From 62b61f611eb5e20f7e9f8619bfd03bdfe8af6348 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Dec 2009 17:59:33 -0800 Subject: ksm: memory hotremove migration only The previous patch enables page migration of ksm pages, but that soon gets into trouble: not surprising, since we're using the ksm page lock to lock operations on its stable_node, but page migration switches the page whose lock is to be used for that. Another layer of locking would fix it, but do we need that yet? Do we actually need page migration of ksm pages? Yes, memory hotremove needs to offline sections of memory: and since we stopped allocating ksm pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE candidates for migration. But KSM is currently unconscious of NUMA issues, happily merging pages from different NUMA nodes: at present the rule must be, not to use MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of ksm pages does not make sense yet. So, to complete support for ksm swapping we need to make hotremove safe. ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages are freed before migration reaches them, stable_nodes may be left still pointing to struct pages which have been removed from the system: the stable_node needs to identify a page by pfn rather than page pointer, then it can safely prune them when MEM_OFFLINE. And make NUMA migration skip PageKsm pages where it skips PageReserved. But it's only when we reach unmap_and_move() that the page lock is taken and we can be sure that raised pagecount has prevented a PageAnon from being upgraded: so add offlining arg to migrate_pages(), to migrate ksm page when offlining (has sufficient locking) but reject it otherwise. Signed-off-by: Hugh Dickins Cc: Izik Eidus Cc: Andrea Arcangeli Cc: Chris Wright Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f11fdad06204..290fb5bf0440 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -85,6 +85,7 @@ #include #include #include +#include #include #include #include @@ -413,17 +414,11 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (!page) continue; /* - * The check for PageReserved here is important to avoid - * handling zero pages and other pages that may have been - * marked special by the system. - * - * If the PageReserved would not be checked here then f.e. - * the location of the zero page could have an influence - * on MPOL_MF_STRICT, zero pages would be counted for - * the per node stats, and there would be useless attempts - * to put zero pages on the migration list. + * vm_normal_page() filters out zero pages, but there might + * still be PageReserved pages to skip, perhaps in a VDSO. + * And we cannot move PageKsm pages sensibly or safely yet. */ - if (PageReserved(page)) + if (PageReserved(page) || PageKsm(page)) continue; nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) @@ -839,7 +834,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) - err = migrate_pages(&pagelist, new_node_page, dest); + err = migrate_pages(&pagelist, new_node_page, dest, 0); return err; } @@ -1056,7 +1051,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma); + (unsigned long)vma, 0); if (!err && nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; -- cgit v1.2.3-58-ga151