/proc/<pid>/cmdline: add back the setproctitle() special case

[platform/kernel/linux-rpi.git] / fs / fs-writeback.c

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 471d863..7ee86d8 100644 (file)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -331,11 +331,22 @@ struct inode_switch_wbs_context {
        struct work_struct      work;
 };
 
+static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi)
+{
+       down_write(&bdi->wb_switch_rwsem);
+}
+
+static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi)
+{
+       up_write(&bdi->wb_switch_rwsem);
+}
+
 static void inode_switch_wbs_work_fn(struct work_struct *work)
 {
        struct inode_switch_wbs_context *isw =
                container_of(work, struct inode_switch_wbs_context, work);
        struct inode *inode = isw->inode;
+       struct backing_dev_info *bdi = inode_to_bdi(inode);
        struct address_space *mapping = inode->i_mapping;
        struct bdi_writeback *old_wb = inode->i_wb;
        struct bdi_writeback *new_wb = isw->new_wb;
@@ -344,6 +355,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
        void **slot;
 
        /*
+        * If @inode switches cgwb membership while sync_inodes_sb() is
+        * being issued, sync_inodes_sb() might miss it.  Synchronize.
+        */
+       down_read(&bdi->wb_switch_rwsem);
+
+       /*
         * By the time control reaches here, RCU grace period has passed
         * since I_WB_SWITCH assertion and all wb stat update transactions
         * between unlocked_inode_to_wb_begin/end() are guaranteed to be
@@ -435,6 +452,8 @@ skip_switch:
        spin_unlock(&new_wb->list_lock);
        spin_unlock(&old_wb->list_lock);
 
+       up_read(&bdi->wb_switch_rwsem);
+
        if (switched) {
                wb_wakeup(new_wb);
                wb_put(old_wb);
@@ -475,9 +494,18 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
        if (inode->i_state & I_WB_SWITCH)
                return;
 
+       /*
+        * Avoid starting new switches while sync_inodes_sb() is in
+        * progress.  Otherwise, if the down_write protected issue path
+        * blocks heavily, we might end up starting a large number of
+        * switches which will block on the rwsem.
+        */
+       if (!down_read_trylock(&bdi->wb_switch_rwsem))
+               return;
+
        isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
        if (!isw)
-               return;
+               goto out_unlock;
 
        /* find and pin the new wb */
        rcu_read_lock();
@@ -502,8 +530,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
        isw->inode = inode;
 
-       atomic_inc(&isw_nr_in_flight);
-
        /*
         * In addition to synchronizing among switchers, I_WB_SWITCH tells
         * the RCU protected stat update paths to grab the i_page
@@ -511,12 +537,17 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
         * Let's continue after I_WB_SWITCH is guaranteed to be visible.
         */
        call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
-       return;
+
+       atomic_inc(&isw_nr_in_flight);
+
+       goto out_unlock;
 
 out_free:
        if (isw->new_wb)
                wb_put(isw->new_wb);
        kfree(isw);
+out_unlock:
+       up_read(&bdi->wb_switch_rwsem);
 }
 
 /**
@@ -690,6 +721,7 @@ void wbc_detach_inode(struct writeback_control *wbc)
 void wbc_account_io(struct writeback_control *wbc, struct page *page,
                    size_t bytes)
 {
+       struct cgroup_subsys_state *css;
        int id;
 
        /*
@@ -701,7 +733,12 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
        if (!wbc->wb)
                return;
 
-       id = mem_cgroup_css_from_page(page)->id;
+       css = mem_cgroup_css_from_page(page);
+       /* dead cgroups shouldn't contribute to inode ownership arbitration */
+       if (!(css->flags & CSS_ONLINE))
+               return;
+
+       id = css->id;
 
        if (id == wbc->wb_id) {
                wbc->wb_bytes += bytes;
@@ -878,7 +915,11 @@ restart:
 void cgroup_writeback_umount(void)
 {
        if (atomic_read(&isw_nr_in_flight)) {
-               synchronize_rcu();
+               /*
+                * Use rcu_barrier() to wait for all pending callbacks to
+                * ensure that all in-flight wb switches are in the workqueue.
+                */
+               rcu_barrier();
                flush_workqueue(isw_wq);
        }
 }
@@ -894,6 +935,9 @@ fs_initcall(cgroup_writeback_init);
 
 #else  /* CONFIG_CGROUP_WRITEBACK */
 
+static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
+static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
+
 static struct bdi_writeback *
 locked_inode_to_wb_and_lock_list(struct inode *inode)
        __releases(&inode->i_lock)
@@ -2420,8 +2464,11 @@ void sync_inodes_sb(struct super_block *sb)
                return;
        WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
+       /* protect against inode wb switch, see inode_switch_wbs_work_fn() */
+       bdi_down_write_wb_switch_rwsem(bdi);
        bdi_split_work_to_wbs(bdi, &work, false);
        wb_wait_for_completion(bdi, &done);
+       bdi_up_write_wb_switch_rwsem(bdi);
 
        wait_sb_inodes(sb);
 }