[PATCH] COMPACTION: bugfix of improper cache flush in MIGRATION code.

* [PATCH] COMPACTION: bugfix of improper cache flush in MIGRATION code.
@ 2013-05-09  0:18 Leonid Yegoshin
  2013-05-09 14:38 ` Rik van Riel
  2013-05-10  9:52 ` Mel Gorman
  0 siblings, 2 replies; 3+ messages in thread
From: Leonid Yegoshin @ 2013-05-09  0:18 UTC (permalink / raw)
  To: riel, mhocko, akpm, mgorman, kamezawa.hiroyu; +Cc: linux-mm, linux-kernel

Page 'new' during MIGRATION can't be flushed by flush_cache_page().
Using flush_cache_page(vma, addr, pfn) is justified only if
page is already placed in process page table, and that is done right
after flush_cache_page(). But without it the arch function has
no knowledge of process PTE and does nothing.

Besides that, flush_cache_page() flushes an application cache,
kernel has a different page virtual address and dirtied it.

Replace it with flush_dcache_page(new) which is a proper usage.

Old page is flushed in try_to_unmap_one() before MIGRATION.

This bug takes place in Sead3 board with M14Kc MIPS CPU without
cache aliasing (but Harvard arch - separate I and D cache)
in tight memory environment (128MB) each 1-3days on SOAK test.
It fails in cc1 during kernel build (SIGILL, SIGBUS, SIGSEG) if
CONFIG_COMPACTION is switched ON.

Author: Leonid Yegoshin <yegoshin@mips.com>
Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
---
 mm/migrate.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 2fd8b4a..4c6250a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -165,7 +165,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		pte = arch_make_huge_pte(pte, vma, new, 0);
 	}
 #endif
-	flush_cache_page(vma, addr, pte_pfn(pte));
+	flush_dcache_page(new);
 	set_pte_at(mm, addr, ptep, pte);
 
 	if (PageHuge(new)) {



^ permalink raw reply related	[flat|nested] 3+ messages in thread