laptop-mode: Make flushes per-device

One of the features of laptop-mode is that it forces a writeout of dirty
pages if something else triggers a physical read or write from a device.
The current implementation flushes pages on all devices, rather than only
the one that triggered the flush. This patch alters the behaviour so that
only the recently accessed block device is flushed, preventing other
disks being spun up for no terribly good reason.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

4 files changed, 30 insertions, 21 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 1d94f15d7f0..4b1b29ef2cb 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -451,6 +451,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	blk_sync_queue(q);
 
+	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	mutex_lock(&q->sysfs_lock);
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 	mutex_unlock(&q->sysfs_lock);
@@ -511,6 +512,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 		return NULL;
 	}
 
+	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
+		    laptop_mode_timer_fn, (unsigned long) q);
 	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
@@ -2101,7 +2104,7 @@ static void blk_finish_request(struct request *req, int error)
 	BUG_ON(blk_queued_rq(req));
 
 	if (unlikely(laptop_mode) && blk_fs_request(req))
-		laptop_io_completion();
+		laptop_io_completion(&req->q->backing_dev_info);
 
 	blk_delete_timer(req);
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index fcbc26af00e..2742e1adfc3 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/timer.h>
 #include <linux/writeback.h>
 #include <asm/atomic.h>
 
@@ -88,6 +89,8 @@ struct backing_dev_info {
 
 	struct device *dev;
 
+	struct timer_list laptop_mode_wb_timer;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debug_dir;
 	struct dentry *debug_stats;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 36520ded3e0..eb38a2c645f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -96,8 +96,10 @@ static inline void inode_sync_wait(struct inode *inode)
 /*
  * mm/page-writeback.c
  */
-void laptop_io_completion(void);
+void laptop_io_completion(struct backing_dev_info *info);
 void laptop_sync_completion(void);
+void laptop_mode_sync(struct work_struct *work);
+void laptop_mode_timer_fn(unsigned long data);
 void throttle_vm_writeout(gfp_t gfp_mask);
 
 /* These are exported to sysctl. */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0b19943ecf8..d0f2b3765f8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -683,10 +683,6 @@ void throttle_vm_writeout(gfp_t gfp_mask)
         }
 }
 
-static void laptop_timer_fn(unsigned long unused);
-
-static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
-
 /*
  * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
  */
@@ -697,21 +693,19 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write,
 	return 0;
 }
 
-static void do_laptop_sync(struct work_struct *work)
+void laptop_mode_timer_fn(unsigned long data)
 {
-	wakeup_flusher_threads(0);
-	kfree(work);
-}
+	struct request_queue *q = (struct request_queue *)data;
+	int nr_pages = global_page_state(NR_FILE_DIRTY) +
+		global_page_state(NR_UNSTABLE_NFS);
 
-static void laptop_timer_fn(unsigned long unused)
-{
-	struct work_struct *work;
+	/*
+	 * We want to write everything out, not just down to the dirty
+	 * threshold
+	 */
 
-	work = kmalloc(sizeof(*work), GFP_ATOMIC);
-	if (work) {
-		INIT_WORK(work, do_laptop_sync);
-		schedule_work(work);
-	}
+	if (bdi_has_dirty_io(&q->backing_dev_info))
+		bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages);
 }
 
 /*
@@ -719,9 +713,9 @@ static void laptop_timer_fn(unsigned long unused)
  * of all dirty data a few seconds from now.  If the flush is already scheduled
  * then push it back - the user is still using the disk.
  */
-void laptop_io_completion(void)
+void laptop_io_completion(struct backing_dev_info *info)
 {
-	mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
+	mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode);
 }
 
 /*
@@ -731,7 +725,14 @@ void laptop_io_completion(void)
  */
 void laptop_sync_completion(void)
 {
-	del_timer(&laptop_mode_wb_timer);
+	struct backing_dev_info *bdi;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
+		del_timer(&bdi->laptop_mode_wb_timer);
+
+	rcu_read_unlock();
 }
 
 /*