On Wed, Dec 4, 2019 at 11:01 AM Felix Abecassis <fabecassis@xxxxxxxxxx> wrote:
>
> Hello all,
>
> On kernel 5.3, when using the move_pages syscall (wrapped by libnuma) and all
> pages happen to be on the right node already, this function returns 0 but the
> "status" array is not updated. This array potentially contains garbage values
> (e.g. from malloc(3)), and I don't see a way to detect this.
>
> Looking at the kernel code, we are probably exiting do_pages_move here:
> out_flush:
> if (list_empty(&pagelist))
> return err;
May you please give the below patch a try? I just did build test.
diff --git a/mm/migrate.c b/mm/migrate.c
index a8f87cb..f2f1279 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1517,7 +1517,8 @@ static int do_move_pages_to_node(struct mm_struct *mm,
* the target node
*/
static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
- int node, struct list_head *pagelist, bool migrate_all)
+ int node, struct list_head *pagelist, bool migrate_all,
+ int __user *status, int start)
{
struct vm_area_struct *vma;
struct page *page;
@@ -1543,8 +1544,10 @@ static int add_page_for_migration(struct
mm_struct *mm, unsigned long addr,
goto out;
err = 0;
- if (page_to_nid(page) == node)
+ if (page_to_nid(page) == node) {
+ err = store_status(status, start, node, 1);
goto out_putpage;
+ }
err = -EACCES;
if (page_mapcount(page) > 1 && !migrate_all)
@@ -1639,7 +1642,9 @@ static int do_pages_move(struct mm_struct *mm,
nodemask_t task_nodes,
* report them via status
*/
err = add_page_for_migration(mm, addr, current_node,
- &pagelist, flags & MPOL_MF_MOVE_ALL);
+ &pagelist, flags & MPOL_MF_MOVE_ALL, status,
+ i);
+
if (!err)
continue;
>
> Here is a sample C program to reproduce the problem:
> /* $ gcc move_pages_bug.c -lnuma -o move_pages_bug */
>
> #define _DEFAULT_SOURCE
> #include <sys/mman.h>
>
> #include <numaif.h>
> #include <stdlib.h>
> #include <stdio.h>
> #include <unistd.h>
>
> int main(void)
> {
> const long node_id = 1;
> const long page_size = sysconf(_SC_PAGESIZE);
> const int64_t num_pages = 8;
>
> unsigned long nodemask = 1 << node_id;
> long ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask));
> if (ret < 0)
> return (EXIT_FAILURE);
>
> void **pages = malloc(sizeof(void*) * num_pages);
> for (int i = 0; i < num_pages; ++i) {
> pages[i] = mmap(NULL, page_size, PROT_WRITE | PROT_READ,
> MAP_PRIVATE | MAP_POPULATE | MAP_ANONYMOUS,
> -1, 0);
> if (pages[i] == MAP_FAILED)
> return (EXIT_FAILURE);
> }
>
> ret = set_mempolicy(MPOL_DEFAULT, NULL, 0);
> if (ret < 0)
> return (EXIT_FAILURE);
>
> int *nodes = malloc(sizeof(int) * num_pages);
> int *status = malloc(sizeof(int) * num_pages);
> for (int i = 0; i < num_pages; ++i) {
> nodes[i] = node_id;
> status[i] = 0xd0; /* simulate garbage values */
> }
>
> ret = move_pages(0, num_pages, pages, nodes, status, MPOL_MF_MOVE);
> printf("move_pages: %ld\n", ret);
> for (int i = 0; i < num_pages; ++i)
> printf("status[%d] = %d\n", i, status[i]);
> }
>
> And here is a sample output showing the "garbage" values:
> $ ./move_pages_bug
> move_pages: 0
> status[0] = 208
> status[1] = 208
> status[2] = 208
> status[3] = 208
> status[4] = 208
> status[5] = 208
> status[6] = 208
> status[7] = 208
>
> Note that passing NULL as the "nodes" argument works as expected here.
>
> Also, it seems that it's the last "run-length" of pages on the right node(s)
> that triggers this problem, e.g. if I add "nodes[0] = nodes[1] = 0", then the
> output becomes:
> $ ./move_pages_bug
> move_pages: 0
> status[0] = 0
> status[1] = 0
> status[2] = 208
> status[3] = 208
> status[4] = 208
> status[5] = 208
> status[6] = 208
> status[7] = 208
>
> And with just "nodes[7] = 0;", the first run-length of pages gets assigned
> correctly:
> $ ./move_pages_bug
> move_pages: 0
> status[0] = 1
> status[1] = 1
> status[2] = 1
> status[3] = 1
> status[4] = 1
> status[5] = 1
> status[6] = 1
> status[7] = 0
>
>
> Thank you,
>
