Dmitry Vyukov reported yet another VM_BUG_ON_PAGE(PageTail(page)) bug from isolate_lru_page(). The fisrt patch fixes the bug by filter out non migratable VMAs in queue_pages_test_walk(). There's no point to queue pages from non-migratable VMA even for MPOL_MF_STRICT. The second patch replace VM_BUG_ON_PAGE() with WARN_RATELIMIT() in isolate_lru_page(). Most attempts to isolate tail pages are not fatal, as these pages usually are not on LRU and will not be isolated. v2: - address feedback from Michal Hocko; Kirill A. Shutemov (2): mempolicy: do not try to queue pages from !vma_migratable() mm: downgrade VM_BUG in isolate_lru_page() to warning mm/mempolicy.c | 14 +++++--------- mm/vmscan.c | 2 +- 2 files changed, 6 insertions(+), 10 deletions(-) -- 2.7.0 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>