From: Nick Piggin <npiggin@xxxxxxx>
The inode moves between different lists protected by the inode_lock. Introduce
a new lock that protects all of the lists (dirty, unused, in use, etc) that the
inode will move around as it changes state. As this is mostly a list for
protecting the writeback lists, name it wb_inode_list_lock and nest all the
list manipulations in this lock inside the current inode_lock scope.
Signed-off-by: Nick Piggin <npiggin@xxxxxxx>
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
---
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(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 2edaad7..fb7b723 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -161,6 +161,7 @@ static void redirty_tail(struct inode *inode)
{
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;
@@ -178,6 +179,7 @@ static void requeue_io(struct inode *inode)
{
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);
}
@@ -218,6 +220,7 @@ static void move_expired_inodes(struct list_head *delaying_queue,
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 &&
@@ -281,11 +284,13 @@ static void inode_wait_for_writeback(struct inode *inode)
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);
}
}
@@ -339,6 +344,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
/* 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);
@@ -375,6 +381,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
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)) {
@@ -461,11 +468,18 @@ static bool pin_sb_for_writeback(struct super_block *sb)
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) {
/*
@@ -474,9 +488,12 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
* 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
@@ -485,10 +502,9 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
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;
}
/*
@@ -511,11 +527,13 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
*/
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;
@@ -535,6 +553,9 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
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);
@@ -544,7 +565,12 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
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);
@@ -553,6 +579,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
if (ret)
break;
}
+ spin_unlock(&wb_inode_list_lock);
spin_unlock(&inode_lock);
/* Leave any unwritten inodes on b_io */
}
@@ -563,9 +590,11 @@ static void __writeback_inodes_sb(struct super_block *sb,
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);
}
@@ -676,13 +705,22 @@ static long wb_writeback(struct bdi_writeback *wb,
* 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);
}
@@ -993,8 +1031,10 @@ void __mark_inode_dirty(struct inode *inode, int flags)
wakeup_bdi = true;
}
+ spin_lock(&wb_inode_list_lock);
inode->dirtied_when = jiffies;
list_move(&inode->i_list, &bdi->wb.b_dirty);
+ spin_unlock(&wb_inode_list_lock);
}
}
out:
@@ -1183,7 +1223,9 @@ int write_inode_now(struct inode *inode, int sync)
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)
@@ -1209,7 +1251,9 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
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;
diff --git a/fs/inode.c b/fs/inode.c
index 2e8ab8e..e15620f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -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 @@ static struct hlist_head *inode_hashtable __read_mostly;
*/
DEFINE_SPINLOCK(inode_lock);
DEFINE_SPINLOCK(sb_inode_list_lock);
+DEFINE_SPINLOCK(wb_inode_list_lock);
DEFINE_SPINLOCK(inode_hash_lock);
/*
@@ -304,8 +308,11 @@ void __iget(struct inode *inode)
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 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
}
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 @@ static void prune_icache(int nr_to_scan)
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 @@ static void prune_icache(int nr_to_scan)
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 @@ static void prune_icache(int nr_to_scan)
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 @@ static void prune_icache(int nr_to_scan)
else
__count_vm_events(PGINODESTEAL, reap);
spin_unlock(&inode_lock);
+ spin_unlock(&wb_inode_list_lock);
dispose_list(&freeable);
up_read(&iprune_sem);
@@ -654,7 +675,9 @@ __inode_add_to_lists(struct super_block *sb, struct hlist_head *head,
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);
@@ -1308,8 +1331,11 @@ static void iput_final(struct inode *inode)
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);
@@ -1333,7 +1359,9 @@ static void iput_final(struct inode *inode)
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);
@@ -1366,17 +1394,17 @@ void iput(struct inode *inode)
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);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 35d6e81..8b9c24f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -11,6 +11,7 @@ struct backing_dev_info;
extern spinlock_t inode_lock;
extern spinlock_t sb_inode_list_lock;
+extern spinlock_t wb_inode_list_lock;
extern spinlock_t inode_hash_lock;
extern struct list_head inode_in_use;
extern struct list_head inode_unused;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c2bf86f..b1e2987 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -73,12 +73,14 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
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);
@@ -681,9 +683,11 @@ void bdi_destroy(struct backing_dev_info *bdi)
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);
}
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
