From: Nadav Amit <namit@xxxxxxxxxx>
Subject: Revert "mm: numa: defer TLB flush for THP migration as long as possible"
While deferring TLB flushes is a good practice, the reverted patch caused
pending TLB flushes to be checked while the page-table lock is not taken.
As a result, in architectures with weak memory model (PPC), Linux may miss
a memory-barrier, miss the fact TLB flushes are pending, and cause (in
theory) a memory corruption.
Since the alternative of using smp_mb__after_unlock_lock() was considered
a bit open-coded, and the performance impact is expected to be small, the
previous patch is reverted.
This reverts b0943d61b8fa4201 ("mm: numa: defer TLB flush for THP
migration as long as possible").
Link: http://lkml.kernel.org/r/20170802000818.4760-4-namit@xxxxxxxxxx
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
Suggested-by: Mel Gorman <mgorman@xxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jeff Dike <jdike@xxxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Nadav Amit <nadav.amit@xxxxxxxxx>
Cc: Russell King <linux@xxxxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Yoshinori Sato <ysato@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 7 +++++++
mm/migrate.c | 6 ------
2 files changed, 7 insertions(+), 6 deletions(-)
diff -puN mm/huge_memory.c~revert-mm-numa-defer-tlb-flush-for-thp-migration-as-long-as-possible mm/huge_memory.c
--- a/mm/huge_memory.c~revert-mm-numa-defer-tlb-flush-for-thp-migration-as-long-as-possible
+++ a/mm/huge_memory.c
@@ -1496,6 +1496,13 @@ int do_huge_pmd_numa_page(struct vm_faul
}
/*
+ * The page_table_lock above provides a memory barrier
+ * with change_protection_range.
+ */
+ if (mm_tlb_flush_pending(vma->vm_mm))
+ flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
+ /*
* Migrate the THP to the requested node, returns with page unlocked
* and access rights restored.
*/
diff -puN mm/migrate.c~revert-mm-numa-defer-tlb-flush-for-thp-migration-as-long-as-possible mm/migrate.c
--- a/mm/migrate.c~revert-mm-numa-defer-tlb-flush-for-thp-migration-as-long-as-possible
+++ a/mm/migrate.c
@@ -1937,12 +1937,6 @@ int migrate_misplaced_transhuge_page(str
put_page(new_page);
goto out_fail;
}
- /*
- * We are not sure a pending tlb flush here is for a huge page
- * mapping or not. Hence use the tlb range variant
- */
- if (mm_tlb_flush_pending(mm))
- flush_tlb_range(vma, mmun_start, mmun_end);
/* Prepare a page as a migration target */
__SetPageLocked(new_page);
_
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
