Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (55 commits)
workqueue: mark init_workqueues() as early_initcall()
workqueue: explain for_each_*cwq_cpu() iterators
fscache: fix build on !CONFIG_SYSCTL
slow-work: kill it
gfs2: use workqueue instead of slow-work
drm: use workqueue instead of slow-work
cifs: use workqueue instead of slow-work
fscache: drop references to slow-work
fscache: convert operation to use workqueue instead of slow-work
fscache: convert object to use workqueue instead of slow-work
workqueue: fix how cpu number is stored in work->data
workqueue: fix mayday_mask handling on UP
workqueue: fix build problem on !CONFIG_SMP
workqueue: fix locking in retry path of maybe_create_worker()
async: use workqueue for worker pool
workqueue: remove WQ_SINGLE_CPU and use WQ_UNBOUND instead
workqueue: implement unbound workqueue
workqueue: prepare for WQ_UNBOUND implementation
libata: take advantage of cmwq and remove concurrency limitations
workqueue: fix worker management invocation without pending works
...
Fixed up conflicts in fs/cifs/* as per Tejun. Other trivial conflicts in
include/linux/workqueue.h, kernel/trace/Kconfig and kernel/workqueue.c
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index d0f7c81..4f9d277 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -9,6 +9,7 @@
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/lockdep.h>
+#include <linux/threads.h>
#include <asm/atomic.h>
struct workqueue_struct;
@@ -22,12 +23,59 @@
*/
#define work_data_bits(work) ((unsigned long *)(&(work)->data))
+enum {
+ WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */
+ WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */
+ WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+ WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */
+ WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */
+#else
+ WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */
+#endif
+
+ WORK_STRUCT_COLOR_BITS = 4,
+
+ WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT,
+ WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT,
+ WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT,
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+ WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT,
+#else
+ 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,
+
+ /* special cpu IDs */
+ WORK_CPU_UNBOUND = NR_CPUS,
+ WORK_CPU_NONE = NR_CPUS + 1,
+ WORK_CPU_LAST = WORK_CPU_NONE,
+
+ /*
+ * Reserve 7 bits off of cwq pointer w/ debugobjects turned
+ * off. This makes cwqs aligned to 128 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,
+ WORK_STRUCT_NO_CPU = WORK_CPU_NONE << WORK_STRUCT_FLAG_BITS,
+
+ /* bit mask for work_busy() return values */
+ WORK_BUSY_PENDING = 1 << 0,
+ WORK_BUSY_RUNNING = 1 << 1,
+};
+
struct work_struct {
atomic_long_t data;
-#define WORK_STRUCT_PENDING 0 /* T if work item pending execution */
-#define WORK_STRUCT_STATIC 1 /* static initializer (debugobjects) */
-#define WORK_STRUCT_FLAG_MASK (3UL)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
struct list_head entry;
work_func_t func;
#ifdef CONFIG_LOCKDEP
@@ -35,8 +83,9 @@
#endif
};
-#define WORK_DATA_INIT() ATOMIC_LONG_INIT(0)
-#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(2)
+#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU)
+#define WORK_DATA_STATIC_INIT() \
+ ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC)
struct delayed_work {
struct work_struct work;
@@ -96,9 +145,14 @@
#ifdef CONFIG_DEBUG_OBJECTS_WORK
extern void __init_work(struct work_struct *work, int onstack);
extern void destroy_work_on_stack(struct work_struct *work);
+static inline unsigned int work_static(struct work_struct *work)
+{
+ return *work_data_bits(work) & WORK_STRUCT_STATIC;
+}
#else
static inline void __init_work(struct work_struct *work, int onstack) { }
static inline void destroy_work_on_stack(struct work_struct *work) { }
+static inline unsigned int work_static(struct work_struct *work) { return 0; }
#endif
/*
@@ -162,7 +216,7 @@
* @work: The work item in question
*/
#define work_pending(work) \
- test_bit(WORK_STRUCT_PENDING, work_data_bits(work))
+ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
/**
* delayed_work_pending - Find out whether a delayable work item is currently
@@ -177,16 +231,56 @@
* @work: The work item in question
*/
#define work_clear_pending(work) \
- clear_bit(WORK_STRUCT_PENDING, work_data_bits(work))
+ clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
+enum {
+ WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */
+ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */
+ WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */
+ WQ_RESCUER = 1 << 3, /* has an rescue worker */
+ WQ_HIGHPRI = 1 << 4, /* high priority */
+ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */
+
+ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
+ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
+ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2,
+};
+
+/* unbound wq's aren't per-cpu, scale max_active according to #cpus */
+#define WQ_UNBOUND_MAX_ACTIVE \
+ max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU)
+
+/*
+ * System-wide workqueues which are always present.
+ *
+ * system_wq is the one used by schedule[_delayed]_work[_on]().
+ * Multi-CPU multi-threaded. There are users which expect relatively
+ * short queue flush time. Don't queue works which can run for too
+ * long.
+ *
+ * system_long_wq is similar to system_wq but may host long running
+ * works. Queue flushing might take relatively long.
+ *
+ * system_nrt_wq is non-reentrant and guarantees that any given work
+ * item is never executed in parallel by multiple CPUs. Queue
+ * flushing might take relatively long.
+ *
+ * system_unbound_wq is unbound workqueue. Workers are not bound to
+ * any specific CPU, not concurrency managed, and all queued works are
+ * executed immediately as long as max_active limit is not reached and
+ * resources are available.
+ */
+extern struct workqueue_struct *system_wq;
+extern struct workqueue_struct *system_long_wq;
+extern struct workqueue_struct *system_nrt_wq;
+extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *
-__create_workqueue_key(const char *name, int singlethread,
- int freezeable, int rt, struct lock_class_key *key,
- const char *lock_name);
+__alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
+ struct lock_class_key *key, const char *lock_name);
#ifdef CONFIG_LOCKDEP
-#define __create_workqueue(name, singlethread, freezeable, rt) \
+#define alloc_workqueue(name, flags, max_active) \
({ \
static struct lock_class_key __key; \
const char *__lock_name; \
@@ -196,20 +290,20 @@
else \
__lock_name = #name; \
\
- __create_workqueue_key((name), (singlethread), \
- (freezeable), (rt), &__key, \
- __lock_name); \
+ __alloc_workqueue_key((name), (flags), (max_active), \
+ &__key, __lock_name); \
})
#else
-#define __create_workqueue(name, singlethread, freezeable, rt) \
- __create_workqueue_key((name), (singlethread), (freezeable), (rt), \
- NULL, NULL)
+#define alloc_workqueue(name, flags, max_active) \
+ __alloc_workqueue_key((name), (flags), (max_active), NULL, NULL)
#endif
-#define create_workqueue(name) __create_workqueue((name), 0, 0, 0)
-#define create_rt_workqueue(name) __create_workqueue((name), 0, 0, 1)
-#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1, 0)
-#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0, 0)
+#define create_workqueue(name) \
+ alloc_workqueue((name), WQ_RESCUER, 1)
+#define create_freezeable_workqueue(name) \
+ alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1)
+#define create_singlethread_workqueue(name) \
+ alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1)
extern void destroy_workqueue(struct workqueue_struct *wq);
@@ -231,16 +325,19 @@
extern int schedule_delayed_work_on(int cpu, struct delayed_work *work,
unsigned long delay);
extern int schedule_on_each_cpu(work_func_t func);
-extern int current_is_keventd(void);
extern int keventd_up(void);
-extern void init_workqueues(void);
int execute_in_process_context(work_func_t fn, struct execute_work *);
extern int flush_work(struct work_struct *work);
-
extern int cancel_work_sync(struct work_struct *work);
+extern void workqueue_set_max_active(struct workqueue_struct *wq,
+ int max_active);
+extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq);
+extern unsigned int work_cpu(struct work_struct *work);
+extern unsigned int work_busy(struct work_struct *work);
+
/*
* Kill off a pending schedule_delayed_work(). Note that the work callback
* function may still be running on return from cancel_delayed_work(), unless
@@ -298,7 +395,14 @@
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
#endif /* CONFIG_SMP */
+#ifdef CONFIG_FREEZER
+extern void freeze_workqueues_begin(void);
+extern bool freeze_workqueues_busy(void);
+extern void thaw_workqueues(void);
+#endif /* CONFIG_FREEZER */
+
#ifdef CONFIG_LOCKDEP
int in_workqueue_context(struct workqueue_struct *wq);
#endif
+
#endif