mm-fix-is_pinnable_page-against-a-cma-page.patch removed from -mm tree
The quilt patch titled
Subject: mm: fix is_pinnable_page against a cma page
has been removed from the -mm tree. Its filename was
mm-fix-is_pinnable_page-against-a-cma-page.patch
This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Minchan Kim <[email protected]>
Subject: mm: fix is_pinnable_page against a cma page
Date: Tue, 24 May 2022 10:15:25 -0700
Pages in the CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA so the current is_pinnable_page() could miss CMA pages which have MIGRATE_ISOLATE. It ends up pinning CMA pages as longterm for the pin_user_pages() API so CMA allocations keep failing until the pin is released.
CPU 0 CPU 1 - Task B
cma_allocalloc_contig_range
pin_user_pages_fast(FOLL_LONGTERM)
change pageblock as MIGRATE_ISOLATE
internal_get_user_pages_fast lockless_pages_from_mm gup_pte_range try_grab_folio is_pinnable_page
return true;
So, pinned the page successfully.
page migration failure with pinned page
..
.. After 30 sec
unpin_user_page(page)CMA allocation succeeded after 30 sec.
The CMA allocation path protects the migration type change race using zone->lock but what GUP path need to know is just whether the page is on CMA area or not rather than exact migration type. Thus, we don't need zone->lock but just checks migration type in either of (MIGRATE_ISOLATE and MIGRATE_CMA).
Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause rejecting of pinning pages on MIGRATE_ISOLATE pageblocks even though it's neither CMA nor movable zone if the page is temporarily unmovable. However, such a migration failure by unexpected temporal refcount holding is general issue, not only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also transient state like other temporal elevated refcount problem.
---
include/linux/mm.h | 9 +++++++-- mm/page_alloc.c | 8 ++++++-- 2 files changed, 13 insertions(+), 4 deletions(-)
include/linux/mm.h renamed from include/linux/mm.h~mm-fix-is_pinnable_page-against-a-cma-page +7 -2
@@ -1594,8 +1594,13 @@ static inline bool page_needs_cow_for_dm#ifdef CONFIG_MIGRATION static inline bool is_pinnable_page (struct page *page) { -return !(is_zone_movable_page (page) ||is_migrate_cma_page (page)) || -is_zero_pfn (page_to_pfn (page)); +#ifdef CONFIG_CMA +int mt =get_pageblock_migratetype (page); + +if (mt ==MIGRATE_CMA || mt ==MIGRATE_ISOLATE ) +return false; +#endif +return !(is_zone_movable_page (page) ||is_zero_pfn (page_to_pfn (page))); }#else static inline bool is_pinnable_page (struct page *page)
mm/page_alloc.c renamed from mm/page_alloc.c~mm-fix-is_pinnable_page-against-a-cma-page +6 -2
@@ -482,8 +482,12 @@ unsigned long __get_pfnblock_flags_mask( bitidx =pfn_to_bitidx (page, pfn); word_bitidx = bitidx /BITS_PER_LONG ; bitidx &= (BITS_PER_LONG -1 ); - - word = bitmap[word_bitidx]; +/* +* This races, without locks, with set_pfnblock_flags_mask(). Ensure +* a consistent read of the memory array, so that results, even though +* racy, are not corrupted. +*/ + word =READ_ONCE (bitmap[word_bitidx]);return (word >> bitidx) & mask; }
_
Patches currently in -mm which might be from [email protected] are