@@ -1556,26 +1556,23 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
unsigned int gup_flags)
{
unsigned long i;
- unsigned long step;
bool drain_allow = true;
bool migrate_allow = true;
LIST_HEAD(cma_page_list);
long ret = nr_pages;
+ struct page *prev_head, *head;
struct migration_target_control mtc = {
.nid = NUMA_NO_NODE,
.gfp_mask = GFP_USER | __GFP_NOWARN,
};
check_again:
- for (i = 0; i < nr_pages;) {
-
- struct page *head = compound_head(pages[i]);
-
- /*
- * gup may start from a tail page. Advance step by the left
- * part.
- */
- step = compound_nr(head) - (pages[i] - head);
+ prev_head = NULL;
+ for (i = 0; i < nr_pages; i++) {
+ head = compound_head(pages[i]);
+ if (head == prev_head)
+ continue;
+ prev_head = head;
/*
* If we get a page from the CMA zone, since we are going to
* be pinning these entries, we might as well move them out
@@ -1599,8 +1596,6 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
}
}
}
-
- i += step;
}
if (!list_empty(&cma_page_list)) {
When pages are isolated in check_and_migrate_movable_pages() we skip compound number of pages at a time. However, as Jason noted, it is not necessary correct that pages[i] corresponds to the pages that we skipped. This is because it is possible that the addresses in this range had split_huge_pmd()/split_huge_pud(), and these functions do not update the compound page metadata. The problem can be reproduced if something like this occurs: 1. User faulted huge pages. 2. split_huge_pmd() was called for some reason 3. User has unmapped some sub-pages in the range 4. User tries to longterm pin the addresses. The resulting pages[i] might end-up having pages which are not compound size page aligned. Fixes: aa712399c1e8 ("mm/gup: speed up check_and_migrate_cma_pages() on huge page") Reported-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> --- mm/gup.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-)