workqueue: reimplement workqueue flushing using color coded works

Reimplement workqueue flushing using color coded works.  wq has the
current work color which is painted on the works being issued via
cwqs.  Flushing a workqueue is achieved by advancing the current work
colors of cwqs and waiting for all the works which have any of the
previous colors to drain.

Currently there are 16 possible colors, one is reserved for no color
and 15 colors are useable allowing 14 concurrent flushes.  When color
space gets full, flush attempts are batched up and processed together
when color frees up, so even with many concurrent flushers, the new
implementation won't build up huge queue of flushers which has to be
processed one after another.

Only works which are queued via __queue_work() are colored.  Works
which are directly put on queue using insert_work() use NO_COLOR and
don't participate in workqueue flushing.  Currently only works used
for work-specific flush fall in this category.

This new implementation leaves only cleanup_workqueue_thread() as the
user of flush_cpu_workqueue().  Just make its users use
flush_workqueue() and kthread_stop() directly and kill
cleanup_workqueue_thread().  As workqueue flushing doesn't use barrier
request anymore, the comment describing the complex synchronization
around it in cleanup_workqueue_thread() is removed together with the
function.

This new implementation is to allow having and sharing multiple
workers per cpu.

Please note that one more bit is reserved for a future work flag by
this patch.  This is to avoid shifting bits and updating comments
later.
Signed-off-by: Tejun Heo <tj@kernel.org>

include/linux/workqueue.h

@@ -26,11 +26,13 @@ enum {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 	WORK_STRUCT_STATIC_BIT	= 1,	/* static initializer (debugobjects) */
-	WORK_STRUCT_FLAG_BITS	= 2,
+	WORK_STRUCT_COLOR_SHIFT	= 3,	/* color for workqueue flushing */
 #else
-	WORK_STRUCT_FLAG_BITS	= 1,
+	WORK_STRUCT_COLOR_SHIFT	= 2,	/* color for workqueue flushing */
 #endif
 
+	WORK_STRUCT_COLOR_BITS	= 4,
+
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
@@ -38,6 +40,21 @@ enum {
 	WORK_STRUCT_STATIC	= 0,
 #endif
 
+	/*
+	 * The last color is no color used for works which don't
+	 * participate in workqueue flushing.
+	 */
+	WORK_NR_COLORS		= (1 << WORK_STRUCT_COLOR_BITS) - 1,
+	WORK_NO_COLOR		= WORK_NR_COLORS,
+
+	/*
+	 * Reserve 6 bits off of cwq pointer w/ debugobjects turned
+	 * off.  This makes cwqs aligned to 64 bytes which isn't too
+	 * excessive while allowing 15 workqueue flush colors.
+	 */
+	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
+				  WORK_STRUCT_COLOR_BITS,
+
 	WORK_STRUCT_FLAG_MASK	= (1UL << WORK_STRUCT_FLAG_BITS) - 1,
 	WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
 };