In the reservation routine, we only check whether the cpuset meets
the memory allocation requirements. But we ignore the mempolicy of
MPOL_BIND case. If someone mmap hugetlb succeeds, but the subsequent
memory allocation may fail due to mempolicy restrictions and receives
the SIGBUS signal. This can be reproduced by the follow steps.
1) Compile the test case.
cd tools/testing/selftests/vm/
gcc map_hugetlb.c -o map_hugetlb
2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
system. Each node will pre-allocate one huge page.
echo 2 > /proc/sys/vm/nr_hugepages
3) Run test case(mmap 4MB). We receive the SIGBUS signal.
numactl --membind=0 ./map_hugetlb 4
With this patch applied, the mmap will fail in the step 3) and throw
"mmap: Cannot allocate memory".
Reported-by: Jianchao Guo <[email protected]>
Signed-off-by: Muchun Song <[email protected]>
---
mm/hugetlb.c | 30 +++++++++++++++++++++++++++---
1 file changed, 27 insertions(+), 3 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 589c330df4db..e946f41b4dcb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3463,12 +3463,36 @@ static int __init default_hugepagesz_setup(char *s)
}
__setup("default_hugepagesz=", default_hugepagesz_setup);
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static nodemask_t *mempolicy_current_bind_nodemask(void)
+{
+ struct mempolicy *mpol;
+ nodemask_t *nodemask;
+
+ mpol = get_task_policy(current);
+ if (mpol->mode == MPOL_BIND)
+ nodemask = &mpol->v.nodes;
+ else
+ nodemask = NULL;
+
+ return nodemask;
+}
+
+static unsigned int allowed_mems_nr(unsigned int *array)
{
int node;
unsigned int nr = 0;
+ nodemask_t *mempolicy_allowed, *mems_allowed, nodemask;
+
+ mempolicy_allowed = mempolicy_current_bind_nodemask();
+ if (mempolicy_allowed) {
+ nodes_and(nodemask, cpuset_current_mems_allowed,
+ *mempolicy_allowed);
+ mems_allowed = &nodemask;
+ } else {
+ mems_allowed = &cpuset_current_mems_allowed;
+ }
- for_each_node_mask(node, cpuset_current_mems_allowed)
+ for_each_node_mask(node, *mems_allowed)
nr += array[node];
return nr;
@@ -3653,7 +3677,7 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
if (gather_surplus_pages(h, delta) < 0)
goto out;
- if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+ if (delta > allowed_mems_nr(h->free_huge_pages_node)) {
return_unused_surplus_pages(h, delta);
goto out;
}
--
2.11.0
On Thu 23-07-20 15:44:17, Muchun Song wrote:
> In the reservation routine, we only check whether the cpuset meets
> the memory allocation requirements. But we ignore the mempolicy of
> MPOL_BIND case. If someone mmap hugetlb succeeds, but the subsequent
> memory allocation may fail due to mempolicy restrictions and receives
> the SIGBUS signal. This can be reproduced by the follow steps.
>
> 1) Compile the test case.
> cd tools/testing/selftests/vm/
> gcc map_hugetlb.c -o map_hugetlb
>
> 2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
> system. Each node will pre-allocate one huge page.
> echo 2 > /proc/sys/vm/nr_hugepages
>
> 3) Run test case(mmap 4MB). We receive the SIGBUS signal.
> numactl --membind=0 ./map_hugetlb 4
Cpusets and mempolicy interaction has always been a nightmare and
semantic might get really awkward in some cases. In this case I am not
really sure anybody really does soemthing like that but anyway...
[...]
> -static unsigned int cpuset_mems_nr(unsigned int *array)
> +static nodemask_t *mempolicy_current_bind_nodemask(void)
> +{
> + struct mempolicy *mpol;
> + nodemask_t *nodemask;
> +
> + mpol = get_task_policy(current);
> + if (mpol->mode == MPOL_BIND)
> + nodemask = &mpol->v.nodes;
> + else
> + nodemask = NULL;
> +
> + return nodemask;
> +}
We already have policy_nodemask which tries to do this. Is there any
reason to not reuse it?
--
Michal Hocko
SUSE Labs
On Fri, Jul 24, 2020 at 3:39 PM Michal Hocko <[email protected]> wrote:
>
> On Thu 23-07-20 15:44:17, Muchun Song wrote:
> > In the reservation routine, we only check whether the cpuset meets
> > the memory allocation requirements. But we ignore the mempolicy of
> > MPOL_BIND case. If someone mmap hugetlb succeeds, but the subsequent
> > memory allocation may fail due to mempolicy restrictions and receives
> > the SIGBUS signal. This can be reproduced by the follow steps.
> >
> > 1) Compile the test case.
> > cd tools/testing/selftests/vm/
> > gcc map_hugetlb.c -o map_hugetlb
> >
> > 2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
> > system. Each node will pre-allocate one huge page.
> > echo 2 > /proc/sys/vm/nr_hugepages
> >
> > 3) Run test case(mmap 4MB). We receive the SIGBUS signal.
> > numactl --membind=0 ./map_hugetlb 4
>
> Cpusets and mempolicy interaction has always been a nightmare and
Yeah, I agree with you.
> semantic might get really awkward in some cases. In this case I am not
> really sure anybody really does soemthing like that but anyway...
Someone may like to use numactl to bind memory nodes. So I think
that it is better to add a mempolicy check.
>
> [...]
>
> > -static unsigned int cpuset_mems_nr(unsigned int *array)
> > +static nodemask_t *mempolicy_current_bind_nodemask(void)
> > +{
> > + struct mempolicy *mpol;
> > + nodemask_t *nodemask;
> > +
> > + mpol = get_task_policy(current);
> > + if (mpol->mode == MPOL_BIND)
> > + nodemask = &mpol->v.nodes;
> > + else
> > + nodemask = NULL;
> > +
> > + return nodemask;
> > +}
>
> We already have policy_nodemask which tries to do this. Is there any
> reason to not reuse it?
Yeah, we can reuse it, I didn't know it before. Thanks.
> --
> Michal Hocko
> SUSE Labs
--
Yours,
Muchun