From 42cb14b110a5698ccf26ce59c4441722605a3743 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 5 Nov 2015 18:50:05 -0800 Subject: mm: migrate dirty page without clear_page_dirty_for_io etc clear_page_dirty_for_io() has accumulated writeback and memcg subtleties since v2.6.16 first introduced page migration; and the set_page_dirty() which completed its migration of PageDirty, later had to be moderated to __set_page_dirty_nobuffers(); then PageSwapBacked had to skip that too. No actual problems seen with this procedure recently, but if you look into what the clear_page_dirty_for_io(page)+set_page_dirty(newpage) is actually achieving, it turns out to be nothing more than moving the PageDirty flag, and its NR_FILE_DIRTY stat from one zone to another. It would be good to avoid a pile of irrelevant decrementations and incrementations, and improper event counting, and unnecessary descent of the radix_tree under tree_lock (to set the PAGECACHE_TAG_DIRTY which radix_tree_replace_slot() left in place anyway). Do the NR_FILE_DIRTY movement, like the other stats movements, while interrupts still disabled in migrate_page_move_mapping(); and don't even bother if the zone is the same. Do the PageDirty movement there under tree_lock too, where old page is frozen and newpage not yet visible: bearing in mind that as soon as newpage becomes visible in radix_tree, an un-page-locked set_page_dirty() might interfere (or perhaps that's just not possible: anything doing so should already hold an additional reference to the old page, preventing its migration; but play safe). But we do still need to transfer PageDirty in migrate_page_copy(), for those who don't go the mapping route through migrate_page_move_mapping(). Signed-off-by: Hugh Dickins Cc: Christoph Lameter Cc: "Kirill A. Shutemov" Cc: Rik van Riel Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Oleg Nesterov Cc: Sasha Levin Cc: Dmitry Vyukov Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 51 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 20 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 3067e40e7be9..2834faba719a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -313,6 +314,8 @@ int migrate_page_move_mapping(struct address_space *mapping, struct buffer_head *head, enum migrate_mode mode, int extra_count) { + struct zone *oldzone, *newzone; + int dirty; int expected_count = 1 + extra_count; void **pslot; @@ -331,6 +334,9 @@ int migrate_page_move_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } + oldzone = page_zone(page); + newzone = page_zone(newpage); + spin_lock_irq(&mapping->tree_lock); pslot = radix_tree_lookup_slot(&mapping->page_tree, @@ -378,6 +384,13 @@ int migrate_page_move_mapping(struct address_space *mapping, set_page_private(newpage, page_private(page)); } + /* Move dirty while page refs frozen and newpage not yet exposed */ + dirty = PageDirty(page); + if (dirty) { + ClearPageDirty(page); + SetPageDirty(newpage); + } + radix_tree_replace_slot(pslot, newpage); /* @@ -387,6 +400,9 @@ int migrate_page_move_mapping(struct address_space *mapping, */ page_unfreeze_refs(page, expected_count - 1); + spin_unlock(&mapping->tree_lock); + /* Leave irq disabled to prevent preemption while updating stats */ + /* * If moved to a different zone then also account * the page for that zone. Other VM counters will be @@ -397,13 +413,19 @@ int migrate_page_move_mapping(struct address_space *mapping, * via NR_FILE_PAGES and NR_ANON_PAGES if they * are mapped to swap space. */ - __dec_zone_page_state(page, NR_FILE_PAGES); - __inc_zone_page_state(newpage, NR_FILE_PAGES); - if (!PageSwapCache(page) && PageSwapBacked(page)) { - __dec_zone_page_state(page, NR_SHMEM); - __inc_zone_page_state(newpage, NR_SHMEM); + if (newzone != oldzone) { + __dec_zone_state(oldzone, NR_FILE_PAGES); + __inc_zone_state(newzone, NR_FILE_PAGES); + if (PageSwapBacked(page) && !PageSwapCache(page)) { + __dec_zone_state(oldzone, NR_SHMEM); + __inc_zone_state(newzone, NR_SHMEM); + } + if (dirty && mapping_cap_account_dirty(mapping)) { + __dec_zone_state(oldzone, NR_FILE_DIRTY); + __inc_zone_state(newzone, NR_FILE_DIRTY); + } } - spin_unlock_irq(&mapping->tree_lock); + local_irq_enable(); return MIGRATEPAGE_SUCCESS; } @@ -524,20 +546,9 @@ void migrate_page_copy(struct page *newpage, struct page *page) if (PageMappedToDisk(page)) SetPageMappedToDisk(newpage); - if (PageDirty(page)) { - clear_page_dirty_for_io(page); - /* - * Want to mark the page and the radix tree as dirty, and - * redo the accounting that clear_page_dirty_for_io undid, - * but we can't use set_page_dirty because that function - * is actually a signal that all of the page has become dirty. - * Whereas only part of our page may be dirty. - */ - if (PageSwapBacked(page)) - SetPageDirty(newpage); - else - __set_page_dirty_nobuffers(newpage); - } + /* Move dirty on pages not done by migrate_page_move_mapping() */ + if (PageDirty(page)) + SetPageDirty(newpage); if (page_is_young(page)) set_page_young(newpage); -- cgit v1.2.3