-only regions (as they implicitly share the zero page).  Reservations
are tracked via the VM_ACCOUNT vma flag which is present when the region
has reservation backing it.  When we convert a region from read-only to
read-write new reservations are aquired and VM_ACCOUNT is set.  However,
when a read-only map is created with MAP_NORESERVE it is indistinguishable
from a normal mapping.  When we then convert that to read/write we are
forced to incorrectly create reservations for it as we have no record of
the original MAP_NORESERVE.

This patch introduces a new vma flag VM_NORESERVE which records the
presence of the original MAP_NORESERVE flag.  This allows us to
distinguish these two circumstances and correctly account the reserve.

As well as fixing this FIXME in the code, this makes it much easier to
introduce MAP_NORESERVE support for huge pages as this flag is available
consistantly for the life of the mapping.  VM_ACCOUNT on the other hand is
heavily used at the generic level in association with small pages.

Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Adam Litke <agl@us.ibm.com>
Cc: Johannes Weiner <hannes@saeurebad.de>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Andy Whitcroft 2008-07-23 21:27:28 -07:00 committed by Linus Torvalds
parent e7c4b0bfd0
commit cdfd4325c0
3 changed files with 6 additions and 4 deletions

View File

@ -100,6 +100,7 @@ extern unsigned int kobjsize(const void *objp);
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
#define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */
#define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */

View File

@ -1110,6 +1110,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
if (flags & MAP_NORESERVE)
vm_flags |= VM_NORESERVE;
if (accountable && (!(flags & MAP_NORESERVE) ||
sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
if (vm_flags & VM_SHARED) {

View File

@ -153,12 +153,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
* If we make a private mapping writable we increase our commit;
* but (without finer accounting) cannot reduce our commit if we
* make it unwritable again.
*
* FIXME? We haven't defined a VM_NORESERVE flag, so mprotecting
* a MAP_NORESERVE private mapping to writable will now reserve.
*/
if (newflags & VM_WRITE) {
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED))) {
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|
VM_SHARED|VM_NORESERVE))) {
charged = nrpages;
if (security_vm_enough_memory(charged))
return -ENOMEM;