block: initial patch for on-stack per-task plugging

This patch adds support for creating a queuing context outside
of the queue itself. This enables us to batch up pieces of IO
before grabbing the block device queue lock and submitting them to
the IO scheduler.

The context is created on the stack of the process and assigned in
the task structure, so that we can auto-unplug it if we hit a schedule
event.

The current queue plugging happens implicitly if IO is submitted to
an empty device, yet callers have to remember to unplug that IO when
they are going to wait for it. This is an ugly API and has caused bugs
in the past. Additionally, it requires hacks in the vm (->sync_page()
callback) to handle that logic. By switching to an explicit plugging
scheme we make the API a lot nicer and can get rid of the ->sync_page()
hack in the vm.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

4 files changed, 51 insertions, 0 deletions

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index dddedfc0af8..16b28647304 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -152,6 +152,7 @@ enum rq_flag_bits {
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
+	__REQ_ON_PLUG,		/* on plug list */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -193,5 +194,6 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
+#define REQ_ON_PLUG		(1 << __REQ_ON_PLUG)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f55b2a8b661..5873037eeb9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -871,6 +871,31 @@ struct request_queue *blk_alloc_queue(gfp_t);
 struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
 
+struct blk_plug {
+	unsigned long magic;
+	struct list_head list;
+	unsigned int should_sort;
+};
+
+extern void blk_start_plug(struct blk_plug *);
+extern void blk_finish_plug(struct blk_plug *);
+extern void __blk_flush_plug(struct task_struct *, struct blk_plug *);
+
+static inline void blk_flush_plug(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	if (unlikely(plug))
+		__blk_flush_plug(tsk, plug);
+}
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	return plug && !list_empty(&plug->list);
+}
+
 /*
  * tag stuff
  */
@@ -1294,6 +1319,23 @@ static inline long nr_blockdev_pages(void)
 	return 0;
 }
 
+static inline void blk_start_plug(struct list_head *list)
+{
+}
+
+static inline void blk_finish_plug(struct list_head *list)
+{
+}
+
+static inline void blk_flush_plug(struct task_struct *tsk)
+{
+}
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	return false;
+}
+
 #endif /* CONFIG_BLOCK */
 
 #endif
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 39b68edb388..8857cf9adbb 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -105,6 +105,7 @@ extern void elv_add_request(struct request_queue *, struct request *, int, int);
 extern void __elv_add_request(struct request_queue *, struct request *, int, int);
 extern void elv_insert(struct request_queue *, struct request *, int);
 extern int elv_merge(struct request_queue *, struct request **, struct bio *);
+extern int elv_try_merge(struct request *, struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
 			       struct request *);
 extern void elv_merged_request(struct request_queue *, struct request *, int);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5ed06..96ac2264374 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,6 +99,7 @@ struct robust_list_head;
 struct bio_list;
 struct fs_struct;
 struct perf_event_context;
+struct blk_plug;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -1429,6 +1430,11 @@ struct task_struct {
 /* stacked block device info */
 	struct bio_list *bio_list;
 
+#ifdef CONFIG_BLOCK
+/* stack plugging */
+	struct blk_plug *plug;
+#endif
+
 /* VM state */
 	struct reclaim_state *reclaim_state;