| From 9ffa957b5409f1c6afbfcd58f05803139d2a5048 Mon Sep 17 00:00:00 2001 |
| From: Sasha Levin <sashal@kernel.org> |
| Date: Tue, 4 May 2021 18:38:42 -0700 |
| Subject: mm/gup: check every subpage of a compound page during isolation |
| |
| From: Pavel Tatashin <pasha.tatashin@soleen.com> |
| |
| [ Upstream commit 83c02c23d0747a7bdcd71f99a538aacec94b146c ] |
| |
| 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. |
| |
| Link: https://lkml.kernel.org/r/20210215161349.246722-3-pasha.tatashin@soleen.com |
| Fixes: aa712399c1e8 ("mm/gup: speed up check_and_migrate_cma_pages() on huge page") |
| Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com> |
| Reported-by: Jason Gunthorpe <jgg@nvidia.com> |
| Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> |
| Cc: Dan Williams <dan.j.williams@intel.com> |
| Cc: David Hildenbrand <david@redhat.com> |
| Cc: David Rientjes <rientjes@google.com> |
| Cc: Ingo Molnar <mingo@redhat.com> |
| Cc: Ira Weiny <ira.weiny@intel.com> |
| Cc: James Morris <jmorris@namei.org> |
| Cc: Jason Gunthorpe <jgg@ziepe.ca> |
| Cc: John Hubbard <jhubbard@nvidia.com> |
| Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> |
| Cc: Matthew Wilcox <willy@infradead.org> |
| Cc: Mel Gorman <mgorman@suse.de> |
| Cc: Michal Hocko <mhocko@kernel.org> |
| Cc: Michal Hocko <mhocko@suse.com> |
| Cc: Mike Kravetz <mike.kravetz@oracle.com> |
| Cc: Oscar Salvador <osalvador@suse.de> |
| Cc: Peter Zijlstra <peterz@infradead.org> |
| Cc: Sasha Levin <sashal@kernel.org> |
| Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> |
| Cc: Tyler Hicks <tyhicks@linux.microsoft.com> |
| Cc: Vlastimil Babka <vbabka@suse.cz> |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| Signed-off-by: Sasha Levin <sashal@kernel.org> |
| --- |
| mm/gup.c | 19 +++++++------------ |
| 1 file changed, 7 insertions(+), 12 deletions(-) |
| |
| diff --git a/mm/gup.c b/mm/gup.c |
| index 054ff923d3d9..e10807c4c46b 100644 |
| --- a/mm/gup.c |
| +++ b/mm/gup.c |
| @@ -1562,26 +1562,23 @@ 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_MOVABLE | __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 |
| @@ -1605,8 +1602,6 @@ check_again: |
| } |
| } |
| } |
| - |
| - i += step; |
| } |
| |
| if (!list_empty(&cma_page_list)) { |
| -- |
| 2.30.2 |
| |