From 29c1f677d424e8c5683a837fc4f03fc9f19201d7 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:47:21 -0800 Subject: mm: migration: use rcu_dereference_protected when dereferencing the radix tree slot during file page migration migrate_pages() -> unmap_and_move() only calls rcu_read_lock() for anonymous pages, as introduced by git commit 989f89c57e6361e7d16fbd9572b5da7d313b073d ("fix rcu_read_lock() in page migraton"). The point of the RCU protection there is part of getting a stable reference to anon_vma and is only held for anon pages as file pages are locked which is sufficient protection against freeing. However, while a file page's mapping is being migrated, the radix tree is double checked to ensure it is the expected page. This uses radix_tree_deref_slot() -> rcu_dereference() without the RCU lock held triggering the following warning. [ 173.674290] =================================================== [ 173.676016] [ INFO: suspicious rcu_dereference_check() usage. ] [ 173.676016] --------------------------------------------------- [ 173.676016] include/linux/radix-tree.h:145 invoked rcu_dereference_check() without protection! [ 173.676016] [ 173.676016] other info that might help us debug this: [ 173.676016] [ 173.676016] [ 173.676016] rcu_scheduler_active = 1, debug_locks = 0 [ 173.676016] 1 lock held by hugeadm/2899: [ 173.676016] #0: (&(&inode->i_data.tree_lock)->rlock){..-.-.}, at: [] migrate_page_move_mapping+0x40/0x1ab [ 173.676016] [ 173.676016] stack backtrace: [ 173.676016] Pid: 2899, comm: hugeadm Not tainted 2.6.37-rc5-autobuild [ 173.676016] Call Trace: [ 173.676016] [] ? printk+0x14/0x1b [ 173.676016] [] lockdep_rcu_dereference+0x7d/0x86 [ 173.676016] [] migrate_page_move_mapping+0xca/0x1ab [ 173.676016] [] migrate_page+0x23/0x39 [ 173.676016] [] buffer_migrate_page+0x22/0x107 [ 173.676016] [] ? buffer_migrate_page+0x0/0x107 [ 173.676016] [] move_to_new_page+0x9a/0x1ae [ 173.676016] [] migrate_pages+0x1e7/0x2fa This patch introduces radix_tree_deref_slot_protected() which calls rcu_dereference_protected(). Users of it must pass in the mapping->tree_lock that is protecting this dereference. Holding the tree lock protects against parallel updaters of the radix tree meaning that rcu_dereference_protected is allowable. [akpm@linux-foundation.org: remove unneeded casts] Signed-off-by: Mel Gorman Cc: Minchan Kim Cc: KAMEZAWA Hiroyuki Cc: Milton Miller Cc: Nick Piggin Cc: Wu Fengguang Cc: [2.6.37.early] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 16 ++++++++++++++++ mm/migrate.c | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index ab2baa5c488..23241c2fecc 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -145,6 +145,22 @@ static inline void *radix_tree_deref_slot(void **pslot) return rcu_dereference(*pslot); } +/** + * radix_tree_deref_slot_protected - dereference a slot without RCU lock but with tree lock held + * @pslot: pointer to slot, returned by radix_tree_lookup_slot + * Returns: item that was stored in that slot with any direct pointer flag + * removed. + * + * Similar to radix_tree_deref_slot but only used during migration when a pages + * mapping is being moved. The caller does not hold the RCU read lock but it + * must hold the tree lock to prevent parallel updates. + */ +static inline void *radix_tree_deref_slot_protected(void **pslot, + spinlock_t *treelock) +{ + return rcu_dereference_protected(*pslot, lockdep_is_held(treelock)); +} + /** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot diff --git a/mm/migrate.c b/mm/migrate.c index 1a531b760b3..89a6bc8cd30 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -248,7 +248,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || - (struct page *)radix_tree_deref_slot(pslot) != page) { + radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -320,7 +320,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || - (struct page *)radix_tree_deref_slot(pslot) != page) { + radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } -- cgit v1.2.3-18-g5258