Add a new lock, wb_inode_list_lock, to protect i_list and various lists which the inode can be put onto. Signed-off-by: Nick Piggin --- fs/fs-writeback.c | 48 ++++++++++++++++++++++++++++++++++++++++++++-- fs/inode.c | 44 ++++++++++++++++++++++++++++++++++-------- include/linux/writeback.h | 1 mm/backing-dev.c | 4 +++ 4 files changed, 87 insertions(+), 10 deletions(-) Index: linux-2.6/fs/fs-writeback.c =================================================================== --- linux-2.6.orig/fs/fs-writeback.c 2010-10-19 14:18:58.000000000 +1100 +++ linux-2.6/fs/fs-writeback.c 2010-10-19 14:19:33.000000000 +1100 @@ -169,6 +169,7 @@ { struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + assert_spin_locked(&wb_inode_list_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -186,6 +187,7 @@ { struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + assert_spin_locked(&wb_inode_list_lock); list_move(&inode->i_list, &wb->b_more_io); } @@ -226,6 +228,7 @@ struct inode *inode; int do_sb_sort = 0; + assert_spin_locked(&wb_inode_list_lock); while (!list_empty(delaying_queue)) { inode = list_entry(delaying_queue->prev, struct inode, i_list); if (older_than_this && @@ -289,11 +292,13 @@ wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode->i_lock); spin_unlock(&inode_lock); __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode_lock); spin_lock(&inode->i_lock); + spin_lock(&wb_inode_list_lock); } } @@ -347,6 +352,7 @@ /* Set I_SYNC, reset I_DIRTY_PAGES */ inode->i_state |= I_SYNC; inode->i_state &= ~I_DIRTY_PAGES; + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode->i_lock); spin_unlock(&inode_lock); @@ -383,6 +389,7 @@ spin_lock(&inode_lock); spin_lock(&inode->i_lock); + spin_lock(&wb_inode_list_lock); inode->i_state &= ~I_SYNC; if (!(inode->i_state & I_FREEING)) { if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { @@ -469,11 +476,18 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct writeback_control *wbc, bool only_this_sb) { +again: while (!list_empty(&wb->b_io)) { long pages_skipped; struct inode *inode = list_entry(wb->b_io.prev, struct inode, i_list); + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&wb_inode_list_lock); + spin_lock(&wb_inode_list_lock); + goto again; + } + if (inode->i_sb != sb) { if (only_this_sb) { /* @@ -482,9 +496,12 @@ * to it back onto the dirty list. */ redirty_tail(inode); + spin_unlock(&inode->i_lock); continue; } + spin_unlock(&inode->i_lock); + /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and @@ -493,10 +510,9 @@ return 0; } - spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_WILL_FREE)) { - spin_unlock(&inode->i_lock); requeue_io(inode); + spin_unlock(&inode->i_lock); continue; } /* @@ -519,11 +535,13 @@ */ redirty_tail(inode); } + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode->i_lock); spin_unlock(&inode_lock); iput(inode); cond_resched(); spin_lock(&inode_lock); + spin_lock(&wb_inode_list_lock); if (wbc->nr_to_write <= 0) { wbc->more_io = 1; return 1; @@ -543,6 +561,9 @@ if (!wbc->wb_start) wbc->wb_start = jiffies; /* livelock avoidance */ spin_lock(&inode_lock); +again: + spin_lock(&wb_inode_list_lock); + if (!wbc->for_kupdate || list_empty(&wb->b_io)) queue_io(wb, wbc->older_than_this); @@ -552,7 +573,12 @@ struct super_block *sb = inode->i_sb; if (!pin_sb_for_writeback(sb)) { + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&wb_inode_list_lock); + goto again; + } requeue_io(inode); + spin_unlock(&inode->i_lock); continue; } ret = writeback_sb_inodes(sb, wb, wbc, false); @@ -561,6 +587,7 @@ if (ret) break; } + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode_lock); /* Leave any unwritten inodes on b_io */ } @@ -571,9 +598,11 @@ WARN_ON(!rwsem_is_locked(&sb->s_umount)); spin_lock(&inode_lock); + spin_lock(&wb_inode_list_lock); if (!wbc->for_kupdate || list_empty(&wb->b_io)) queue_io(wb, wbc->older_than_this); writeback_sb_inodes(sb, wb, wbc, true); + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode_lock); } @@ -684,13 +713,22 @@ * become available for writeback. Otherwise * we'll just busyloop. */ +retry: spin_lock(&inode_lock); + spin_lock(&wb_inode_list_lock); if (!list_empty(&wb->b_more_io)) { inode = list_entry(wb->b_more_io.prev, struct inode, i_list); + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&wb_inode_list_lock); + spin_unlock(&inode_lock); + goto retry; + } trace_wbc_writeback_wait(&wbc, wb->bdi); inode_wait_for_writeback(inode); + spin_unlock(&inode->i_lock); } + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode_lock); } @@ -1002,7 +1040,9 @@ } inode->dirtied_when = jiffies; + spin_lock(&wb_inode_list_lock); list_move(&inode->i_list, &bdi->wb.b_dirty); + spin_unlock(&wb_inode_list_lock); } } out: @@ -1195,7 +1235,9 @@ might_sleep(); spin_lock(&inode_lock); spin_lock(&inode->i_lock); + spin_lock(&wb_inode_list_lock); ret = writeback_single_inode(inode, &wbc); + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode->i_lock); spin_unlock(&inode_lock); if (sync) @@ -1221,7 +1263,9 @@ spin_lock(&inode_lock); spin_lock(&inode->i_lock); + spin_lock(&wb_inode_list_lock); ret = writeback_single_inode(inode, wbc); + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode->i_lock); spin_unlock(&inode_lock); return ret; Index: linux-2.6/fs/inode.c =================================================================== --- linux-2.6.orig/fs/inode.c 2010-10-19 14:18:58.000000000 +1100 +++ linux-2.6/fs/inode.c 2010-10-19 14:19:33.000000000 +1100 @@ -31,6 +31,8 @@ * s_inodes, i_sb_list * inode_hash_lock protects: * inode hash table, i_hash + * wb_inode_list_lock protects: + * inode_in_use, inode_unused, b_io, b_more_io, b_dirty, i_list * inode->i_lock protects: * i_state, i_count * @@ -38,6 +40,7 @@ * inode_lock * sb_inode_list_lock * inode->i_lock + * wb_inode_list_lock * inode_hash_lock */ /* @@ -99,6 +102,7 @@ */ DEFINE_SPINLOCK(inode_lock); DEFINE_SPINLOCK(sb_inode_list_lock); +DEFINE_SPINLOCK(wb_inode_list_lock); static DEFINE_SPINLOCK(inode_hash_lock); /* @@ -304,8 +308,11 @@ if (inode->i_count > 1) return; - if (!(inode->i_state & (I_DIRTY|I_SYNC))) + if (!(inode->i_state & (I_DIRTY|I_SYNC))) { + spin_lock(&wb_inode_list_lock); list_move(&inode->i_list, &inode_in_use); + spin_unlock(&wb_inode_list_lock); + } inodes_stat.nr_unused--; } @@ -408,7 +415,9 @@ } invalidate_inode_buffers(inode); if (!inode->i_count) { + spin_lock(&wb_inode_list_lock); list_move(&inode->i_list, dispose); + spin_unlock(&wb_inode_list_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; spin_unlock(&inode->i_lock); @@ -486,6 +495,8 @@ down_read(&iprune_sem); spin_lock(&inode_lock); +again: + spin_lock(&wb_inode_list_lock); for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) { struct inode *inode; @@ -494,13 +505,17 @@ inode = list_entry(inode_unused.prev, struct inode, i_list); - spin_lock(&inode->i_lock); + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&wb_inode_list_lock); + goto again; + } if (inode->i_state || inode->i_count) { list_move(&inode->i_list, &inode_unused); spin_unlock(&inode->i_lock); continue; } if (inode_has_buffers(inode) || inode->i_data.nrpages) { + spin_unlock(&wb_inode_list_lock); __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&inode_lock); @@ -509,11 +524,16 @@ 0, -1); iput(inode); spin_lock(&inode_lock); +again2: + spin_lock(&wb_inode_list_lock); if (inode != list_entry(inode_unused.next, struct inode, i_list)) continue; /* wrong inode or list_empty */ - spin_lock(&inode->i_lock); + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&wb_inode_list_lock); + goto again2; + } if (!can_unuse(inode)) { spin_unlock(&inode->i_lock); continue; @@ -531,6 +551,7 @@ else __count_vm_events(PGINODESTEAL, reap); spin_unlock(&inode_lock); + spin_unlock(&wb_inode_list_lock); dispose_list(&freeable); up_read(&iprune_sem); @@ -663,7 +684,9 @@ spin_lock(&sb_inode_list_lock); list_add(&inode->i_sb_list, &sb->s_inodes); spin_unlock(&sb_inode_list_lock); + spin_lock(&wb_inode_list_lock); list_add(&inode->i_list, &inode_in_use); + spin_unlock(&wb_inode_list_lock); if (head) { spin_lock(&inode_hash_lock); hlist_add_head(&inode->i_hash, head); @@ -1316,8 +1339,11 @@ drop = generic_drop_inode(inode); if (!drop) { - if (!(inode->i_state & (I_DIRTY|I_SYNC))) + if (!(inode->i_state & (I_DIRTY|I_SYNC))) { + spin_lock(&wb_inode_list_lock); list_move(&inode->i_list, &inode_unused); + spin_unlock(&wb_inode_list_lock); + } inodes_stat.nr_unused++; if (sb->s_flags & MS_ACTIVE) { spin_unlock(&inode->i_lock); @@ -1341,7 +1367,9 @@ hlist_del_init(&inode->i_hash); spin_unlock(&inode_hash_lock); } + spin_lock(&wb_inode_list_lock); list_del_init(&inode->i_list); + spin_unlock(&wb_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&sb_inode_list_lock); WARN_ON(inode->i_state & I_NEW); @@ -1374,17 +1402,17 @@ if (inode) { BUG_ON(inode->i_state & I_CLEAR); -retry: +retry1: spin_lock(&inode->i_lock); if (inode->i_count == 1) { if (!spin_trylock(&inode_lock)) { +retry2: spin_unlock(&inode->i_lock); - goto retry; + goto retry1; } if (!spin_trylock(&sb_inode_list_lock)) { spin_unlock(&inode_lock); - spin_unlock(&inode->i_lock); - goto retry; + goto retry2; } inode->i_count--; iput_final(inode); Index: linux-2.6/include/linux/writeback.h =================================================================== --- linux-2.6.orig/include/linux/writeback.h 2010-10-19 14:18:58.000000000 +1100 +++ linux-2.6/include/linux/writeback.h 2010-10-19 14:19:32.000000000 +1100 @@ -11,6 +11,7 @@ extern spinlock_t inode_lock; extern spinlock_t sb_inode_list_lock; +extern spinlock_t wb_inode_list_lock; extern struct list_head inode_in_use; extern struct list_head inode_unused; Index: linux-2.6/mm/backing-dev.c =================================================================== --- linux-2.6.orig/mm/backing-dev.c 2010-10-19 14:17:24.000000000 +1100 +++ linux-2.6/mm/backing-dev.c 2010-10-19 14:19:32.000000000 +1100 @@ -74,12 +74,14 @@ nr_wb = nr_dirty = nr_io = nr_more_io = 0; spin_lock(&inode_lock); + spin_lock(&wb_inode_list_lock); list_for_each_entry(inode, &wb->b_dirty, i_list) nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_list) nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_list) nr_more_io++; + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode_lock); global_dirty_limits(&background_thresh, &dirty_thresh); @@ -683,9 +685,11 @@ struct bdi_writeback *dst = &default_backing_dev_info.wb; spin_lock(&inode_lock); + spin_lock(&wb_inode_list_lock); list_splice(&bdi->wb.b_dirty, &dst->b_dirty); list_splice(&bdi->wb.b_io, &dst->b_io); list_splice(&bdi->wb.b_more_io, &dst->b_more_io); + spin_unlock(&wb_inode_list_lock); spin_unlock(&inode_lock); } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/