summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_buf.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/xfs_buf.c')
-rw-r--r--fs/xfs/xfs_buf.c253
1 files changed, 132 insertions, 121 deletions
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index c06823fe10d3..263470075ea2 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -81,54 +81,6 @@ xfs_buf_vmap_len(
}
/*
- * xfs_buf_lru_add - add a buffer to the LRU.
- *
- * The LRU takes a new reference to the buffer so that it will only be freed
- * once the shrinker takes the buffer off the LRU.
- */
-STATIC void
-xfs_buf_lru_add(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
-
- spin_lock(&btp->bt_lru_lock);
- if (list_empty(&bp->b_lru)) {
- atomic_inc(&bp->b_hold);
- list_add_tail(&bp->b_lru, &btp->bt_lru);
- btp->bt_lru_nr++;
- bp->b_lru_flags &= ~_XBF_LRU_DISPOSE;
- }
- spin_unlock(&btp->bt_lru_lock);
-}
-
-/*
- * xfs_buf_lru_del - remove a buffer from the LRU
- *
- * The unlocked check is safe here because it only occurs when there are not
- * b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there
- * to optimise the shrinker removing the buffer from the LRU and calling
- * xfs_buf_free(). i.e. it removes an unnecessary round trip on the
- * bt_lru_lock.
- */
-STATIC void
-xfs_buf_lru_del(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
-
- if (list_empty(&bp->b_lru))
- return;
-
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- }
- spin_unlock(&btp->bt_lru_lock);
-}
-
-/*
* When we mark a buffer stale, we remove the buffer from the LRU and clear the
* b_lru_ref count so that the buffer is freed immediately when the buffer
* reference count falls to zero. If the buffer is already on the LRU, we need
@@ -151,20 +103,14 @@ xfs_buf_stale(
*/
bp->b_flags &= ~_XBF_DELWRI_Q;
- atomic_set(&(bp)->b_lru_ref, 0);
- if (!list_empty(&bp->b_lru)) {
- struct xfs_buftarg *btp = bp->b_target;
+ spin_lock(&bp->b_lock);
+ atomic_set(&bp->b_lru_ref, 0);
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
+ (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
+ atomic_dec(&bp->b_hold);
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru) &&
- !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- atomic_dec(&bp->b_hold);
- }
- spin_unlock(&btp->bt_lru_lock);
- }
ASSERT(atomic_read(&bp->b_hold) >= 1);
+ spin_unlock(&bp->b_lock);
}
static int
@@ -228,6 +174,7 @@ _xfs_buf_alloc(
INIT_LIST_HEAD(&bp->b_list);
RB_CLEAR_NODE(&bp->b_rbnode);
sema_init(&bp->b_sema, 0); /* held, no waiters */
+ spin_lock_init(&bp->b_lock);
XB_SET_OWNER(bp);
bp->b_target = target;
bp->b_flags = flags;
@@ -917,12 +864,33 @@ xfs_buf_rele(
ASSERT(atomic_read(&bp->b_hold) > 0);
if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
- if (!(bp->b_flags & XBF_STALE) &&
- atomic_read(&bp->b_lru_ref)) {
- xfs_buf_lru_add(bp);
+ spin_lock(&bp->b_lock);
+ if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+ /*
+ * If the buffer is added to the LRU take a new
+ * reference to the buffer for the LRU and clear the
+ * (now stale) dispose list state flag
+ */
+ if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
+ bp->b_state &= ~XFS_BSTATE_DISPOSE;
+ atomic_inc(&bp->b_hold);
+ }
+ spin_unlock(&bp->b_lock);
spin_unlock(&pag->pag_buf_lock);
} else {
- xfs_buf_lru_del(bp);
+ /*
+ * most of the time buffers will already be removed from
+ * the LRU, so optimise that case by checking for the
+ * XFS_BSTATE_DISPOSE flag indicating the last list the
+ * buffer was on was the disposal list
+ */
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
+ list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
+ } else {
+ ASSERT(list_empty(&bp->b_lru));
+ }
+ spin_unlock(&bp->b_lock);
+
ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
spin_unlock(&pag->pag_buf_lock);
@@ -1502,83 +1470,121 @@ xfs_buf_iomove(
* returned. These buffers will have an elevated hold count, so wait on those
* while freeing all the buffers only held by the LRU.
*/
+static enum lru_status
+xfs_buftarg_wait_rele(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ if (atomic_read(&bp->b_hold) > 1) {
+ /* need to wait, so skip it this pass */
+ trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+ return LRU_SKIP;
+ }
+ if (!spin_trylock(&bp->b_lock))
+ return LRU_SKIP;
+
+ /*
+ * clear the LRU reference count so the buffer doesn't get
+ * ignored in xfs_buf_rele().
+ */
+ atomic_set(&bp->b_lru_ref, 0);
+ bp->b_state |= XFS_BSTATE_DISPOSE;
+ list_move(item, dispose);
+ spin_unlock(&bp->b_lock);
+ return LRU_REMOVED;
+}
+
void
xfs_wait_buftarg(
struct xfs_buftarg *btp)
{
- struct xfs_buf *bp;
+ LIST_HEAD(dispose);
+ int loop = 0;
-restart:
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
- if (atomic_read(&bp->b_hold) > 1) {
- trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- spin_unlock(&btp->bt_lru_lock);
- delay(100);
- goto restart;
+ /* loop until there is nothing left on the lru list. */
+ while (list_lru_count(&btp->bt_lru)) {
+ list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,
+ &dispose, LONG_MAX);
+
+ while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
+ bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
+ list_del_init(&bp->b_lru);
+ xfs_buf_rele(bp);
}
- /*
- * clear the LRU reference count so the buffer doesn't get
- * ignored in xfs_buf_rele().
- */
- atomic_set(&bp->b_lru_ref, 0);
- spin_unlock(&btp->bt_lru_lock);
- xfs_buf_rele(bp);
- spin_lock(&btp->bt_lru_lock);
+ if (loop++ != 0)
+ delay(100);
}
- spin_unlock(&btp->bt_lru_lock);
}
-int
-xfs_buftarg_shrink(
+static enum lru_status
+xfs_buftarg_isolate(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ /*
+ * we are inverting the lru lock/bp->b_lock here, so use a trylock.
+ * If we fail to get the lock, just skip it.
+ */
+ if (!spin_trylock(&bp->b_lock))
+ return LRU_SKIP;
+ /*
+ * Decrement the b_lru_ref count unless the value is already
+ * zero. If the value is already zero, we need to reclaim the
+ * buffer, otherwise it gets another trip through the LRU.
+ */
+ if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
+ spin_unlock(&bp->b_lock);
+ return LRU_ROTATE;
+ }
+
+ bp->b_state |= XFS_BSTATE_DISPOSE;
+ list_move(item, dispose);
+ spin_unlock(&bp->b_lock);
+ return LRU_REMOVED;
+}
+
+static unsigned long
+xfs_buftarg_shrink_scan(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_buftarg *btp = container_of(shrink,
struct xfs_buftarg, bt_shrinker);
- struct xfs_buf *bp;
- int nr_to_scan = sc->nr_to_scan;
LIST_HEAD(dispose);
+ unsigned long freed;
+ unsigned long nr_to_scan = sc->nr_to_scan;
- if (!nr_to_scan)
- return btp->bt_lru_nr;
-
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- if (nr_to_scan-- <= 0)
- break;
-
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
-
- /*
- * Decrement the b_lru_ref count unless the value is already
- * zero. If the value is already zero, we need to reclaim the
- * buffer, otherwise it gets another trip through the LRU.
- */
- if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- continue;
- }
-
- /*
- * remove the buffer from the LRU now to avoid needing another
- * lock round trip inside xfs_buf_rele().
- */
- list_move(&bp->b_lru, &dispose);
- btp->bt_lru_nr--;
- bp->b_lru_flags |= _XBF_LRU_DISPOSE;
- }
- spin_unlock(&btp->bt_lru_lock);
+ freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
+ &dispose, &nr_to_scan);
while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
xfs_buf_rele(bp);
}
- return btp->bt_lru_nr;
+ return freed;
+}
+
+static unsigned long
+xfs_buftarg_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_buftarg *btp = container_of(shrink,
+ struct xfs_buftarg, bt_shrinker);
+ return list_lru_count_node(&btp->bt_lru, sc->nid);
}
void
@@ -1587,6 +1593,7 @@ xfs_free_buftarg(
struct xfs_buftarg *btp)
{
unregister_shrinker(&btp->bt_shrinker);
+ list_lru_destroy(&btp->bt_lru);
if (mp->m_flags & XFS_MOUNT_BARRIER)
xfs_blkdev_issue_flush(btp);
@@ -1660,12 +1667,16 @@ xfs_alloc_buftarg(
if (!btp->bt_bdi)
goto error;
- INIT_LIST_HEAD(&btp->bt_lru);
- spin_lock_init(&btp->bt_lru_lock);
if (xfs_setsize_buftarg_early(btp, bdev))
goto error;
- btp->bt_shrinker.shrink = xfs_buftarg_shrink;
+
+ if (list_lru_init(&btp->bt_lru))
+ goto error;
+
+ btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
+ btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
btp->bt_shrinker.seeks = DEFAULT_SEEKS;
+ btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE;
register_shrinker(&btp->bt_shrinker);
return btp;