Make workqueue bit operations work on "atomic_long_t"

On architectures where the atomicity of the bit operations is handled by
external means (ie a separate spinlock to protect concurrent accesses),
just doing a direct assignment on the workqueue data field (as done by
commit 4594bf159f1962cec3b727954b7c598b07e2e737) can cause the
assignment to be lost due to lack of serialization with the bitops on
the same word.

So we need to serialize the assignment with the locks on those
architectures (notably older ARM chips, PA-RISC and sparc32).

So rather than using an "unsigned long", let's use "atomic_long_t",
which already has a safe assignment operation (atomic_long_set()) on
such architectures.

This requires that the atomic operations use the same atomicity locks as
the bit operations do, but that is largely the case anyway.  Sparc32
will probably need fixing.

Architectures (including modern ARM with LL/SC) that implement sane
atomic operations for SMP won't see any of this matter.

Cc: Russell King <rmk+lkml@arm.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: David Miller <davem@davemloft.com>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Linux Arch Maintainers <linux-arch@vger.kernel.org>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 22 insertions, 10 deletions

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 5b13dcf02714..2a7b38d87018 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -8,16 +8,21 @@
 #include <linux/timer.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>
+#include <asm/atomic.h>
 
 struct workqueue_struct;
 
 struct work_struct;
 typedef void (*work_func_t)(struct work_struct *work);
 
+/*
+ * The first word is the work queue pointer and the flags rolled into
+ * one
+ */
+#define work_data_bits(work) ((unsigned long *)(&(work)->data))
+
 struct work_struct {
-	/* the first word is the work queue pointer and the flags rolled into
-	 * one */
-	unsigned long management;
+	atomic_long_t data;
 #define WORK_STRUCT_PENDING 0		/* T if work item pending execution */
 #define WORK_STRUCT_NOAUTOREL 1		/* F if work item automatically released on exec */
 #define WORK_STRUCT_FLAG_MASK (3UL)
@@ -26,6 +31,9 @@ struct work_struct {
 	work_func_t func;
 };
 
+#define WORK_DATA_INIT(autorelease) \
+	ATOMIC_LONG_INIT((autorelease) << WORK_STRUCT_NOAUTOREL)
+
 struct delayed_work {
 	struct work_struct work;
 	struct timer_list timer;
@@ -36,13 +44,13 @@ struct execute_work {
 };
 
 #define __WORK_INITIALIZER(n, f) {				\
-	.management = 0,					\
+	.data = WORK_DATA_INIT(0),				\
         .entry	= { &(n).entry, &(n).entry },			\
 	.func = (f),						\
 	}
 
 #define __WORK_INITIALIZER_NAR(n, f) {				\
-	.management = (1 << WORK_STRUCT_NOAUTOREL),		\
+	.data = WORK_DATA_INIT(1),				\
         .entry	= { &(n).entry, &(n).entry },			\
 	.func = (f),						\
 	}
@@ -82,17 +90,21 @@ struct execute_work {
 
 /*
  * initialize all of a work item in one go
+ *
+ * NOTE! No point in using "atomic_long_set()": useing a direct
+ * assignment of the work data initializer allows the compiler
+ * to generate better code.
  */
 #define INIT_WORK(_work, _func)					\
 	do {							\
-		(_work)->management = 0;			\
+		(_work)->data = (atomic_long_t) WORK_DATA_INIT(0);	\
 		INIT_LIST_HEAD(&(_work)->entry);		\
 		PREPARE_WORK((_work), (_func));			\
 	} while (0)
 
 #define INIT_WORK_NAR(_work, _func)					\
 	do {								\
-		(_work)->management = (1 << WORK_STRUCT_NOAUTOREL);	\
+		(_work)->data = (atomic_long_t) WORK_DATA_INIT(1);	\
 		INIT_LIST_HEAD(&(_work)->entry);			\
 		PREPARE_WORK((_work), (_func));				\
 	} while (0)
@@ -114,7 +126,7 @@ struct execute_work {
  * @work: The work item in question
  */
 #define work_pending(work) \
-	test_bit(WORK_STRUCT_PENDING, &(work)->management)
+	test_bit(WORK_STRUCT_PENDING, work_data_bits(work))
 
 /**
  * delayed_work_pending - Find out whether a delayable work item is currently
@@ -143,7 +155,7 @@ struct execute_work {
  * This should also be used to release a delayed work item.
  */
 #define work_release(work) \
-	clear_bit(WORK_STRUCT_PENDING, &(work)->management)
+	clear_bit(WORK_STRUCT_PENDING, work_data_bits(work))
 
 
 extern struct workqueue_struct *__create_workqueue(const char *name,
@@ -188,7 +200,7 @@ static inline int cancel_delayed_work(struct delayed_work *work)
 
 	ret = del_timer_sync(&work->timer);
 	if (ret)
-		clear_bit(WORK_STRUCT_PENDING, &work->work.management);
+		work_release(&work->work);
 	return ret;
 }