This patch adds the possibilty to read-lock an extent
even if it is already write-locked from the same thread.
Subvolume quota needs this capability.
Signed-off-by: Arne Jansen <sensille@xxxxxxx>
---
fs/btrfs/ctree.c | 22 ++++++++++++--------
fs/btrfs/ctree.h | 1 +
fs/btrfs/extent_io.c | 1 +
fs/btrfs/extent_io.h | 2 +
fs/btrfs/locking.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++--
fs/btrfs/locking.h | 2 +-
6 files changed, 66 insertions(+), 13 deletions(-)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 51b387b..964ac9a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -186,13 +186,14 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
* tree until you end up with a lock on the root. A locked buffer
* is returned, with a reference held.
*/
-struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
+struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root,
+ int nested)
{
struct extent_buffer *eb;
while (1) {
eb = btrfs_root_node(root);
- btrfs_tree_read_lock(eb);
+ btrfs_tree_read_lock(eb, nested);
if (eb == root->node)
break;
btrfs_tree_read_unlock(eb);
@@ -1620,6 +1621,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
/* everything at write_lock_level or lower must be write locked */
int write_lock_level = 0;
u8 lowest_level = 0;
+ int nested = p->nested;
lowest_level = p->lowest_level;
WARN_ON(lowest_level && ins_len > 0);
@@ -1661,8 +1663,9 @@ again:
b = root->commit_root;
extent_buffer_get(b);
level = btrfs_header_level(b);
+ BUG_ON(p->skip_locking && nested);
if (!p->skip_locking)
- btrfs_tree_read_lock(b);
+ btrfs_tree_read_lock(b, 0);
} else {
if (p->skip_locking) {
b = btrfs_root_node(root);
@@ -1671,7 +1674,7 @@ again:
/* we don't know the level of the root node
* until we actually have it read locked
*/
- b = btrfs_read_lock_root_node(root);
+ b = btrfs_read_lock_root_node(root, nested);
level = btrfs_header_level(b);
if (level <= write_lock_level) {
/* whoops, must trade for write lock */
@@ -1810,7 +1813,8 @@ cow_done:
err = btrfs_try_tree_read_lock(b);
if (!err) {
btrfs_set_path_blocking(p);
- btrfs_tree_read_lock(b);
+ btrfs_tree_read_lock(b,
+ nested);
btrfs_clear_path_blocking(p, b,
BTRFS_READ_LOCK);
}
@@ -3955,7 +3959,7 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
WARN_ON(!path->keep_locks);
again:
- cur = btrfs_read_lock_root_node(root);
+ cur = btrfs_read_lock_root_node(root, 0);
level = btrfs_header_level(cur);
WARN_ON(path->nodes[level]);
path->nodes[level] = cur;
@@ -4049,7 +4053,7 @@ find_next_key:
cur = read_node_slot(root, cur, slot);
BUG_ON(!cur);
- btrfs_tree_read_lock(cur);
+ btrfs_tree_read_lock(cur, 0);
path->locks[level - 1] = BTRFS_READ_LOCK;
path->nodes[level - 1] = cur;
@@ -4243,7 +4247,7 @@ again:
ret = btrfs_try_tree_read_lock(next);
if (!ret) {
btrfs_set_path_blocking(path);
- btrfs_tree_read_lock(next);
+ btrfs_tree_read_lock(next, 0);
btrfs_clear_path_blocking(path, next,
BTRFS_READ_LOCK);
}
@@ -4280,7 +4284,7 @@ again:
ret = btrfs_try_tree_read_lock(next);
if (!ret) {
btrfs_set_path_blocking(path);
- btrfs_tree_read_lock(next);
+ btrfs_tree_read_lock(next, 0);
btrfs_clear_path_blocking(path, next,
BTRFS_READ_LOCK);
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 68f2315..2765b8d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -487,6 +487,7 @@ struct btrfs_path {
unsigned int skip_locking:1;
unsigned int leave_spinning:1;
unsigned int search_commit_root:1;
+ unsigned int nested:1;
};
/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d418164..0bb29da 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2979,6 +2979,7 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
atomic_set(&eb->blocking_writers, 0);
atomic_set(&eb->spinning_readers, 0);
atomic_set(&eb->spinning_writers, 0);
+ eb->lock_nested = 0;
init_waitqueue_head(&eb->write_lock_wq);
init_waitqueue_head(&eb->read_lock_wq);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 7b2f0c3..3a2d1f9 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -125,6 +125,7 @@ struct extent_buffer {
struct list_head leak_list;
struct rcu_head rcu_head;
atomic_t refs;
+ pid_t lock_owner;
/* count of read lock holders on the extent buffer */
atomic_t write_locks;
@@ -133,6 +134,7 @@ struct extent_buffer {
atomic_t blocking_readers;
atomic_t spinning_readers;
atomic_t spinning_writers;
+ int lock_nested;
/* protects write locks */
rwlock_t lock;
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index d77b67c..3cd604f 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -33,6 +33,14 @@ void btrfs_assert_tree_read_locked(struct extent_buffer *eb);
*/
void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
{
+ if (eb->lock_nested) {
+ read_lock(&eb->lock);
+ if (eb->lock_nested && current->pid == eb->lock_owner) {
+ read_unlock(&eb->lock);
+ return;
+ }
+ read_unlock(&eb->lock);
+ }
if (rw == BTRFS_WRITE_LOCK) {
if (atomic_read(&eb->blocking_writers) == 0) {
WARN_ON(atomic_read(&eb->spinning_writers) != 1);
@@ -57,6 +65,14 @@ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
*/
void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
{
+ if (eb->lock_nested) {
+ read_lock(&eb->lock);
+ if (&eb->lock_nested && current->pid == eb->lock_owner) {
+ read_unlock(&eb->lock);
+ return;
+ }
+ read_unlock(&eb->lock);
+ }
if (rw == BTRFS_WRITE_LOCK_BLOCKING) {
BUG_ON(atomic_read(&eb->blocking_writers) != 1);
write_lock(&eb->lock);
@@ -78,15 +94,24 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
* take a spinning read lock. This will wait for any blocking
* writers
*/
-void btrfs_tree_read_lock(struct extent_buffer *eb)
+void btrfs_tree_read_lock(struct extent_buffer *eb, int nested)
{
again:
+ if (nested) {
+ read_lock(&eb->lock);
+ if (atomic_read(&eb->blocking_writers) &&
+ current->pid == eb->lock_owner) {
+ BUG_ON(eb->lock_nested);
+ eb->lock_nested = 1;
+ read_unlock(&eb->lock);
+ return;
+ }
+ read_unlock(&eb->lock);
+ }
wait_event(eb->write_lock_wq, atomic_read(&eb->blocking_writers) == 0);
read_lock(&eb->lock);
if (atomic_read(&eb->blocking_writers)) {
read_unlock(&eb->lock);
- wait_event(eb->write_lock_wq,
- atomic_read(&eb->blocking_writers) == 0);
goto again;
}
atomic_inc(&eb->read_locks);
@@ -129,6 +154,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
}
atomic_inc(&eb->write_locks);
atomic_inc(&eb->spinning_writers);
+ eb->lock_owner = current->pid;
return 1;
}
@@ -137,6 +163,15 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
*/
void btrfs_tree_read_unlock(struct extent_buffer *eb)
{
+ if (eb->lock_nested) {
+ read_lock(&eb->lock);
+ if (eb->lock_nested && current->pid == eb->lock_owner) {
+ eb->lock_nested = 0;
+ read_unlock(&eb->lock);
+ return;
+ }
+ read_unlock(&eb->lock);
+ }
btrfs_assert_tree_read_locked(eb);
WARN_ON(atomic_read(&eb->spinning_readers) == 0);
atomic_dec(&eb->spinning_readers);
@@ -149,6 +184,15 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
*/
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
{
+ if (eb->lock_nested) {
+ read_lock(&eb->lock);
+ if (eb->lock_nested && current->pid == eb->lock_owner) {
+ eb->lock_nested = 0;
+ read_unlock(&eb->lock);
+ return;
+ }
+ read_unlock(&eb->lock);
+ }
btrfs_assert_tree_read_locked(eb);
WARN_ON(atomic_read(&eb->blocking_readers) == 0);
if (atomic_dec_and_test(&eb->blocking_readers))
@@ -181,6 +225,7 @@ again:
WARN_ON(atomic_read(&eb->spinning_writers));
atomic_inc(&eb->spinning_writers);
atomic_inc(&eb->write_locks);
+ eb->lock_owner = current->pid;
return 0;
}
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 17247dd..c6d69e5 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -28,7 +28,7 @@ int btrfs_tree_lock(struct extent_buffer *eb);
int btrfs_tree_unlock(struct extent_buffer *eb);
int btrfs_try_spin_lock(struct extent_buffer *eb);
-void btrfs_tree_read_lock(struct extent_buffer *eb);
+void btrfs_tree_read_lock(struct extent_buffer *eb, int nested);
void btrfs_tree_read_unlock(struct extent_buffer *eb);
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb);
void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw);
--
1.7.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
