summaryrefslogtreecommitdiff
path: root/include/linux/backing-dev.h
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2015-05-28 21:50:53 +0300
committerJens Axboe <axboe@fb.com>2015-06-02 17:40:20 +0300
commit682aa8e1a6a1504a4caaa62e6c2c9daae3757210 (patch)
treed2471a86d2a286ef8076f629f9709310d68f4e95 /include/linux/backing-dev.h
parent87e1d789bf55b12fa7c1cdce024499aee3bc0af0 (diff)
downloadlinux-682aa8e1a6a1504a4caaa62e6c2c9daae3757210.tar.xz
writeback: implement unlocked_inode_to_wb transaction and use it for stat updates
The mechanism for detecting whether an inode should switch its wb (bdi_writeback) association is now in place. This patch build the framework for the actual switching. This patch adds a new inode flag I_WB_SWITCHING, which has two functions. First, the easy one, it ensures that there's only one switching in progress for a give inode. Second, it's used as a mechanism to synchronize wb stat updates. The two stats, WB_RECLAIMABLE and WB_WRITEBACK, aren't event counters but track the current number of dirty pages and pages under writeback respectively. As such, when an inode is moved from one wb to another, the inode's portion of those stats have to be transferred together; unfortunately, this is a bit tricky as those stat updates are percpu operations which are performed without holding any lock in some places. This patch solves the problem in a similar way as memcg. Each such lockless stat updates are wrapped in transaction surrounded by unlocked_inode_to_wb_begin/end(). During normal operation, they map to rcu_read_lock/unlock(); however, if I_WB_SWITCHING is asserted, mapping->tree_lock is grabbed across the transaction. In turn, the switching path sets I_WB_SWITCHING and waits for a RCU grace period to pass before actually starting to switch, which guarantees that all stat update paths are synchronizing against mapping->tree_lock. This patch still doesn't implement the actual switching. v3: Updated on top of the recent cancel_dirty_page() updates. unlocked_inode_to_wb_begin() now nests inside mem_cgroup_begin_page_stat() to match the locking order. v2: The i_wb access transaction will be used for !stat accesses too. Function names and comments updated accordingly. s/inode_wb_stat_unlocked_{begin|end}/unlocked_inode_to_wb_{begin|end}/ s/switch_wb/switch_wbs/ Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'include/linux/backing-dev.h')
-rw-r--r--include/linux/backing-dev.h54
1 files changed, 54 insertions, 0 deletions
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index b1d2489a6536..73ffa32e58ee 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -332,6 +332,50 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
return inode->i_wb;
}
+/**
+ * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
+ * @inode: target inode
+ * @lockedp: temp bool output param, to be passed to the end function
+ *
+ * The caller wants to access the wb associated with @inode but isn't
+ * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This
+ * function determines the wb associated with @inode and ensures that the
+ * association doesn't change until the transaction is finished with
+ * unlocked_inode_to_wb_end().
+ *
+ * The caller must call unlocked_inode_to_wb_end() with *@lockdep
+ * afterwards and can't sleep during transaction. IRQ may or may not be
+ * disabled on return.
+ */
+static inline struct bdi_writeback *
+unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+{
+ rcu_read_lock();
+
+ /*
+ * Paired with store_release in inode_switch_wb_work_fn() and
+ * ensures that we see the new wb if we see cleared I_WB_SWITCH.
+ */
+ *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+
+ if (unlikely(*lockedp))
+ spin_lock_irq(&inode->i_mapping->tree_lock);
+ return inode_to_wb(inode);
+}
+
+/**
+ * unlocked_inode_to_wb_end - end inode wb access transaction
+ * @inode: target inode
+ * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ */
+static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+{
+ if (unlikely(locked))
+ spin_unlock_irq(&inode->i_mapping->tree_lock);
+
+ rcu_read_unlock();
+}
+
struct wb_iter {
int start_blkcg_id;
struct radix_tree_iter tree_iter;
@@ -420,6 +464,16 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
return &inode_to_bdi(inode)->wb;
}
+static inline struct bdi_writeback *
+unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+{
+ return inode_to_wb(inode);
+}
+
+static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+{
+}
+
static inline void wb_memcg_offline(struct mem_cgroup *memcg)
{
}