Skip to content

Commit

Permalink
mm: hugetlb: soft-offline: dissolve_free_huge_page() return zero on !…
Browse files Browse the repository at this point in the history
…PageHuge

madvise(MADV_SOFT_OFFLINE) often returns -EBUSY when calling soft offline
for hugepages with overcommitting enabled.  That was caused by the
suboptimal code in current soft-offline code.  See the following part:

    ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
                            MIGRATE_SYNC, MR_MEMORY_FAILURE);
    if (ret) {
            ...
    } else {
            /*
             * We set PG_hwpoison only when the migration source hugepage
             * was successfully dissolved, because otherwise hwpoisoned
             * hugepage remains on free hugepage list, then userspace will
             * find it as SIGBUS by allocation failure. That's not expected
             * in soft-offlining.
             */
            ret = dissolve_free_huge_page(page);
            if (!ret) {
                    if (set_hwpoison_free_buddy_page(page))
                            num_poisoned_pages_inc();
            }
    }
    return ret;

Here dissolve_free_huge_page() returns -EBUSY if the migration source page
was freed into buddy in migrate_pages(), but even in that case we actually
has a chance that set_hwpoison_free_buddy_page() succeeds.  So that means
current code gives up offlining too early now.

dissolve_free_huge_page() checks that a given hugepage is suitable for
dissolving, where we should return success for !PageHuge() case because
the given hugepage is considered as already dissolved.

This change also affects other callers of dissolve_free_huge_page(), which
are cleaned up together.

[[email protected]: v3]
  Link: http://lkml.kernel.org/r/[email protected]: http://lkml.kernel.org/r/[email protected]
Fixes: 6bc9b56 ("mm: fix race on soft-offlining")
Signed-off-by: Naoya Horiguchi <[email protected]>
Reported-by: Chen, Jerry T <[email protected]>
Tested-by: Chen, Jerry T <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Xishi Qiu <[email protected]>
Cc: "Chen, Jerry T" <[email protected]>
Cc: "Zhuo, Qiuxu" <[email protected]>
Cc: <[email protected]>	[4.19+]
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
  • Loading branch information
Naoya Horiguchi authored and torvalds committed Jun 29, 2019
1 parent b38e596 commit faf53de
Show file tree
Hide file tree
Showing 2 changed files with 21 additions and 13 deletions.
29 changes: 20 additions & 9 deletions mm/hugetlb.c
Original file line number Diff line number Diff line change
Expand Up @@ -1510,16 +1510,29 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,

/*
* Dissolve a given free hugepage into free buddy pages. This function does
* nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
* dissolution fails because a give page is not a free hugepage, or because
* free hugepages are fully reserved.
* nothing for in-use hugepages and non-hugepages.
* This function returns values like below:
*
* -EBUSY: failed to dissolved free hugepages or the hugepage is in-use
* (allocated or reserved.)
* 0: successfully dissolved free hugepages or the page is not a
* hugepage (considered as already dissolved)
*/
int dissolve_free_huge_page(struct page *page)
{
int rc = -EBUSY;

/* Not to disrupt normal path by vainly holding hugetlb_lock */
if (!PageHuge(page))
return 0;

spin_lock(&hugetlb_lock);
if (PageHuge(page) && !page_count(page)) {
if (!PageHuge(page)) {
rc = 0;
goto out;
}

if (!page_count(page)) {
struct page *head = compound_head(page);
struct hstate *h = page_hstate(head);
int nid = page_to_nid(head);
Expand Down Expand Up @@ -1564,11 +1577,9 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)

for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
page = pfn_to_page(pfn);
if (PageHuge(page) && !page_count(page)) {
rc = dissolve_free_huge_page(page);
if (rc)
break;
}
rc = dissolve_free_huge_page(page);
if (rc)
break;
}

return rc;
Expand Down
5 changes: 1 addition & 4 deletions mm/memory-failure.c
Original file line number Diff line number Diff line change
Expand Up @@ -1856,11 +1856,8 @@ static int soft_offline_in_use_page(struct page *page, int flags)

static int soft_offline_free_page(struct page *page)
{
int rc = 0;
struct page *head = compound_head(page);
int rc = dissolve_free_huge_page(page);

if (PageHuge(head))
rc = dissolve_free_huge_page(page);
if (!rc) {
if (set_hwpoison_free_buddy_page(page))
num_poisoned_pages_inc();
Expand Down

0 comments on commit faf53de

Please sign in to comment.